[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BZF2Y2T3SAHF1V0YFVVR1W":3,"skill-same:01M7BZF2Y2T3SAHF1V0YFVVR1W":82},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7BZF2Y2T3SAHF1V0YFVVR1W","reverse-engineer-anything",null,"Reverse engineer native, managed, Electron\u002FJavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.","Mostafa-Taher-git\u002FGreeneek","Mostafa-Taher-git","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F178865212?v=4","01M7BZ9VH4JJ0HP475H6CEJCGJ","Mostafa Taher Ahmed","01M7BZ9VHSXZMWJSX2W9MSCMB2",0,"MIT","https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: reverse-engineer-anything\ndescription: Reverse engineer native, managed, Electron\u002FJavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.\nmetadata:\n  version: \"62\"\n---\n\n# REA\n\nUse REA when a claim depends on a shipped binary or package, decompilation,\nrequested runtime evidence, or comparison with\nbehavior not established by available source. For ordinary analysis of a\ncomplete source repository, use normal repository tools and do not run REA\nreadiness or provider commands.\n\n## Connect only when needed\n\nInstalling this skill supplies instructions; it does not register the REA MCP\nserver, install analysis engines, or add tools to an already-running agent.\nThe exception is a Claude Code, Codex, or Cursor Marketplace plugin install:\nthe plugin bundles this skill and registers its own `rea` server, outside the\nstate that `rea setup` and `rea doctor` manage.\n\nIf REA tools are available and their registration is not known to be stale,\nproceed directly to the target. Do not run diagnostics or setup before every\ninvestigation. Use the connected server's actual tool list and input schemas;\na skill installed from repository main may describe capabilities absent from\nan older npm release. Keep complete inline Evidence when that server does not\nadvertise retained references.\n\nIf tools are absent, a call is blocked by the client, or a required provider is\nunavailable, read [connection and recovery](references\u002Fconnection-and-recovery.md).\nDiagnose the observed blocker, continue useful supported work, and resume the\noriginal task after repair. Client approval, shell PATH, registration and engine\navailability have different remedies; avoid repeating setup for all of them.\nIf the host times out without a REA result, do not repeat the unchanged call or\nassume work stopped. Read the recovery guide's deadline distinction before retrying.\nIf the MCP connection drops, retry that call once only when it is safe to\nrepeat or known not to have started. If it may already have changed the\ntarget, or it fails again, tell the user and ask them to restart the MCP\nclient. If REA could not start its connection, retry once, then tell the user\nand ask them to restart the MCP client. Do not retry a startup failure that\nreturns the same unchanged result. For plugin installs, follow\n[plugin recovery](references\u002Fconnection-and-recovery.md#rea-installed-as-a-client-plugin).\nFor setup-owned registrations, run `rea doctor` when REA could not start\nor tools stay missing after that restart. For `cleanup_incomplete`, a retryable\ncapacity limit, or `configuration_invalid`, follow the recovery guide's ladder\nbefore asking for a restart. Read that guide before a second repair attempt.\n\nChoose the installation owner before repairing registration. Plugin installs use\n[plugin recovery](references\u002Fconnection-and-recovery.md#rea-installed-as-a-client-plugin);\nonly setup-owned registrations use the guide's\n[registration repair plan](references\u002Fconnection-and-recovery.md#repair-registration-when-needed).\nA plugin-only doctor result of `missing` does not call for `rea setup`.\n\nREA setup never installs or upgrades Node.js, npm, Homebrew, Java, Ghidra, IDA,\nJADX, Kuna, Binwalk, or Unblob. Use existing prerequisites; do not install unrelated\nsoftware to repair MCP registration. For an unsupported client, use manual stdio\nregistration with an existing installation’s absolute runtime and entry script, or continue through the CLI.\n\nA concrete CLI fallback for an operator-supplied JavaScript tree or ASAR is:\n\n```bash\nnpx -y rea-agents@latest analyze-javascript-application \u002Fabsolute\u002Fpath\u002Fto\u002Fapp --json\n```\n\nNo MCP registration or native engine is required. Read the returned Evidence,\ngraph, limitations, and unknowns with the same care as an MCP result; the CLI\nreturns the Evidence record directly. This fallback does not establish that\nMCP is configured. Native CLI tasks still require their selected engine.\nPrefer an existing `rea` CLI. When none is installed and REA package acquisition\nis within the authorized scope, use `npx -y rea-agents@latest` in its place from a\ntrusted directory outside the target project, with absolute target paths. Managed\nsetup binds the current installation directly; retain its runtime and package\ncache entry, or restore that installation before repairing its registration.\nFor setup-owned registration, configuration repair starts with a read-only setup plan; show paths, backups and\nskill replacement before applying authorized changes. Preserve existing approval\nand target-execution boundaries.\n\n## Route the target first\n\nChoose the first tool from the target the user supplied. Use `open_binary` for\nactive-target native or archive workflows; target-free tools take their own\nexplicit path or endpoint and do not need it.\n\n- ASAR or extracted JavaScript\u002FElectron tree:\n  `analyze_javascript_application`.\n- Archive\u002Fpackage member inventory (ZIP\u002FAPK\u002FIPA\u002FMSIX\u002FAppX, DMG, or a PyInstaller\n  executable): `open_binary` with the supplied local path; use `inspect_artifact`\n  when its graph and findings help answer the question. A PyInstaller CArchive\n  is the application layer; the bootloader is only the native prefix. Start with\n  `detail: \"summary\"` for large inventories, then use retained inventory views\n  for selected member fields\u002Fpages. A complete small inventory can cost less\n  than extra calls and schemas. Runtime options are metadata, not files.\n  Compact delivery still inventories and hashes members. See the\n  [Python packaged applications guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpython-packaged-applications.md).\n- Bun `--compile` executable: `open_binary`, then `inspect_artifact`; the Bun\n  module graph is the application layer. Extract stored modules and analyze the\n  JavaScript. See [Bun standalone executables](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fbun-standalone.md).\n- Deno `deno compile` executable: `open_binary`, then `inspect_artifact`; the\n  embedded virtual filesystem is the application layer. Extract stored files and\n  analyze compatible JavaScript. Environment-file values and CA certificate bytes\n  are retained in local Evidence with their counts and byte lengths. The npm\n  snapshot length is reported and not decoded, and the executable is not run. See\n  [Deno compile executables](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fdeno-standalone.md).\n- Apple app plist, Interface Builder, asset catalog, or keyed archive resources:\n  `open_bundle_resources`, then the selected resource tool. This does not\n  require `CFBundleExecutable` or a deep provider. Resource sessions have no\n  executable digest or binary snapshot; use `open_binary` for native code.\n- Android APK code, classes, methods, or incoming references:\n  `inspect_android_package`, then focused Android tools when advertised.\n  Archive member inventory still uses the archive route above.\n- Managed PE\u002FCLI assembly: `inspect_managed_artifact`.\n- Firmware image: `inspect_firmware_regions` when advertised. Use\n  `extract_firmware` when extraction is requested, with a caller-selected new\n  absolute output directory. These tools use caller-supplied Binwalk\u002FUnblob on\n  Linux; see the [firmware guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Ffirmware\u002Ffirmware-analysis.md).\n- ESP32-family app or bootloader image (`0xE9` magic): `inspect_artifact`\n  without a provider; see the ESP section of `references\u002Fnative-and-artifacts.md`.\n- .NET NativeAOT PE\u002FELF: native Ghidra analysis. Native code can yield pseudocode;\n  consult the NativeAOT workflow in `references\u002Fnative-and-artifacts.md` for\n  optional metadata recovery and its supported host\u002Flayout boundary.\n- Native program behavior, live calls, instrumentation, or command-run effects:\n  choose the matching [native runtime workflow](references\u002Fruntime-observation.md#native-runtime-questions).\n  `open_binary` and `trace_native_values` establish static facts; they do not\n  observe execution. Runtime tools have distinct launch, attach, mutation and\n  cleanup effects, and do not require a preliminary static session unless their\n  own contract says so.\n- User-owned browser page already open: `list_browser_targets`.\n- Passive traffic capture of a SPA: the default scope is the page's own origin,\n  and data APIs usually live on another origin. Discover API origins from\n  absolute URLs in loaded bundles or script text via JavaScript analysis tools\n  (another passive capture without those origins still scopes to the page\n  origin, and `completeness.excluded` counts lack URLs). Pass both the page\n  origin and those API origins in `allowed_origins` — the list replaces the\n  default scope — and read `completeness.excluded` before reporting that an\n  API is absent. For long captures with body shapes, use\n  `export_evidence_bundle` instead of expecting an inline result.\n- Browser action the agent must perform (click, type, navigate):\n  `capture_browser_scenario` with declared actions. See\n  [runtime observation](references\u002Fruntime-observation.md) for connect\u002Flaunch\n  and the focused follow-up browser tools.\n- Agent environment (AgentEnv bundle) of a web application: read\n  [environments](references\u002Fenvironments.md) before recording; it records with\n  `capture_browser_scenario` and writes the bundle with `export_environment_bundle`.\n- Task for a desktop application's exported environment, from a\n  `capture-desktop-application` folder: read\n  [desktop application tasks](references\u002Fenvironments.md#tasks-for-a-desktop-application-environment).\n- Environment of a Linux desktop app with a task, from a request such as\n  \"build me an Inkscape environment where the agent changes a poster's\n  headline\": read [desktop builds](references\u002Fdesktop-build.md). You drive the\n  app on a build computer from `start_build_computer`, then export and witness.\n- Fiddler Everywhere traffic or a native `.saz` capture: read the\n  [Fiddler workflow](references\u002Fruntime-observation.md#fiddler-everywhere-traffic-debugging).\n  Inspect saved SAZ with `inspect_web_network_capture` and `format: \"saz\"`;\n  connect Everywhere's separate MCP server for live traffic.\n- Retained HAR\u002FSAZ\u002Fnative mitmproxy\u002Faioquic qlog capture: `inspect_web_network_capture`. Select\n  original record ordinals when useful; inspect producer fields and byte\u002Fnumber\n  sidecars without fetching recorded URLs or claiming live attribution. HAR\u002FSAZ\u002Fqlog\n  old-generation heap is `REA_CAPTURE_DECODER_OLD_GENERATION_MIB` (default 192 MiB,\n  floor 8, maximum 16384), set where REA starts. Host memory and `NODE_OPTIONS` do not\n  raise it. See\n  [historical captures](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fweb\u002Fweb-network-captures.md) for the exact upstream\n  profile and credential exclusions. Qlog support starts with aioquic 1.5.0\n  JSON 0.3; stream coverage and endpoint loss declarations do not recover bodies\n  or establish network loss. Prefer detail summary, then kind qlog trace\u002Fstream\n  pages; select one trace, stream ID and direction for contribution\u002Frange pages.\n  Facts retain all-recorded-events-before-selection scope. Other qlog layouts\n  and PCAP correlation are unsupported.\n- User-owned Electron runtime already open: `list_electron_targets`. Before an electron-main Inspector attempt, check packaged fuses with `inspect_electron_fuses`; disabled `EnableNodeCliInspectArguments` means the app ignores `--inspect`.\n- Shipped application exposure for a local `.app`, install directory, ASAR, or executable: `audit_release_exposure` \u002F `rea audit-release-exposure`. Each check has a stable id, a status, and fixed remediation. Unknown and unassessed checks stay in the report. This does not establish that an application is secure. Credential-marker hits report the rule id and location only. See [release exposure](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Frelease-exposure.md).\n- Packet-field discovery: `inspect_packet_fields` searches installed protocols\n  and field names\u002Ftypes before choosing fields for `inspect_packet_capture`.\n  Query\u002Fpage the relevant records; registrations do not establish observed traffic.\n- Recorded packet captures: `inspect_packet_capture` with selected TShark fields,\n  display filters and decode-as rules. Requires Linux, util-linux prlimit and\n  TShark 4.x on an absolute `PATH` entry or via the optional absolute\n  `REA_TSHARK_COMMAND` override; see\n  [capture guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fdata\u002Fpacket-captures.md).\n  Packet limits count input packets before filtering. Output defaults to 50 matching\n  frames; use `match_offset` \u002F `match_limit` for later pages, or explicit null\n  limit for complete matching output. Preserve the source digest across pages.\n  This does not perform live capture.\n  For address\u002FDNS\u002FSNI\u002Fprotocol summaries use `inspect_pcap_capture` with MCP\n  detail summary, then retained kind pcap pages. Requires Wireshark 4.x tshark\n  and capinfos, with Linux prlimit or Windows Job Objects; see\n  [packet summaries](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fdata\u002Fpcap-analysis.md).\n  Select an exact DNS question for address pages; page exhaustion does not prove\n  network completeness. This reads recordings and does not acquire traffic.\n- Decoder discovery: `inspect_signal_decoders` searches installed decoder IDs\n  or selected decoder help, including channels and options. Query and page the\n  relevant details before choosing settings; this does not scan hardware.\n- Recorded logic\u002Fsignal traces: `decode_signal_recording` with explicit decoder,\n  channel and protocol settings. On Linux with util-linux prlimit, supply sigrok-cli 0.7.2 through\n  `REA_SIGROK_COMMAND`; see [recording guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fsignals\u002Fsignal-recordings.md).\n  Output defaults to 50 literal lines; select annotation classes and page with\n  `line_offset` \u002F `line_limit`, or explicit null for all remaining output.\n  Window counts are display lines, not annotations or samples. Preserve source digests across pages.\n  This reads existing files; it does not acquire hardware signals.\n- Explicit local WebAssembly artifact: `inspect_wasm_artifact`. Supply WABT 1.0.42\n  through `REA_WABT_BIN_DIRECTORY`; retain exact byte\u002Ftool identity and decoded WAT.\n  Select JavaScript glue and candidate paths explicitly and preserve URL\u002Fpath\n  ambiguity. No implicit fetch or target execution; WAT is not original source.\n  See the [WASM guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fwasm\u002Fwasm-artifacts.md).\n- Explicit local Android APK (or ZIP\u002FAAB) signing: `inspect_apk_signature`.\n  Prefer its summary or selected signer\u002Fdigest\u002Flineage page; retain complete\n  Evidence and use `inspect_analysis_view` kind `apk-signature` for follow-ups.\n  Reports which schemes are present (v1 JAR, v2, v3, v3.1), each signer's\n  certificate SHA-256 fingerprint (v1 included, from its PKCS#7 block), v3 key-rotation lineage, source stamp, and\n  whether each signed digest still matches the bytes (self-consistency). This\n  is identity and integrity, not a trust or authenticity verdict.\n  See the [APK signature guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fapk-signature.md).\n- Explicit local EVM bytecode carrier: `inspect_evm_interface` with caller-selected\n  `raw` or `hex` encoding. The owned worker deadline is `timeout_ms` (default\n  30000 ms, range 1..2147483647, next call). Select byte, address-space and CPU\n  allowances separately through `producer_limits`; tighter inherited OS limits\n  remain enforced, and the 256 MiB worker heap is independent. Preserve\n  carrier\u002Fdecoded digests and treat selectors,\n  argument strings and mutability as inferred candidates; this performs no chain\n  lookup or target execution. For the complete inferred interface without hex or\n  duplicate stdout, discover support and select `detail: \"summary\"`; complete\n  Evidence stays retained under its original identity. Use the returned\n  `parent_evidence_id` for exact function or `bytecode_hex`\u002Fstdout\u002Fstderr pages.\n  Candidate coverage does not establish interface completeness. See the\n  [EVM bytecode guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fevm\u002Fevm-bytecode.md).\n- Embedded Go compiler, module, build-setting metadata, or static `(ptr, len)`\n  string literals: `inspect_go_binary` with the explicit local file (pass\n  `include_string_literals: true` and optional `max_string_literals` for bounded\n  inferred static string-header recovery, and page retained rows with\n  `inspect_analysis_view` kind `go` collection `string_literals`). This built-in\n  target-free inspection requires no Go installation or disassembler. Preserve\n  raw module bytes and source ranges; absent metadata does not prove a binary is\n  not Go, static string recovery excludes compiler-inlined stack or immediate\n  strings, and unparsed text records remain explicit. See the\n  [Go binary guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fgo-binaries.md).\n- Embedded CUDA\u002FHIP code objects: `inspect_gpu_code_objects`; inventory targets\n  first, then decode selected payloads and query retained GPU Evidence.\n- Bundled GGUF or safetensors model declarations: `inspect_model_artifact`\n  with the explicit local file. Default header hashing leaves full-file identity\n  unknown; `hash: \"full\"` additionally reads all weights for SHA-256. MCP returns\n  retained summaries; optional `view` selects one page in the initial call. Use\n  `inspect_analysis_view` kind `model-artifact` for\n  batched metadata keys, tensor names or type totals, selected fields and pages.\n  Preserve header-scoped indices and array preview omissions; do not infer model\n  behavior from declared architecture or tensor types. See the\n  [model file guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fmodel-artifacts.md).\n- Unity IL2CPP names, member owners and string literals from `global-metadata.dat`:\n  `inspect_il2cpp_metadata` with the explicit local file; MCP defaults to compact\n  counts. Query sections, images, types, methods, fields, properties, events,\n  parameters or string_literals through `inspect_analysis_view`\n  with the returned `parent_evidence_id`, using exact filters, batch indices and\n  selected fields. Parameters accept `method_indices`, avoiding a scan of all\n  parameter pages. Missing collections in historical Evidence remain unknown.\n  Versions 24, 27, 29, 31 and 39; no Unity, IL2CPP\n  binary or disassembler is run. Unrecognized magic (possibly encrypted) and\n  other versions are unsupported. Optional matching `binary_path` enables static native addresses and type references; query `method_addresses` with indices or addresses\u002Fstates, preserving every shared-body method and both artifact identities. Without a linked binary native counts remain unknown. Byte-pattern fallback is inferred; no runtime behavior or same-build pairing is proved. See the\n  [IL2CPP metadata guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fil2cpp-metadata.md).\n- Embedded cargo-auditable Rust dependency metadata: `inspect_rust_binary`\n  with the explicit local ELF, PE, or thin Mach-O file. This built-in\n  target-free inspection requires no Rust installation or disassembler. Preserve\n  package order, dependency indices, and the section file range. A missing\n  `.dep-v0` section is null metadata, not proof the binary has no dependencies.\n  A rustc commit hash is an inference from a read-only `\u002Frustc\u002F\u003C40-hex>\u002F` path.\n  For selected crates, use `view: {collection: \"packages\", names: [...],\n  fields: [\"name\", \"version\", \"source\"]}` on the first call; explicitly include\n  `dependencies` for direct index references. Use `detail: \"summary\"` for counts\n  and ranges, or retained `inspect_analysis_view` Rust package\u002Fedge pages for\n  subsequent filters. Keep the complete parent Evidence accessible; CLI compact\n  delivery requires `--evidence_output`.\n  See the\n  [Rust binary guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Frust-binaries.md).\n- PE Authenticode certificate table: `inspect_pe_certificates` with the explicit\n  local PE32\u002FPE32+ file. This built-in target-free inspection requires no\n  Windows SDK. Preserve WIN_CERTIFICATE ranges, types, payload SHA-256, and\n  PKCS#7 signer\u002FX.509 identity fields, including `subject_key_identifier_hex`\n  when the signer uses that form. A missing security directory is observed\n  absence of that table, not proof the image is unsigned in every catalog sense.\n  Signatures are not verified. See the\n  [PE certificate guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpe-certificates.md).\n- PE import and delay-load tables: `inspect_pe_imports` with the explicit\n  local PE32\u002FPE32+ file. This built-in target-free inspection requires no\n  Windows SDK. Preserve DLL names, named and ordinal functions, ILT\u002FIAT RVAs,\n  delay-load descriptors, and the pefile import hash of the standard import\n  table. A missing import directory is observed absence of that table, not\n  proof the image never imported APIs through another table. Bound snapshots\n  and loaded IAT contents remain unobserved. See the\n  [PE import guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpe-imports.md).\n- Windows Shell Link shortcuts: `inspect_windows_shortcut` with the explicit\n  local `.lnk` file. This built-in target-free inspection requires no Windows\n  SDK or COM. Preserve header flags and FILETIMEs, IDList items, LinkInfo\n  volume and network names, StringData arguments and icon location, ExtraData\n  signatures, and Tracker droid facts labelled derived. Unknown IDList items\n  and ExtraData signatures stay raw with SHA-256. The target path is not\n  resolved or executed. See the\n  [Windows shortcut guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fwindows-shortcut.md).\n- PE TLS callbacks and load configuration: `inspect_pe_load_config` with the\n  explicit local PE32\u002FPE32+ file. This built-in target-free inspection requires\n  no Windows SDK. Preserve callback VAs as strings with their RVA, file offset\n  and section, and the size-covered security cookie, SafeSEH, CFG,\n  EH-continuation and XFG fields. Guard-flag mitigation claims are inferred\n  linker declarations, not proof of enforcement. A missing directory is observed\n  absence of that declaration. See the\n  [PE load configuration guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpe-load-config.md).\n- ELF, PE, and Mach-O hardening: `inspect_binary_hardening` with the explicit\n  local file. This built-in target-free inspection requires no pwntools or other\n  host tool. One image per Mach-O slice. Each property is `enabled`, `disabled`,\n  `partial`, `unknown`, or `not_applicable`, with the header field or import\n  behind it. A missing stack-protector or fortify import is `unknown`, not\n  proof the protection was omitted. Authenticode and Mach-O code signatures\n  report presence, not validity. Hardened runtime stays unknown and names\n  `inspect_signature`. The image is not executed. See the\n  [binary hardening guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fbinary-hardening.md).\n- ELF note tables: `inspect_elf_notes` with the explicit local ELF32\u002FELF64\n  file. This built-in target-free inspection requires no disassembler. Preserve\n  PT_NOTE and SHT_NOTE ranges, owners, types, descriptor SHA-256, and GNU\n  build-id or ABI-tag fields. A missing table is observed absence of those\n  declarations, not proof the image never carried notes. See the\n  [ELF notes guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Felf-notes.md).\n- Code that runs before `main` or at exit in ELF or Mach-O:\n  `inspect_native_initializers` with the explicit local file (and\n  `architecture` for a universal Mach-O). This built-in inspection requires no\n  disassembler. Preserve slot and target addresses, the `resolution` of each\n  entry, and its limitations. An `unresolved` slot is not a zero pointer, and a\n  missing table is not proof that no constructor exists. See the\n  [initializer guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fnative-initializers.md).\n\n- ELF unwind function ranges: `inspect_elf_unwind_ranges` with the explicit\n  local ELF32\u002FELF64 file. This built-in target-free inspection requires no\n  disassembler. Preserve FDE start, end, size, containing section, exact\n  symbol name, CIE index, LSDA, and personality. Page with `offset` and\n  `limit`. A missing `.eh_frame` is observed absence of that declaration,\n  not proof the image has no functions. `.debug_frame` is reported present\n  or absent and is not decoded. CFA instructions are counted and not\n  evaluated. See the\n  [ELF unwind ranges guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Felf-unwind-ranges.md).\n- Apple `.ips` crash reports: `inspect_apple_ips` with the explicit local\n  file. This built-in target-free inspection requires no Xcode, atos, or\n  pwntools. Preserve first-line metadata, `bug_type` as a string, process and\n  exception facts, lossless integer registers, usedImages UUIDs, and\n  documented classification matches. Only `bug_type` `\"309\"` yields a crash\n  body; other types, including `\"288\"` stackshots, return no crash result.\n  Select an optional `join_path` for UUID-and-architecture matching to one\n  local Mach-O or dSYM; preserve slice identity and unjoined reasons. Joined\n  static addresses do not resolve function names or dSYM symbols. See the\n  [Apple IPS guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fapple-ips.md).\n- Linux kernel module metadata: `inspect_kernel_module` with the explicit local\n  ELF32\u002FELF64 relocatable file. This built-in target-free inspection requires\n  no Linux host or `modinfo`. Preserve `.modinfo` key order and duplicate keys,\n  `__versions` CRC hex, section file ranges, and the appended signature\n  trailer's PKCS#7 SHA-256. A missing section is observed absence when section\n  names are known, not proof the module never carried that metadata.\n  `struct module` is not decoded. The signature is not validated. gzip, xz, and\n  zstd containers are unsupported; decompress into a separate file with an\n  external codec utility, then inspect the decompressed `ET_REL` image. See the\n  [kernel module guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fkernel-modules.md).\n- Linux kernel version and build config (`CONFIG_*` options such as\n  `CONFIG_SECURITY_SELINUX`): `inspect_kernel_build_config` with the explicit\n  local `vmlinux`, raw `Image`, x86 `bzImage`, or `configs.ko`. This built-in\n  target-free inspection requires no Linux host or `extract-ikconfig`. Preserve\n  the banner version, config SHA-256, option count, and value kinds; use `name`\n  for one option. An `IKCFG_ST` string is a config only with a valid gzip member\n  and `IKCFG_ED`. An absent config may mean the kernel was built without\n  `CONFIG_IKCONFIG`. Non-gzip payloads are unsupported; decompress externally,\n  then inspect the result. See the\n  [kernel build config guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fkernel-build-config.md).\n- CPython 3.7–3.13 `.pyc` header, nested marshal code objects and bytecode\n  identity: `inspect_python_pyc` with the explicit local file. This built-in\n  target-free inspection requires no Python installation. Preserve magic,\n  PEP 552 hash or mtime\u002Fsize, nested names, and bytecode SHA-256. Bytecode is\n  not decompiled, and a decoded header does not prove the matching `.py` is\n  present. See the\n  [CPython pyc guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpython-pyc.md).\n- Erlang BEAM IFF container: `inspect_erlang_beam` with the explicit local\n  `.beam` file. This built-in target-free inspection requires no Erlang\n  installation. Preserve chunk names, atom order, export\u002Fimport\u002Flambda tables,\n  and the Code header. For selected facts, prefer `detail: \"summary\"` plus a\n  `beam` view (collection, names\u002Findices, fields and paging), retaining the full\n  Evidence. CLI summary requires `--evidence_output`. Missing table counts stay\n  null; decoded empty tables count zero. Bytecode is not executed. See the\n  [Erlang BEAM guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Ferlang-beam.md).\n\n- Explicit local SQLite database snapshot: `inspect_sqlite_database`. Inspect\n  with Node.js 24.x >=24.15 or 26+ providing native SQLite limits. Read schema\n  first (compact inventory by default), or select an exact ordinary table\n  and `columns` when rows are needed. Defaults are selected-table schema and\n  20 rows; request `schema_scope: \"database\"` for the complete stored schema. Preserve both database and existing sibling WAL identity; row samples\n  report truncation and have unspecified order. Use a quiescent snapshot rather\n  than assuming a live database\u002FWAL pair was copied atomically. See the\n  [SQLite guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fdata\u002Fsqlite-databases.md).\n- Explicit Linux ELF file for offline layout, symbols, relocations or static\n  mitigation evidence: `inspect_binary_layout`. This target-free operation uses\n  caller-supplied pwntools without opening a disassembler database. Preserve its\n  raw locations and inference\u002Fcoverage limits; see the\n  [offline binary guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fbinary-diagnostics.md).\n- Supplied Linux x86-64 ELF core: `inspect_recorded_crash`. Read every recorded\n  thread, raw note and source-bound register without opening a live target.\n  Historical PIDs do not select live processes. Request `include_debugger_context`\n  only when core-only mapping candidates help; see the\n  [recorded crash guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Frecorded-crashes.md).\n- PE resource type\u002Fname\u002Flanguage trees and static icon group references:\n  `inspect_pe_resources` with an explicit path. This portable operation requires\n  no active target or engine; opaque payloads retain file ranges and SHA-256.\n- PE export directories and ELF dynamic-symbol exports: `inspect_native_exports`\n  with an explicit path; portable, no active target or engine.\n- Native executable, library, or analysis database: `open_binary`, then\n  use focused analysis tools directly; call `binary_overview` when metadata or\n  inventory context is useful and available from the selected provider.\n\nFor an existing IDA MCP configuration, use `open_binary` with the original\ninput binary and `provider_id: \"ida\"`; do not pass an `.idb` or `.i64` database.\nThe legacy attached profile binds the already-open GUI input by SHA-256 and\nleaves its database open. The modern headless profile creates and closes an\nowned private database without saving. Installation and registration reuse\n[mrexodia\u002Fida-pro-mcp](https:\u002F\u002Fgithub.com\u002Fmrexodia\u002Fida-pro-mcp); see the\n[IDA provider guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fproviders\u002Fida-provider.md).\nFor migration to the separate native IDA MCP plugin, follow the guide's\n[legacy attached migration](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fproviders\u002Fida-provider.md#migrate-a-legacy-attached-registration).\nReplace the upstream registration explicitly; modern mrexodia tools are not the\nnative profile. Native attachment preserves the database but does not provide\ndirect callers; check session availability and the guide's verification limits.\nProceed directly to `analyze_function`, pseudocode, or function\u002Fstring searches\nafter opening; IDA does not supply `binary_overview`. Consult session availability\nwhen composing broader workflows. Modern direct callers and unsupported dossier\nfacets remain unknown; live IDA results are not replayed from snapshots.\n\nWith `REA_KUNA_COMMAND` configured, `provider_id: \"kuna\"` answers procedure\nlists, lookups, pseudocode, assembly and `analyze_function` from Kuna's cached\nwhole-program export. Callers\u002Fcallees use a separate body-free graph shared by\nthe session; `xrefs` returns exact-address incoming sites and filters forwarding\naliases. These queries and inventory lookups do not trigger a C export. Indirect\ntargets remain unknown and can make relationship coverage partial. Reference\ncaches expire on close; a fresh CLI process repeats the native reference walk.\nTyped references, CFG, raw-memory tools and annotations remain unsupported. A cold first\nanswer can come from a single-function run (its limitations say so); assembly\nwaits for the export. For pseudocode and assembly, `raw_result.source` names the\ncached `.c`\u002F`.asm` file and byte span, which you may search directly instead of\ncalling per function. See the\n[Kuna provider guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fkuna-provider.md).\n\nIf the user says only \"my app\" without a name, path, or target already selected\nfor this task, ask which app before searching for artifacts. Paths in unrelated\nsaved reports and nearby test fixtures do not select the user's target. Resolve\nan actual human-readable app name to one clear installed artifact when possible;\nask when matches are ambiguous. Never choose an example app on the user's behalf.\n\nIn a target-free session, use `open_binary` to bind any archive\u002Fpackage or\nnative target whose analysis tool operates on the active target. Do not call an\nunadvertised tool; inspect `binary_session` with `{}` and its\n`result.tool_availability` for availability reasons and remediation. Expand each\ngroup's `names` into entries, inheriting the inventory-level client requirements\nunless the group overrides them. The grouped name union is the complete tool\ninventory; use `tools\u002Flist` for canonical tool schemas. The default summary keeps\neach provider candidate's availability and target-support status, code and\nreason; `omitted_fields` lists what it leaves out. Request `{\"detail\": \"complete\"}`\nonly when you need an unavailable candidate's remediation, provider\ndiagnostics, candidate capability sets, or tool surface, effect and annotation\nflags; in those closed flag vocabularies, listed\nflags are true and omitted known flags are false. Provider candidate facts\ndescribe possible providers, while top-level session capabilities describe the\ncurrent route and `analysis_provider_binding` names the selected provider. Do\nnot treat those scopes as interchangeable.\n\nFor editable Ghidra analysis that must survive a later agent process, select\nthe [owned Program checkpoint workflow](references\u002Fnative-and-artifacts.md#continue-editable-ghidra-analysis-across-processes)\nbefore making metadata edits. It is separate from Evidence\u002FUnknown persistence.\n\nFor a Ghidra startup timeout on a large native target, follow\n[deadline recovery](references\u002Fnative-and-artifacts.md#ghidra-startup-deadline-recovery)\nbefore abandoning deep analysis or repeating the same cold import. The default\n330 seconds can be changed for new startup attempts through\n`update_analysis_settings` using `ghidra.startup_timeout_ms`. Changing the\nserver's launch environment instead requires a new REA process.\n\n## Work summary-first\n\nStart with the default result and use its inline Evidence and graph context.\nFor a JavaScript application or ELF layout whose size is unknown or large,\ncall `analyze_javascript_application` or `inspect_binary_layout` with\n`\"detail\": \"summary\"`, then inspect the retained `parent_evidence_id` with\n`inspect_analysis_view`. Over MCP, `analyze_function` is summary-first without\na flag: its default reply is the summary, and the complete dossier stays\nretained under `parent_evidence_id` for facet paging. Pass that ID as a\n`retained-evidence` reference to `compare_functions`, or inside\n`match_native_functions` `left_observations`\u002F`right_observations` or\n`build_call_path.functions`; request `\"detail\": \"complete\"` only when the\ndossier must travel inline.\nUse the same exact-reference form in other advertised logical Evidence inputs,\nincluding optional sources, arrays and nested sources across domains. Each\nsource can independently be inline or retained; preserve its source identity,\ncoverage, partial facts and unknowns. A summary or inspection page has its own\nEvidence ID: use `normalized_result.parent_evidence_id` when the consumer needs\nthe complete source. For portable CLI follow-ups, commands advertising\n`--evidence-bundle` resolve references from that selected exported bundle.\nSee [Evidence composition](references\u002Fevidence-workflows.md) for scope and\nrecovery; file selectors are supported only where explicitly advertised.\nPage module identities and select the returned `node_id` before requesting an\nitem; a single file path can represent several graph roles. Do not repeat an\nidentical analysis or rejected call without a changed input or resolved blocker.\nRecheck session state when a lifecycle change makes that status useful.\nMake a focused follow-up only when the\nreturned result leaves a specific question unanswered.\n\nIf MCP reports `resource_constraint` with `details.resource: \"transport\"`, call\n`inspect_analysis_view` with its reported same-session Evidence reference for a\nsummary, one section\u002Fmodule, or a stable page. Use `trace_application_feature`\nonce a seed is known, or call `export_evidence_bundle` to write the complete\nsession to a selected path. The analysis remains complete in the ledger; avoid\nrepeating it merely to request the same oversized response. Complete CLI JSON\noutput also streams without a single MCP frame.\n\nWhen the retained parent ID is unknown, use `get_evidence_bundle` with\n`detail: \"summary\"` and exact filters for operation, target SHA-256,\nanalysis-profile digest or canonical procedure address. Select its returned\nEvidence ID for the next view instead of requesting the complete bundle. When\nthat record has no supported view (for example an annotation), read it with\n`detail: \"records\"` and an `evidence_id` filter; `missing_evidence_links`\nnames linked sources this session does not retain.\n`retention: \"complete-record\"` means the whole record is stored; native\nvalue-flow truncation and unknown metadata remain separate. For an exported\nportable bundle, use `rea inspect-evidence-bundle` with JSON containing `path`,\n`detail: \"summary\"` and the same `filters`. Reading that file still requires\nvalidating its full contents within the local memory budget.\n\nA client can also truncate a successful tool result without a REA transport\nerror. Treat that preview as incomplete; use the retained parent ID for smaller\nviews or export when the full record is needed. Do not parse the preview as\ncanonical JSON or repeat the producer. For JavaScript, read the\n[module-view and trace recipes](references\u002Fjavascript-applications.md) before\ndrilling into a large graph; a broad bidirectional trace can expand unrelated\ncontainment relationships even after summary analysis.\n\nEvery conclusion must distinguish observations, inferences, and unknowns. Cite\nEvidence IDs, preserve limitations and incomplete coverage, and never imply\nthat static analysis observed execution. Runtime requests execute the declared\ntarget and lifecycle; do not broaden the target or action beyond those fields.\n\nWithin the user's requested investigation, call available analysis tools\ndirectly. REA does not require permission grants or per-call approval flags.\nThe agent client can independently require approval. Follow the declared request\nscope and the host's actual access requirements; use the recovery guide for an\nobserved client-policy rejection.\n\n## Plan broader investigations\n\nFor requests that span multiple features or subsystems, use a staged workflow:\n\n1. Turn the request into a checklist of questions and the evidence each answer\n   needs. Resolve target identity and constraints from the conversation and\n   workspace before asking for information again.\n2. Inspect the current REA session, artifact identity, saved analysis database,\n   bookmarks, and prior evidence. Reuse matching state; do not open duplicate\n   sessions or repeat identical analysis.\n3. Start with the smallest useful overview or inventory. Follow each question\n   from its entry point through relevant data and state changes to its result.\n   Batch related operations around a specific hypothesis, then expand only when\n   the returned evidence leaves a concrete gap.\n4. Inspect relevant packaged resources and configuration alongside code when\n   they affect the question. Use format-aware inventory and parsers; do not\n   infer behavior from filenames, strings, or layout alone.\n5. Corroborate a conclusion with the evidence type it requires. Use runtime\n   observation only when static evidence cannot answer the question and the\n   required host runtime and OS access are available. For JavaScript behavior,\n   run probes against the actual app through the available browser, Electron,\n   or process capture workflow.\n6. Decompose work into independent questions. When parallel workers are\n   available and the questions do not depend on one another, assign distinct\n   scopes, point workers to existing evidence, and ask them to return sources,\n   conclusions, and unresolved gaps. Otherwise, work sequentially.\n7. Keep a concise finding ledger linking each conclusion to Evidence IDs,\n   confidence\u002Fevidence type, search boundary, and remaining unknowns. Update\n   the shared index or investigation report so later passes can reuse results.\n\nBefore finishing, revisit the original checklist. Mark each question as\nanswered, partially answered, or unresolved based on its evidence; keep\nbounded negative searches bounded, and do not describe a broad investigation\nas complete while required questions remain open.\n\n## Read only the relevant guide\n\n- Native binaries, managed assemblies, archives, and extraction:\n  [references\u002Fnative-and-artifacts.md](references\u002Fnative-and-artifacts.md)\n- ASARs, extracted JavaScript, feature tracing, and version comparison:\n  [references\u002Fjavascript-applications.md](references\u002Fjavascript-applications.md)\n- Android APK declarations, classes, methods, and static references:\n  [references\u002Fandroid-applications.md](references\u002Fandroid-applications.md)\n- Native instrumentation, debugger and process capture; browser\u002FElectron\n  observation; static\u002Fruntime comparison:\n  [references\u002Fruntime-observation.md](references\u002Fruntime-observation.md)\n- Evidence paging, comparisons, residual unknowns, and verification:\n  [references\u002Fevidence-workflows.md](references\u002Fevidence-workflows.md)\n- Agent environments (AgentEnv bundles) of a web application, recorded from\n  a live instance or a HAR:\n  [references\u002Fenvironments.md](references\u002Fenvironments.md)\n- Tasks for a desktop application's exported environment:\n  [references\u002Fenvironments.md](references\u002Fenvironments.md#tasks-for-a-desktop-application-environment)\n- A desktop app environment from a request, built and witnessed on build\n  computers: [references\u002Fdesktop-build.md](references\u002Fdesktop-build.md)\n\n## Finish the task\n\nExplain findings in plain language and tie them to returned evidence. When the\nuser asks to build something, use normal coding tools and separate observed\nbehavior from design choices. Close an opened native session with\n`close_binary` when its engine is no longer needed. Evidence references and Unknown\nhistory remain in memory on the same MCP connection. End the investigation with\n`reset_investigation`; supply `save_path` to checkpoint the complete bundle before\nclearing. Import the saved bundle to restore original references and Unknown\nhistory in a new process. Retention is bounded and is not automatic persistence.\n","# REA\n\nUse REA when a claim depends on a shipped binary or package, decompilation,\nrequested runtime evidence, or comparison with\nbehavior not established by available source. For ordinary analysis of a\ncomplete source repository, use normal repository tools and do not run REA\nreadiness or provider commands.\n\n## Connect only when needed\n\nInstalling this skill supplies instructions; it does not register the REA MCP\nserver, install analysis engines, or add tools to an already-running agent.\nThe exception is a Claude Code, Codex, or Cursor Marketplace plugin install:\nthe plugin bundles this skill and registers its own `rea` server, outside the\nstate that `rea setup` and `rea doctor` manage.\n\nIf REA tools are available and their registration is not known to be stale,\nproceed directly to the target. Do not run diagnostics or setup before every\ninvestigation. Use the connected server's actual tool list and input schemas;\na skill installed from repository main may describe capabilities absent from\nan older npm release. Keep complete inline Evidence when that server does not\nadvertise retained references.\n\nIf tools are absent, a call is blocked by the client, or a required provider is\nunavailable, read [connection and recovery](references\u002Fconnection-and-recovery.md).\nDiagnose the observed blocker, continue useful supported work, and resume the\noriginal task after repair. Client approval, shell PATH, registration and engine\navailability have different remedies; avoid repeating setup for all of them.\nIf the host times out without a REA result, do not repeat the unchanged call or\nassume work stopped. Read the recovery guide's deadline distinction before retrying.\nIf the MCP connection drops, retry that call once only when it is safe to\nrepeat or known not to have started. If it may already have changed the\ntarget, or it fails again, tell the user and ask them to restart the MCP\nclient. If REA could not start its connection, retry once, then tell the user\nand ask them to restart the MCP client. Do not retry a startup failure that\nreturns the same unchanged result. For plugin installs, follow\n[plugin recovery](references\u002Fconnection-and-recovery.md#rea-installed-as-a-client-plugin).\nFor setup-owned registrations, run `rea doctor` when REA could not start\nor tools stay missing after that restart. For `cleanup_incomplete`, a retryable\ncapacity limit, or `configuration_invalid`, follow the recovery guide's ladder\nbefore asking for a restart. Read that guide before a second repair attempt.\n\nChoose the installation owner before repairing registration. Plugin installs use\n[plugin recovery](references\u002Fconnection-and-recovery.md#rea-installed-as-a-client-plugin);\nonly setup-owned registrations use the guide's\n[registration repair plan](references\u002Fconnection-and-recovery.md#repair-registration-when-needed).\nA plugin-only doctor result of `missing` does not call for `rea setup`.\n\nREA setup never installs or upgrades Node.js, npm, Homebrew, Java, Ghidra, IDA,\nJADX, Kuna, Binwalk, or Unblob. Use existing prerequisites; do not install unrelated\nsoftware to repair MCP registration. For an unsupported client, use manual stdio\nregistration with an existing installation’s absolute runtime and entry script, or continue through the CLI.\n\nA concrete CLI fallback for an operator-supplied JavaScript tree or ASAR is:\n\n```bash\nnpx -y rea-agents@latest analyze-javascript-application \u002Fabsolute\u002Fpath\u002Fto\u002Fapp --json\n```\n\nNo MCP registration or native engine is required. Read the returned Evidence,\ngraph, limitations, and unknowns with the same care as an MCP result; the CLI\nreturns the Evidence record directly. This fallback does not establish that\nMCP is configured. Native CLI tasks still require their selected engine.\nPrefer an existing `rea` CLI. When none is installed and REA package acquisition\nis within the authorized scope, use `npx -y rea-agents@latest` in its place from a\ntrusted directory outside the target project, with absolute target paths. Managed\nsetup binds the current installation directly; retain its runtime and package\ncache entry, or restore that installation before repairing its registration.\nFor setup-owned registration, configuration repair starts with a read-only setup plan; show paths, backups and\nskill replacement before applying authorized changes. Preserve existing approval\nand target-execution boundaries.\n\n## Route the target first\n\nChoose the first tool from the target the user supplied. Use `open_binary` for\nactive-target native or archive workflows; target-free tools take their own\nexplicit path or endpoint and do not need it.\n\n- ASAR or extracted JavaScript\u002FElectron tree:\n  `analyze_javascript_application`.\n- Archive\u002Fpackage member inventory (ZIP\u002FAPK\u002FIPA\u002FMSIX\u002FAppX, DMG, or a PyInstaller\n  executable): `open_binary` with the supplied local path; use `inspect_artifact`\n  when its graph and findings help answer the question. A PyInstaller CArchive\n  is the application layer; the bootloader is only the native prefix. Start with\n  `detail: \"summary\"` for large inventories, then use retained inventory views\n  for selected member fields\u002Fpages. A complete small inventory can cost less\n  than extra calls and schemas. Runtime options are metadata, not files.\n  Compact delivery still inventories and hashes members. See the\n  [Python packaged applications guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpython-packaged-applications.md).\n- Bun `--compile` executable: `open_binary`, then `inspect_artifact`; the Bun\n  module graph is the application layer. Extract stored modules and analyze the\n  JavaScript. See [Bun standalone executables](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fbun-standalone.md).\n- Deno `deno compile` executable: `open_binary`, then `inspect_artifact`; the\n  embedded virtual filesystem is the application layer. Extract stored files and\n  analyze compatible JavaScript. Environment-file values and CA certificate bytes\n  are retained in local Evidence with their counts and byte lengths. The npm\n  snapshot length is reported and not decoded, and the executable is not run. See\n  [Deno compile executables](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fdeno-standalone.md).\n- Apple app plist, Interface Builder, asset catalog, or keyed archive resources:\n  `open_bundle_resources`, then the selected resource tool. This does not\n  require `CFBundleExecutable` or a deep provider. Resource sessions have no\n  executable digest or binary snapshot; use `open_binary` for native code.\n- Android APK code, classes, methods, or incoming references:\n  `inspect_android_package`, then focused Android tools when advertised.\n  Archive member inventory still uses the archive route above.\n- Managed PE\u002FCLI assembly: `inspect_managed_artifact`.\n- Firmware image: `inspect_firmware_regions` when advertised. Use\n  `extract_firmware` when extraction is requested, with a caller-selected new\n  absolute output directory. These tools use caller-supplied Binwalk\u002FUnblob on\n  Linux; see the [firmware guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Ffirmware\u002Ffirmware-analysis.md).\n- ESP32-family app or bootloader image (`0xE9` magic): `inspect_artifact`\n  without a provider; see the ESP section of `references\u002Fnative-and-artifacts.md`.\n- .NET NativeAOT PE\u002FELF: native Ghidra analysis. Native code can yield pseudocode;\n  consult the NativeAOT workflow in `references\u002Fnative-and-artifacts.md` for\n  optional metadata recovery and its supported host\u002Flayout boundary.\n- Native program behavior, live calls, instrumentation, or command-run effects:\n  choose the matching [native runtime workflow](references\u002Fruntime-observation.md#native-runtime-questions).\n  `open_binary` and `trace_native_values` establish static facts; they do not\n  observe execution. Runtime tools have distinct launch, attach, mutation and\n  cleanup effects, and do not require a preliminary static session unless their\n  own contract says so.\n- User-owned browser page already open: `list_browser_targets`.\n- Passive traffic capture of a SPA: the default scope is the page's own origin,\n  and data APIs usually live on another origin. Discover API origins from\n  absolute URLs in loaded bundles or script text via JavaScript analysis tools\n  (another passive capture without those origins still scopes to the page\n  origin, and `completeness.excluded` counts lack URLs). Pass both the page\n  origin and those API origins in `allowed_origins` — the list replaces the\n  default scope — and read `completeness.excluded` before reporting that an\n  API is absent. For long captures with body shapes, use\n  `export_evidence_bundle` instead of expecting an inline result.\n- Browser action the agent must perform (click, type, navigate):\n  `capture_browser_scenario` with declared actions. See\n  [runtime observation](references\u002Fruntime-observation.md) for connect\u002Flaunch\n  and the focused follow-up browser tools.\n- Agent environment (AgentEnv bundle) of a web application: read\n  [environments](references\u002Fenvironments.md) before recording; it records with\n  `capture_browser_scenario` and writes the bundle with `export_environment_bundle`.\n- Task for a desktop application's exported environment, from a\n  `capture-desktop-application` folder: read\n  [desktop application tasks](references\u002Fenvironments.md#tasks-for-a-desktop-application-environment).\n- Environment of a Linux desktop app with a task, from a request such as\n  \"build me an Inkscape environment where the agent changes a poster's\n  headline\": read [desktop builds](references\u002Fdesktop-build.md). You drive the\n  app on a build computer from `start_build_computer`, then export and witness.\n- Fiddler Everywhere traffic or a native `.saz` capture: read the\n  [Fiddler workflow](references\u002Fruntime-observation.md#fiddler-everywhere-traffic-debugging).\n  Inspect saved SAZ with `inspect_web_network_capture` and `format: \"saz\"`;\n  connect Everywhere's separate MCP server for live traffic.\n- Retained HAR\u002FSAZ\u002Fnative mitmproxy\u002Faioquic qlog capture: `inspect_web_network_capture`. Select\n  original record ordinals when useful; inspect producer fields and byte\u002Fnumber\n  sidecars without fetching recorded URLs or claiming live attribution. HAR\u002FSAZ\u002Fqlog\n  old-generation heap is `REA_CAPTURE_DECODER_OLD_GENERATION_MIB` (default 192 MiB,\n  floor 8, maximum 16384), set where REA starts. Host memory and `NODE_OPTIONS` do not\n  raise it. See\n  [historical captures](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fweb\u002Fweb-network-captures.md) for the exact upstream\n  profile and credential exclusions. Qlog support starts with aioquic 1.5.0\n  JSON 0.3; stream coverage and endpoint loss declarations do not recover bodies\n  or establish network loss. Prefer detail summary, then kind qlog trace\u002Fstream\n  pages; select one trace, stream ID and direction for contribution\u002Frange pages.\n  Facts retain all-recorded-events-before-selection scope. Other qlog layouts\n  and PCAP correlation are unsupported.\n- User-owned Electron runtime already open: `list_electron_targets`. Before an electron-main Inspector attempt, check packaged fuses with `inspect_electron_fuses`; disabled `EnableNodeCliInspectArguments` means the app ignores `--inspect`.\n- Shipped application exposure for a local `.app`, install directory, ASAR, or executable: `audit_release_exposure` \u002F `rea audit-release-exposure`. Each check has a stable id, a status, and fixed remediation. Unknown and unassessed checks stay in the report. This does not establish that an application is secure. Credential-marker hits report the rule id and location only. See [release exposure](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Frelease-exposure.md).\n- Packet-field discovery: `inspect_packet_fields` searches installed protocols\n  and field names\u002Ftypes before choosing fields for `inspect_packet_capture`.\n  Query\u002Fpage the relevant records; registrations do not establish observed traffic.\n- Recorded packet captures: `inspect_packet_capture` with selected TShark fields,\n  display filters and decode-as rules. Requires Linux, util-linux prlimit and\n  TShark 4.x on an absolute `PATH` entry or via the optional absolute\n  `REA_TSHARK_COMMAND` override; see\n  [capture guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fdata\u002Fpacket-captures.md).\n  Packet limits count input packets before filtering. Output defaults to 50 matching\n  frames; use `match_offset` \u002F `match_limit` for later pages, or explicit null\n  limit for complete matching output. Preserve the source digest across pages.\n  This does not perform live capture.\n  For address\u002FDNS\u002FSNI\u002Fprotocol summaries use `inspect_pcap_capture` with MCP\n  detail summary, then retained kind pcap pages. Requires Wireshark 4.x tshark\n  and capinfos, with Linux prlimit or Windows Job Objects; see\n  [packet summaries](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fdata\u002Fpcap-analysis.md).\n  Select an exact DNS question for address pages; page exhaustion does not prove\n  network completeness. This reads recordings and does not acquire traffic.\n- Decoder discovery: `inspect_signal_decoders` searches installed decoder IDs\n  or selected decoder help, including channels and options. Query and page the\n  relevant details before choosing settings; this does not scan hardware.\n- Recorded logic\u002Fsignal traces: `decode_signal_recording` with explicit decoder,\n  channel and protocol settings. On Linux with util-linux prlimit, supply sigrok-cli 0.7.2 through\n  `REA_SIGROK_COMMAND`; see [recording guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fsignals\u002Fsignal-recordings.md).\n  Output defaults to 50 literal lines; select annotation classes and page with\n  `line_offset` \u002F `line_limit`, or explicit null for all remaining output.\n  Window counts are display lines, not annotations or samples. Preserve source digests across pages.\n  This reads existing files; it does not acquire hardware signals.\n- Explicit local WebAssembly artifact: `inspect_wasm_artifact`. Supply WABT 1.0.42\n  through `REA_WABT_BIN_DIRECTORY`; retain exact byte\u002Ftool identity and decoded WAT.\n  Select JavaScript glue and candidate paths explicitly and preserve URL\u002Fpath\n  ambiguity. No implicit fetch or target execution; WAT is not original source.\n  See the [WASM guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fwasm\u002Fwasm-artifacts.md).\n- Explicit local Android APK (or ZIP\u002FAAB) signing: `inspect_apk_signature`.\n  Prefer its summary or selected signer\u002Fdigest\u002Flineage page; retain complete\n  Evidence and use `inspect_analysis_view` kind `apk-signature` for follow-ups.\n  Reports which schemes are present (v1 JAR, v2, v3, v3.1), each signer's\n  certificate SHA-256 fingerprint (v1 included, from its PKCS#7 block), v3 key-rotation lineage, source stamp, and\n  whether each signed digest still matches the bytes (self-consistency). This\n  is identity and integrity, not a trust or authenticity verdict.\n  See the [APK signature guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fapk-signature.md).\n- Explicit local EVM bytecode carrier: `inspect_evm_interface` with caller-selected\n  `raw` or `hex` encoding. The owned worker deadline is `timeout_ms` (default\n  30000 ms, range 1..2147483647, next call). Select byte, address-space and CPU\n  allowances separately through `producer_limits`; tighter inherited OS limits\n  remain enforced, and the 256 MiB worker heap is independent. Preserve\n  carrier\u002Fdecoded digests and treat selectors,\n  argument strings and mutability as inferred candidates; this performs no chain\n  lookup or target execution. For the complete inferred interface without hex or\n  duplicate stdout, discover support and select `detail: \"summary\"`; complete\n  Evidence stays retained under its original identity. Use the returned\n  `parent_evidence_id` for exact function or `bytecode_hex`\u002Fstdout\u002Fstderr pages.\n  Candidate coverage does not establish interface completeness. See the\n  [EVM bytecode guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fevm\u002Fevm-bytecode.md).\n- Embedded Go compiler, module, build-setting metadata, or static `(ptr, len)`\n  string literals: `inspect_go_binary` with the explicit local file (pass\n  `include_string_literals: true` and optional `max_string_literals` for bounded\n  inferred static string-header recovery, and page retained rows with\n  `inspect_analysis_view` kind `go` collection `string_literals`). This built-in\n  target-free inspection requires no Go installation or disassembler. Preserve\n  raw module bytes and source ranges; absent metadata does not prove a binary is\n  not Go, static string recovery excludes compiler-inlined stack or immediate\n  strings, and unparsed text records remain explicit. See the\n  [Go binary guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fgo-binaries.md).\n- Embedded CUDA\u002FHIP code objects: `inspect_gpu_code_objects`; inventory targets\n  first, then decode selected payloads and query retained GPU Evidence.\n- Bundled GGUF or safetensors model declarations: `inspect_model_artifact`\n  with the explicit local file. Default header hashing leaves full-file identity\n  unknown; `hash: \"full\"` additionally reads all weights for SHA-256. MCP returns\n  retained summaries; optional `view` selects one page in the initial call. Use\n  `inspect_analysis_view` kind `model-artifact` for\n  batched metadata keys, tensor names or type totals, selected fields and pages.\n  Preserve header-scoped indices and array preview omissions; do not infer model\n  behavior from declared architecture or tensor types. See the\n  [model file guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fmodel-artifacts.md).\n- Unity IL2CPP names, member owners and string literals from `global-metadata.dat`:\n  `inspect_il2cpp_metadata` with the explicit local file; MCP defaults to compact\n  counts. Query sections, images, types, methods, fields, properties, events,\n  parameters or string_literals through `inspect_analysis_view`\n  with the returned `parent_evidence_id`, using exact filters, batch indices and\n  selected fields. Parameters accept `method_indices`, avoiding a scan of all\n  parameter pages. Missing collections in historical Evidence remain unknown.\n  Versions 24, 27, 29, 31 and 39; no Unity, IL2CPP\n  binary or disassembler is run. Unrecognized magic (possibly encrypted) and\n  other versions are unsupported. Optional matching `binary_path` enables static native addresses and type references; query `method_addresses` with indices or addresses\u002Fstates, preserving every shared-body method and both artifact identities. Without a linked binary native counts remain unknown. Byte-pattern fallback is inferred; no runtime behavior or same-build pairing is proved. See the\n  [IL2CPP metadata guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fil2cpp-metadata.md).\n- Embedded cargo-auditable Rust dependency metadata: `inspect_rust_binary`\n  with the explicit local ELF, PE, or thin Mach-O file. This built-in\n  target-free inspection requires no Rust installation or disassembler. Preserve\n  package order, dependency indices, and the section file range. A missing\n  `.dep-v0` section is null metadata, not proof the binary has no dependencies.\n  A rustc commit hash is an inference from a read-only `\u002Frustc\u002F\u003C40-hex>\u002F` path.\n  For selected crates, use `view: {collection: \"packages\", names: [...],\n  fields: [\"name\", \"version\", \"source\"]}` on the first call; explicitly include\n  `dependencies` for direct index references. Use `detail: \"summary\"` for counts\n  and ranges, or retained `inspect_analysis_view` Rust package\u002Fedge pages for\n  subsequent filters. Keep the complete parent Evidence accessible; CLI compact\n  delivery requires `--evidence_output`.\n  See the\n  [Rust binary guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Frust-binaries.md).\n- PE Authenticode certificate table: `inspect_pe_certificates` with the explicit\n  local PE32\u002FPE32+ file. This built-in target-free inspection requires no\n  Windows SDK. Preserve WIN_CERTIFICATE ranges, types, payload SHA-256, and\n  PKCS#7 signer\u002FX.509 identity fields, including `subject_key_identifier_hex`\n  when the signer uses that form. A missing security directory is observed\n  absence of that table, not proof the image is unsigned in every catalog sense.\n  Signatures are not verified. See the\n  [PE certificate guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpe-certificates.md).\n- PE import and delay-load tables: `inspect_pe_imports` with the explicit\n  local PE32\u002FPE32+ file. This built-in target-free inspection requires no\n  Windows SDK. Preserve DLL names, named and ordinal functions, ILT\u002FIAT RVAs,\n  delay-load descriptors, and the pefile import hash of the standard import\n  table. A missing import directory is observed absence of that table, not\n  proof the image never imported APIs through another table. Bound snapshots\n  and loaded IAT contents remain unobserved. See the\n  [PE import guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpe-imports.md).\n- Windows Shell Link shortcuts: `inspect_windows_shortcut` with the explicit\n  local `.lnk` file. This built-in target-free inspection requires no Windows\n  SDK or COM. Preserve header flags and FILETIMEs, IDList items, LinkInfo\n  volume and network names, StringData arguments and icon location, ExtraData\n  signatures, and Tracker droid facts labelled derived. Unknown IDList items\n  and ExtraData signatures stay raw with SHA-256. The target path is not\n  resolved or executed. See the\n  [Windows shortcut guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fwindows-shortcut.md).\n- PE TLS callbacks and load configuration: `inspect_pe_load_config` with the\n  explicit local PE32\u002FPE32+ file. This built-in target-free inspection requires\n  no Windows SDK. Preserve callback VAs as strings with their RVA, file offset\n  and section, and the size-covered security cookie, SafeSEH, CFG,\n  EH-continuation and XFG fields. Guard-flag mitigation claims are inferred\n  linker declarations, not proof of enforcement. A missing directory is observed\n  absence of that declaration. See the\n  [PE load configuration guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpe-load-config.md).\n- ELF, PE, and Mach-O hardening: `inspect_binary_hardening` with the explicit\n  local file. This built-in target-free inspection requires no pwntools or other\n  host tool. One image per Mach-O slice. Each property is `enabled`, `disabled`,\n  `partial`, `unknown`, or `not_applicable`, with the header field or import\n  behind it. A missing stack-protector or fortify import is `unknown`, not\n  proof the protection was omitted. Authenticode and Mach-O code signatures\n  report presence, not validity. Hardened runtime stays unknown and names\n  `inspect_signature`. The image is not executed. See the\n  [binary hardening guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fbinary-hardening.md).\n- ELF note tables: `inspect_elf_notes` with the explicit local ELF32\u002FELF64\n  file. This built-in target-free inspection requires no disassembler. Preserve\n  PT_NOTE and SHT_NOTE ranges, owners, types, descriptor SHA-256, and GNU\n  build-id or ABI-tag fields. A missing table is observed absence of those\n  declarations, not proof the image never carried notes. See the\n  [ELF notes guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Felf-notes.md).\n- Code that runs before `main` or at exit in ELF or Mach-O:\n  `inspect_native_initializers` with the explicit local file (and\n  `architecture` for a universal Mach-O). This built-in inspection requires no\n  disassembler. Preserve slot and target addresses, the `resolution` of each\n  entry, and its limitations. An `unresolved` slot is not a zero pointer, and a\n  missing table is not proof that no constructor exists. See the\n  [initializer guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fnative-initializers.md).\n\n- ELF unwind function ranges: `inspect_elf_unwind_ranges` with the explicit\n  local ELF32\u002FELF64 file. This built-in target-free inspection requires no\n  disassembler. Preserve FDE start, end, size, containing section, exact\n  symbol name, CIE index, LSDA, and personality. Page with `offset` and\n  `limit`. A missing `.eh_frame` is observed absence of that declaration,\n  not proof the image has no functions. `.debug_frame` is reported present\n  or absent and is not decoded. CFA instructions are counted and not\n  evaluated. See the\n  [ELF unwind ranges guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Felf-unwind-ranges.md).\n- Apple `.ips` crash reports: `inspect_apple_ips` with the explicit local\n  file. This built-in target-free inspection requires no Xcode, atos, or\n  pwntools. Preserve first-line metadata, `bug_type` as a string, process and\n  exception facts, lossless integer registers, usedImages UUIDs, and\n  documented classification matches. Only `bug_type` `\"309\"` yields a crash\n  body; other types, including `\"288\"` stackshots, return no crash result.\n  Select an optional `join_path` for UUID-and-architecture matching to one\n  local Mach-O or dSYM; preserve slice identity and unjoined reasons. Joined\n  static addresses do not resolve function names or dSYM symbols. See the\n  [Apple IPS guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fapple-ips.md).\n- Linux kernel module metadata: `inspect_kernel_module` with the explicit local\n  ELF32\u002FELF64 relocatable file. This built-in target-free inspection requires\n  no Linux host or `modinfo`. Preserve `.modinfo` key order and duplicate keys,\n  `__versions` CRC hex, section file ranges, and the appended signature\n  trailer's PKCS#7 SHA-256. A missing section is observed absence when section\n  names are known, not proof the module never carried that metadata.\n  `struct module` is not decoded. The signature is not validated. gzip, xz, and\n  zstd containers are unsupported; decompress into a separate file with an\n  external codec utility, then inspect the decompressed `ET_REL` image. See the\n  [kernel module guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fkernel-modules.md).\n- Linux kernel version and build config (`CONFIG_*` options such as\n  `CONFIG_SECURITY_SELINUX`): `inspect_kernel_build_config` with the explicit\n  local `vmlinux`, raw `Image`, x86 `bzImage`, or `configs.ko`. This built-in\n  target-free inspection requires no Linux host or `extract-ikconfig`. Preserve\n  the banner version, config SHA-256, option count, and value kinds; use `name`\n  for one option. An `IKCFG_ST` string is a config only with a valid gzip member\n  and `IKCFG_ED`. An absent config may mean the kernel was built without\n  `CONFIG_IKCONFIG`. Non-gzip payloads are unsupported; decompress externally,\n  then inspect the result. See the\n  [kernel build config guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fkernel-build-config.md).\n- CPython 3.7–3.13 `.pyc` header, nested marshal code objects and bytecode\n  identity: `inspect_python_pyc` with the explicit local file. This built-in\n  target-free inspection requires no Python installation. Preserve magic,\n  PEP 552 hash or mtime\u002Fsize, nested names, and bytecode SHA-256. Bytecode is\n  not decompiled, and a decoded header does not prove the matching `.py` is\n  present. See the\n  [CPython pyc guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fpython-pyc.md).\n- Erlang BEAM IFF container: `inspect_erlang_beam` with the explicit local\n  `.beam` file. This built-in target-free inspection requires no Erlang\n  installation. Preserve chunk names, atom order, export\u002Fimport\u002Flambda tables,\n  and the Code header. For selected facts, prefer `detail: \"summary\"` plus a\n  `beam` view (collection, names\u002Findices, fields and paging), retaining the full\n  Evidence. CLI summary requires `--evidence_output`. Missing table counts stay\n  null; decoded empty tables count zero. Bytecode is not executed. See the\n  [Erlang BEAM guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Ferlang-beam.md).\n\n- Explicit local SQLite database snapshot: `inspect_sqlite_database`. Inspect\n  with Node.js 24.x >=24.15 or 26+ providing native SQLite limits. Read schema\n  first (compact inventory by default), or select an exact ordinary table\n  and `columns` when rows are needed. Defaults are selected-table schema and\n  20 rows; request `schema_scope: \"database\"` for the complete stored schema. Preserve both database and existing sibling WAL identity; row samples\n  report truncation and have unspecified order. Use a quiescent snapshot rather\n  than assuming a live database\u002FWAL pair was copied atomically. See the\n  [SQLite guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fdata\u002Fsqlite-databases.md).\n- Explicit Linux ELF file for offline layout, symbols, relocations or static\n  mitigation evidence: `inspect_binary_layout`. This target-free operation uses\n  caller-supplied pwntools without opening a disassembler database. Preserve its\n  raw locations and inference\u002Fcoverage limits; see the\n  [offline binary guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Fbinary-diagnostics.md).\n- Supplied Linux x86-64 ELF core: `inspect_recorded_crash`. Read every recorded\n  thread, raw note and source-bound register without opening a live target.\n  Historical PIDs do not select live processes. Request `include_debugger_context`\n  only when core-only mapping candidates help; see the\n  [recorded crash guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fguides\u002Fnative\u002Frecorded-crashes.md).\n- PE resource type\u002Fname\u002Flanguage trees and static icon group references:\n  `inspect_pe_resources` with an explicit path. This portable operation requires\n  no active target or engine; opaque payloads retain file ranges and SHA-256.\n- PE export directories and ELF dynamic-symbol exports: `inspect_native_exports`\n  with an explicit path; portable, no active target or engine.\n- Native executable, library, or analysis database: `open_binary`, then\n  use focused analysis tools directly; call `binary_overview` when metadata or\n  inventory context is useful and available from the selected provider.\n\nFor an existing IDA MCP configuration, use `open_binary` with the original\ninput binary and `provider_id: \"ida\"`; do not pass an `.idb` or `.i64` database.\nThe legacy attached profile binds the already-open GUI input by SHA-256 and\nleaves its database open. The modern headless profile creates and closes an\nowned private database without saving. Installation and registration reuse\n[mrexodia\u002Fida-pro-mcp](https:\u002F\u002Fgithub.com\u002Fmrexodia\u002Fida-pro-mcp); see the\n[IDA provider guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fproviders\u002Fida-provider.md).\nFor migration to the separate native IDA MCP plugin, follow the guide's\n[legacy attached migration](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fproviders\u002Fida-provider.md#migrate-a-legacy-attached-registration).\nReplace the upstream registration explicitly; modern mrexodia tools are not the\nnative profile. Native attachment preserves the database but does not provide\ndirect callers; check session availability and the guide's verification limits.\nProceed directly to `analyze_function`, pseudocode, or function\u002Fstring searches\nafter opening; IDA does not supply `binary_overview`. Consult session availability\nwhen composing broader workflows. Modern direct callers and unsupported dossier\nfacets remain unknown; live IDA results are not replayed from snapshots.\n\nWith `REA_KUNA_COMMAND` configured, `provider_id: \"kuna\"` answers procedure\nlists, lookups, pseudocode, assembly and `analyze_function` from Kuna's cached\nwhole-program export. Callers\u002Fcallees use a separate body-free graph shared by\nthe session; `xrefs` returns exact-address incoming sites and filters forwarding\naliases. These queries and inventory lookups do not trigger a C export. Indirect\ntargets remain unknown and can make relationship coverage partial. Reference\ncaches expire on close; a fresh CLI process repeats the native reference walk.\nTyped references, CFG, raw-memory tools and annotations remain unsupported. A cold first\nanswer can come from a single-function run (its limitations say so); assembly\nwaits for the export. For pseudocode and assembly, `raw_result.source` names the\ncached `.c`\u002F`.asm` file and byte span, which you may search directly instead of\ncalling per function. See the\n[Kuna provider guide](https:\u002F\u002Fgithub.com\u002Fmorluto\u002Frea\u002Fblob\u002Fmain\u002Fdocs\u002Fkuna-provider.md).\n\nIf the user says only \"my app\" without a name, path, or target already selected\nfor this task, ask which app before searching for artifacts. Paths in unrelated\nsaved reports and nearby test fixtures do not select the user's target. Resolve\nan actual human-readable app name to one clear installed artifact when possible;\nask when matches are ambiguous. Never choose an example app on the user's behalf.\n\nIn a target-free session, use `open_binary` to bind any archive\u002Fpackage or\nnative target whose analysis tool operates on the active target. Do not call an\nunadvertised tool; inspect `binary_session` with `{}` and its\n`result.tool_availability` for availability reasons and remediation. Expand each\ngroup's `names` into entries, inheriting the inventory-level client requirements\nunless the group overrides them. The grouped name union is the complete tool\ninventory; use `tools\u002Flist` for canonical tool schemas. The default summary keeps\neach provider candidate's availability and target-support status, code and\nreason; `omitted_fields` lists what it leaves out. Request `{\"detail\": \"complete\"}`\nonly when you need an unavailable candidate's remediation, provider\ndiagnostics, candidate capability sets, or tool surface, effect and annotation\nflags; in those closed flag vocabularies, listed\nflags are true and omitted known flags are false. Provider candidate facts\ndescribe possible providers, while top-level session capabilities describe the\ncurrent route and `analysis_provider_binding` names the selected provider. Do\nnot treat those scopes as interchangeable.\n\nFor editable Ghidra analysis that must survive a later agent process, select\nthe [owned Program checkpoint workflow](references\u002Fnative-and-artifacts.md#continue-editable-ghidra-analysis-across-processes)\nbefore making metadata edits. It is separate from Evidence\u002FUnknown persistence.\n\nFor a Ghidra startup timeout on a large native target, follow\n[deadline recovery](references\u002Fnative-and-artifacts.md#ghidra-startup-deadline-recovery)\nbefore abandoning deep analysis or repeating the same cold import. The default\n330 seconds can be changed for new startup attempts through\n`update_analysis_settings` using `ghidra.startup_timeout_ms`. Changing the\nserver's launch environment instead requires a new REA process.\n\n## Work summary-first\n\nStart with the default result and use its inline Evidence and graph context.\nFor a JavaScript application or ELF layout whose size is unknown or large,\ncall `analyze_javascript_application` or `inspect_binary_layout` with\n`\"detail\": \"summary\"`, then inspect the retained `parent_evidence_id` with\n`inspect_analysis_view`. Over MCP, `analyze_function` is summary-first without\na flag: its default reply is the summary, and the complete dossier stays\nretained under `parent_evidence_id` for facet paging. Pass that ID as a\n`retained-evidence` reference to `compare_functions`, or inside\n`match_native_functions` `left_observations`\u002F`right_observations` or\n`build_call_path.functions`; request `\"detail\": \"complete\"` only when the\ndossier must travel inline.\nUse the same exact-reference form in other advertised logical Evidence inputs,\nincluding optional sources, arrays and nested sources across domains. Each\nsource can independently be inline or retained; preserve its source identity,\ncoverage, partial facts and unknowns. A summary or inspection page has its own\nEvidence ID: use `normalized_result.parent_evidence_id` when the consumer needs\nthe complete source. For portable CLI follow-ups, commands advertising\n`--evidence-bundle` resolve references from that selected exported bundle.\nSee [Evidence composition](references\u002Fevidence-workflows.md) for scope and\nrecovery; file selectors are supported only where explicitly advertised.\nPage module identities and select the returned `node_id` before requesting an\nitem; a single file path can represent several graph roles. Do not repeat an\nidentical analysis or rejected call without a changed input or resolved blocker.\nRecheck session state when a lifecycle change makes that status useful.\nMake a focused follow-up only when the\nreturned result leaves a specific question unanswered.\n\nIf MCP reports `resource_constraint` with `details.resource: \"transport\"`, call\n`inspect_analysis_view` with its reported same-session Evidence reference for a\nsummary, one section\u002Fmodule, or a stable page. Use `trace_application_feature`\nonce a seed is known, or call `export_evidence_bundle` to write the complete\nsession to a selected path. The analysis remains complete in the ledger; avoid\nrepeating it merely to request the same oversized response. Complete CLI JSON\noutput also streams without a single MCP frame.\n\nWhen the retained parent ID is unknown, use `get_evidence_bundle` with\n`detail: \"summary\"` and exact filters for operation, target SHA-256,\nanalysis-profile digest or canonical procedure address. Select its returned\nEvidence ID for the next view instead of requesting the complete bundle. When\nthat record has no supported view (for example an annotation), read it with\n`detail: \"records\"` and an `evidence_id` filter; `missing_evidence_links`\nnames linked sources this session does not retain.\n`retention: \"complete-record\"` means the whole record is stored; native\nvalue-flow truncation and unknown metadata remain separate. For an exported\nportable bundle, use `rea inspect-evidence-bundle` with JSON containing `path`,\n`detail: \"summary\"` and the same `filters`. Reading that file still requires\nvalidating its full contents within the local memory budget.\n\nA client can also truncate a successful tool result without a REA transport\nerror. Treat that preview as incomplete; use the retained parent ID for smaller\nviews or export when the full record is needed. Do not parse the preview as\ncanonical JSON or repeat the producer. For JavaScript, read the\n[module-view and trace recipes](references\u002Fjavascript-applications.md) before\ndrilling into a large graph; a broad bidirectional trace can expand unrelated\ncontainment relationships even after summary analysis.\n\nEvery conclusion must distinguish observations, inferences, and unknowns. Cite\nEvidence IDs, preserve limitations and incomplete coverage, and never imply\nthat static analysis observed execution. Runtime requests execute the declared\ntarget and lifecycle; do not broaden the target or action beyond those fields.\n\nWithin the user's requested investigation, call available analysis tools\ndirectly. REA does not require permission grants or per-call approval flags.\nThe agent client can independently require approval. Follow the declared request\nscope and the host's actual access requirements; use the recovery guide for an\nobserved client-policy rejection.\n\n## Plan broader investigations\n\nFor requests that span multiple features or subsystems, use a staged workflow:\n\n1. Turn the request into a checklist of questions and the evidence each answer\n   needs. Resolve target identity and constraints from the conversation and\n   workspace before asking for information again.\n2. Inspect the current REA session, artifact identity, saved analysis database,\n   bookmarks, and prior evidence. Reuse matching state; do not open duplicate\n   sessions or repeat identical analysis.\n3. Start with the smallest useful overview or inventory. Follow each question\n   from its entry point through relevant data and state changes to its result.\n   Batch related operations around a specific hypothesis, then expand only when\n   the returned evidence leaves a concrete gap.\n4. Inspect relevant packaged resources and configuration alongside code when\n   they affect the question. Use format-aware inventory and parsers; do not\n   infer behavior from filenames, strings, or layout alone.\n5. Corroborate a conclusion with the evidence type it requires. Use runtime\n   observation only when static evidence cannot answer the question and the\n   required host runtime and OS access are available. For JavaScript behavior,\n   run probes against the actual app through the available browser, Electron,\n   or process capture workflow.\n6. Decompose work into independent questions. When parallel workers are\n   available and the questions do not depend on one another, assign distinct\n   scopes, point workers to existing evidence, and ask them to return sources,\n   conclusions, and unresolved gaps. Otherwise, work sequentially.\n7. Keep a concise finding ledger linking each conclusion to Evidence IDs,\n   confidence\u002Fevidence type, search boundary, and remaining unknowns. Update\n   the shared index or investigation report so later passes can reuse results.\n\nBefore finishing, revisit the original checklist. Mark each question as\nanswered, partially answered, or unresolved based on its evidence; keep\nbounded negative searches bounded, and do not describe a broad investigation\nas complete while required questions remain open.\n\n## Read only the relevant guide\n\n- Native binaries, managed assemblies, archives, and extraction:\n  [references\u002Fnative-and-artifacts.md](references\u002Fnative-and-artifacts.md)\n- ASARs, extracted JavaScript, feature tracing, and version comparison:\n  [references\u002Fjavascript-applications.md](references\u002Fjavascript-applications.md)\n- Android APK declarations, classes, methods, and static references:\n  [references\u002Fandroid-applications.md](references\u002Fandroid-applications.md)\n- Native instrumentation, debugger and process capture; browser\u002FElectron\n  observation; static\u002Fruntime comparison:\n  [references\u002Fruntime-observation.md](references\u002Fruntime-observation.md)\n- Evidence paging, comparisons, residual unknowns, and verification:\n  [references\u002Fevidence-workflows.md](references\u002Fevidence-workflows.md)\n- Agent environments (AgentEnv bundles) of a web application, recorded from\n  a live instance or a HAR:\n  [references\u002Fenvironments.md](references\u002Fenvironments.md)\n- Tasks for a desktop application's exported environment:\n  [references\u002Fenvironments.md](references\u002Fenvironments.md#tasks-for-a-desktop-application-environment)\n- A desktop app environment from a request, built and witnessed on build\n  computers: [references\u002Fdesktop-build.md](references\u002Fdesktop-build.md)\n\n## Finish the task\n\nExplain findings in plain language and tie them to returned evidence. When the\nuser asks to build something, use normal coding tools and separate observed\nbehavior from design choices. Close an opened native session with\n`close_binary` when its engine is no longer needed. Evidence references and Unknown\nhistory remain in memory on the same MCP connection. End the investigation with\n`reset_investigation`; supply `save_path` to checkpoint the complete bundle before\nclearing. Import the saved bundle to restore original references and Unknown\nhistory in a new process. Retention is bounded and is not automatic persistence.\n",{"name":5,"metadata":24,"description":7},{"version":25},"62","main","183a0e26a183c692b6f1fc3d97039183e80c4796",".agents\u002Fskills\u002Freverse-engineer-anything","https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek","https:\u002F\u002Fgreeneek.vercel.app\u002F","https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git","www.mostafa-taher.duckdns.org","2026-11-15 04:10:26",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Mostafa-Taher-git\u002FGreeneek --skill reverse-engineer-anything",{"tool":40,"command":41},"bunx","bunx skills add Mostafa-Taher-git\u002FGreeneek --skill reverse-engineer-anything",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Mostafa-Taher-git\u002FGreeneek --skill reverse-engineer-anything","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002FSKILL.md",true,[48,54,58,62,66,70,74,78],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fandroid-applications.md","REFERENCE","参考文档",4092,"https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002Freferences\u002Fandroid-applications.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fconnection-and-recovery.md",19499,"https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002Freferences\u002Fconnection-and-recovery.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fdesktop-build.md",51806,"https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002Freferences\u002Fdesktop-build.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fenvironments.md",22010,"https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002Freferences\u002Fenvironments.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fevidence-workflows.md",11340,"https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002Freferences\u002Fevidence-workflows.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fjavascript-applications.md",15437,"https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002Freferences\u002Fjavascript-applications.md",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fnative-and-artifacts.md",60788,"https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002Freferences\u002Fnative-and-artifacts.md",{"path":79,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fruntime-observation.md",12296,"https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freverse-engineer-anything\u002Freferences\u002Fruntime-observation.md",[83,90,97,104,111,118],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7BZFPXJY0FHK7MWC9TFFJ6X","user-only-skill","Prove model-disabled skills stay outside the model catalog.","https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.gnk\u002Fskills\u002Fuser-only-skill\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7BZFM9WBCZKC1QHKJNXCGE2","snapshot-skill","Exercise project skill discovery and loading in snapshot tests.","https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.gnk\u002Fskills\u002Fsnapshot-skill\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7BZFK35HJX56MKCBR55BW5A","model-only-skill","Prove user-disabled skills remain available to the model.","https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002Fsnapshots\u002Fsession\u002Fskill-load\u002Fworkspace\u002F.gnk\u002Fskills\u002Fmodel-only-skill\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7BZFFRD3339VT24M97Q52ZE","editing-cordis-compositions","Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted but contributed nothing.","https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002Fpackages\u002Fpreset\u002Fagent-presets\u002Fpresets\u002Fcordis\u002Fskills\u002Fediting-cordis-compositions\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M7BZFAQMT5FNWTPZ9X8JB1RW","cordis-plugin-development","Create, modify, debug, or extend dynamic Cordis Plugins, including Host Services and Events, Client Slot and theme UI, Package-private Client-to-Host calls, dynamic Tools, version updates, approval failures, and runtime diagnostics. Use this Skill to route a user request to the correct platform and Inspect Provider, then define, run, repair, or roll back the Plugin.","https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002Fpackages\u002Fpreset\u002Fagent-presets\u002Fpresets\u002Fcordis\u002Fskills\u002Fcordis-plugin-development\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":19},"01M7BZF8Q58ZZ1T0Y08SVHK9XM","preview-tour","Inspect the bundled Preview workspace and its deterministic Session examples.","https:\u002F\u002Fgithub.com\u002FMostafa-Taher-git\u002FGreeneek\u002Fblob\u002Fmain\u002Fpackages\u002Fexperimental\u002Fwebworker-runtime\u002Ftests\u002Ffixtures\u002Fvfs-example\u002Fworkspace\u002F.agents\u002Fskills\u002Fpreview-tour\u002FSKILL.md",[],[]]