[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77KTP9FZKK6CT7CHTDT0EJS":3,"skill-same:01M77KTP9FZKK6CT7CHTDT0EJS":75},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":54},"01M77KTP9FZKK6CT7CHTDT0EJS","setup",null,"Verify harness-config's readiness for this repository: the external CLI prerequisites its audit scripts need, jq (the JSON-parsing audit scripts) and curl (the plugin-drift check), and the tracked suppression record in docs\u002Fconventions\u002Fharness-config.yaml, so the audit skills run instead of failing. Use when: 'set up harness-config', 'configure harness-config', 'is harness-config working', 'set up audit-pass suppressions', or an audit skill reported a missing prerequisite. Actions: check (read-only verification, default) | apply (resolve what check found) | wsl-profile (print an opt-in WSL hardening settings block, writes nothing). Re-runnable and safe.","melodic-software\u002Fclaude-code-plugins","melodic-software","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F58273638?v=4","01M77JVQTXNGKCE4MDFY2BC936","Melodic Software","01M77JVQVN9QDWKAH6W03ANP76",30,"MIT","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-config\u002Fskills\u002Fsetup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Verify harness-config's readiness for this repository: the external CLI prerequisites its audit scripts need, jq (the JSON-parsing audit scripts) and curl (the plugin-drift check), and the tracked suppression record in docs\u002Fconventions\u002Fharness-config.yaml, so the audit skills run instead of failing. Use when: 'set up harness-config', 'configure harness-config', 'is harness-config working', 'set up audit-pass suppressions', or an audit skill reported a missing prerequisite. Actions: check (read-only verification, default) | apply (resolve what check found) | wsl-profile (print an opt-in WSL hardening settings block, writes nothing). Re-runnable and safe.\"\nargument-hint: \"[check|apply|wsl-profile]\"\nuser-invocable: true\ndisable-model-invocation: true\nallowed-tools:\n  - \"Bash(command -v jq*)\"\n  - \"Bash(command -v curl*)\"\n  - \"Bash(command -v awk*)\"\n  - \"Bash(command -v sort*)\"\n  - \"Bash(bash ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsetup\u002Fscripts\u002Fwsl-profile.sh *)\"\nshell: bash\n---\n\n## Pre-computed context\n\n`check`'s tool probes ran at load time. Read these rows instead of re-issuing them; each shows the\ntool's path when present, or `absent` when missing:\n\n- `jq`: !`command -v jq 2>\u002Fdev\u002Fnull || echo absent`\n- `curl`: !`command -v curl 2>\u002Fdev\u002Fnull || echo absent`\n- `awk`: !`command -v awk 2>\u002Fdev\u002Fnull || echo absent`\n- `sort`: !`command -v sort 2>\u002Fdev\u002Fnull || echo absent`\n\nA row reading `[shell command execution disabled by policy]` carries no result: run that tool's\n`command -v` probe via Bash instead.\n\n- **Pointer**: for the placeholder a skipped load-time command leaves, fetch\n  [skills § Inject dynamic context](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fskills#inject-dynamic-context)\n  live.\n- **As of**: 2026-11-11\n- **Recheck trigger**: the placeholder text changes.\n\n## Purpose\n\nSetup per the uniform setup contract (`docs\u002Fplugin-philosophy.md` \"Setup is explicit and repeatable\" in\nthe marketplace repository): `check` inspects and reports, `apply` resolves. This plugin declares no\n`userConfig`, and has two setup concerns:\n\n- the external command-line tools its bundled scripts require, where `apply` is guidance-and-verify\n  with no write path: it points at platform install instructions and never installs a system package;\n- the **tracked consumer-project configuration** `audit` and `audit-pass` read, the `suppressions`\n  mapping of `\u003Chome>\u002Fharness-config.yaml`, the one file `apply` may write. `\u003Chome>` is the\n  convention home the repository binds in the pointer region of its `AGENTS.md` or `CLAUDE.md`\n  (`bash ${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresolve-convention-home.sh` prints it), else `docs\u002Fconventions`.\n\nAction routing: no argument or `check` runs the check; `apply` runs the check first, then remediation;\n`wsl-profile` runs only its own section. All are non-interactive, so never prompt when the action is given.\n\n## `check` (read-only)\n\nThe bundled scripts are the single source of truth for what this plugin requires.\n\n**Read it first.** Probe what it actually does, don't recite this file. Then read the\npre-computed tool rows, run the remaining probes via Bash, and report a PASS\u002FFAIL\u002FINFO table with one remediation line per FAIL. Do not modify anything.\n\nThe runtime scripts and their tools:\n\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit\u002Fscripts\u002Fcheck-plugin-drift.sh`: jq **and** curl\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit\u002Fscripts\u002Fcheck-structure.sh`, `check-hook-coverage.sh` and `fix-plugin-drift.sh`: jq\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit\u002Fscripts\u002Faudit-engine.sh`: jq plus awk and sort; `check-effort-pins.sh`: jq plus awk\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-automation-gaps\u002Fscripts\u002Finventory.sh`: jq plus awk\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-permission-grants\u002Fscripts\u002Fpermission-rule-check.sh`: jq plus awk and sort\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-permission-state\u002Fscripts\u002F*.sh`: jq (required; `permission-state.sh` exits 2 without it), awk and sort; `automode-block-lint.sh` and `automode-entry-diff.sh` add python3 for an optional lane\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fdraft-auto-mode-rules\u002Fscripts\u002Fdraft-automode-block.sh`: jq\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-pass\u002Fscripts\u002Frun-state.sh`: jq (falls back to python3, then to a scan that announces itself)\n- `${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fcheck-retirements.sh`: awk (no jq)\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-pass\u002Fscripts\u002Fstate-digest.sh` and `finding-identity.sh`: sort\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-instructions\u002Fscripts\u002Finstruction-scan.sh`: grep, tr and awk (no jq)\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-instructions\u002Fscripts\u002Fconflict-scan.sh`: awk **and** sort (no jq)\n\nMost scripts that need `jq` probe for it, but only `conflict-scan.sh` and `instruction-scan.sh` probe\nfor `awk` and `sort`; the rest call those with no guard, so read each script's actual calls rather than trusting a single script's prerequisite block to\nspeak for the plugin.\n\n1. **`jq`**, from the pre-computed `jq` row. FAIL if absent: the JSON-parsing scripts need it (`inventory.sh` degrades\n   to an empty inventory; the others `exit 2` with an install remediation). Missing `jq` blocks every\n   skill whose scripts parse JSON (`audit`, `audit-automation-gaps`, `audit-permission-grants`,\n   `audit-permission-state`, `draft-auto-mode-rules`, and `audit-pass`'s run-state helper); `audit-instructions` scans markdown and is unaffected.\n2. **`curl`**, from the pre-computed `curl` row. FAIL if absent, but scoped: only the plugin-drift check\n   (`check-plugin-drift.sh`) uses it and `exit 2`s without it. The rest of `audit` and every other\n   skill still run; say so in the remediation line.\n3. **`awk` and `sort`**, from the pre-computed `awk` and `sort` rows. FAIL if either is absent, and **not**\n   scoped to one skill: `conflict-scan.sh` and `instruction-scan.sh` probe and `exit 2` naming the\n   missing one, while the other scripts in the list above that use them have no prerequisite check\n   at all, so their skills fail mid-run on a bare `command not found` rather than on a named\n   prerequisite. Say in the\n   remediation line that this FAIL reaches six skills (`audit`, `audit-automation-gaps`,\n   `audit-pass`, `audit-permission-grants`, `audit-permission-state` and `audit-instructions`), not\n   just `audit-instructions`. Report `awk` and `sort` by name rather than as one row, since a\n   minimal shell can carry one and not the other.\n4. **Bash shell**, INFO: the scripts are bash (arrays, `[[ ]]`, process substitution, `BASH_SOURCE`),\n   run through Claude Code's Bash tool. Report the resolved interpreter; FAIL only if no bash is\n   resolvable. Pointer: for which shell a platform's sessions get, native Windows included, fetch\n   [tools reference: PowerShell tool](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Ftools-reference#powershell-tool)\n   live.\n5. **Network reachability**, INFO only: `audit`'s drift\u002Ffreshness fetches read\n   `raw.githubusercontent.com`, and a failed fetch degrades to SKIP rather than a setup failure. Do not\n   fetch here; `check` performs no network call.\n\n### The `audit-pass` suppression record\n\n`audit-pass` reads a tracked suppression record layered per the marketplace's config-cascade\nconvention. Read the operative shape from\n`${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-pass\u002Freference\u002Fsuppression.md` rather than inferring it. That\nreference ships inside this plugin, so it resolves in an installed cache where a path out to the\nmarketplace's own docs does not. The cross-consumer key contract is the marketplace's published\n**finding-suppression** convention, which is not a runtime dependency of this plugin. All layers\nabsent is a valid state (no suppressions), so report INFO, never FAIL, when none exists.\n\nAnchor at the repo root (`${CLAUDE_PROJECT_DIR}`, else `git rev-parse --show-toplevel`), never a\nCWD-relative read, which resolves a different (or missing) file depending on the subdirectory or\nnested worktree the skill was invoked from, then report one row per layer. The same\ntracked\u002Fignored question has opposite correct answers per layer, so verify each on its own terms:\n\n- **user-global** `~\u002F.claude\u002Faudit-pass.md`: outside the worktree; no git command applies. INFO only.\n- **team** `\u003Chome>\u002Fharness-config.yaml`: must be tracked, probed as the pair:\n  `git check-ignore -v` reports no match (a match is FAIL with the pattern) AND\n  `git ls-files --error-unmatch` exits 0. Untracked while present is a hard STOP:\n  teammates never receive the shared suppressions. Parse it with\n  `awk -v STRICT=1 -f ${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fyaml-subset.awk \u003Cfile>`, the parser the audit engine\n  uses: a non-zero exit is FAIL with the line it prints, because the engine then drops the whole team\n  layer. The common cause is an unquoted `anchor\u002Fv1` key; the parser takes a plain key only of\n  letters, digits, `_` and `-`, so the key is written `\"anchor\u002Fv1\":`.\n- **personal override** `.claude\u002Faudit-pass.local.md`: must be gitignored and never staged. Staged or\n  tracked is a FAIL: a personal deviation can reach team history.\n\nParse each present layer and report as malformed any entry missing **any** of its five required\nkeys: `check`, `claim`, `sites`, `reason`, `date`. Checking only `reason` and `date` would pass an\nentry that `audit-pass` itself rejects, so readiness would report green on configuration that cannot\nsuppress anything. Report as malformed too an entry whose stored constituents do not hash to its own\nkey: the constituents are authoritative and the key is derived from them. A malformed entry does not\nsuppress, and a silent partial parse would turn a formatting slip into a lost check.\n\nReport a **user-global or personal override entry for an id the team layer does not carry** as INFO\n`personal-only, not applied`, naming promotion to the team layer as what makes it take effect. The\nteam layer is the only one that enacts a suppression, so a personal-only entry that looks live is a\nfinding the operator believes is accepted and is not.\n\n## `apply` (idempotent)\n\nRun `check`, then for each FAIL give the platform install instructions from the README Requirements.\nThis skill never installs system packages:\n\n- **missing `jq`:** the platform's jq install (for example `winget install jqlang.jq`, `brew install\n  jq`, or `apt-get install jq`); rerun `check` after.\n- **missing `curl`:** the platform's curl install. Modern Windows and Git Bash already ship `curl`.\n  Only the plugin-drift check needs it, so the rest of the plugin works meanwhile.\n- **missing `awk` or `sort`:** both ship with every POSIX userland, so absence means the shell\n  environment is minimal rather than that one package is missing. Git Bash and Windows `busybox`\n  shims are where this shows up. Remediate by installing a full userland rather than the single tool:\n  Git for Windows, which bundles both; the distribution's `gawk`\u002F`mawk` and `coreutils` on Linux;\n  `brew install gawk coreutils` on macOS. Report the two separately, since a minimal shell can carry\n  one and not the other. The skills `check` step 3 names depend on them, and only\n  `conflict-scan.sh` and `instruction-scan.sh` `exit 2` cleanly, so do not offer the others as still\n  working meanwhile.\n- **no resolvable bash:** also not remediable by one package. The scripts use arrays, `[[ ]]`,\n  process substitution, and `BASH_SOURCE`, so they need a real bash on `PATH`: Git for Windows on\n  native Windows, the distribution's `bash` elsewhere. Nothing bundled runs until it resolves, so\n  say that this FAIL blocks the plugin rather than offering a partial workaround.\n\nThe network row stays INFO and has no `apply` entry on purpose: a failed fetch degrades to SKIP by\ndesign, so there is nothing to remediate.\n\nAfter any install, re-run the relevant probe via Bash (`command -v \u003Ctool>`; the pre-computed rows\npredate the install) and report its actual result. Never claim resolved\non the install command's exit code alone. Re-running `apply` once every probe passes changes nothing and\nreports \"already configured\".\n\nThen converge the one surface this plugin owns, conservatively:\n\n- **No suppression record anywhere**: leave it that way and say so. Absent is valid; an empty\n  scaffold is noise. Scaffold `\u003Chome>\u002Fharness-config.yaml` with the documented shape only on an\n  explicit request.\n- **Team layer present but untracked**: report the STOP and the exact `git add` the operator should\n  run. Never stage on their behalf.\n- **Personal override present but not ignored**: recommend the recursive `.claude\u002F**\u002F*.local.*` line and leave\n  the `.gitignore` edit to the consumer.\n- **Malformed or unrecognized entries**: report them and stop. Never rewrite, reorder, or drop an\n  operator's suppression: an entry this skill cannot reconcile is a question for the operator, and a\n  silent rewrite would hide the very finding the entry was suppressing.\n\nEvery write names the file and the exact change before making it, and preserves unrelated content.\n\n## `wsl-profile` (print only)\n\nAn opt-in settings profile for Claude Code inside WSL. Read\n[reference\u002Fwsl-profile.md](reference\u002Fwsl-profile.md) for what it holds and its limits.\n\n1. Run `bash ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsetup\u002Fscripts\u002Fwsl-profile.sh detect`. Exit 1 means this is\n   not a WSL host: say the profile does not apply and stop.\n2. Run `bash ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsetup\u002Fscripts\u002Fwsl-profile.sh print`. It fills in the\n   running user's paths and the Windows host's `\u002Fmnt\u002F\u003Cdrive>\u002FUsers\u002F\u003Cuser>` directories. Show the\n   block, relay its stderr notes (several Windows users, or placeholders left to fill in), and tell\n   the user to merge it into their own settings file.\n3. State the limit from the reference: deny rules do not stop a script that opens files itself; the\n   sandbox is the OS-level control.\n4. Name `appendWindowsPath=false` in `wsl.conf` and the PowerShell symlink as host steps the human\n   runs.\n\nThis action writes no file, edits no settings and never touches `wsl.conf` or creates the symlink. To\ncheck an edited profile, run `... wsl-profile.sh lint \u003Cfile>`.\n\n## Gotchas\n\n- **Never run a git command against the user-global layer.** `~\u002F.claude\u002Faudit-pass.md` is outside the\n  worktree, so `git check-ignore` and `git status` return a meaningless verdict there, or a\n  confidently wrong one when the home directory is itself a git repository.\n- **Missing config is not a failure.** All three suppression layers absent means no suppressions,\n  which is the normal state for a repo that has never suppressed a finding. INFO, never FAIL.\n- **Recommend the recursive gitignore line, and leave the edit to the consumer.** `.claude\u002F**\u002F*.local.*`\n  covers flat, folder-form, and profiled personal overrides alike; the narrower `.claude\u002F*.local.*`\n  silently misses any nested personal override. The consumer's ignore file is their artifact; this skill never writes it.\n- **An install command's exit code is not verification.** After any install, re-run the probe and\n  report its actual result.\n\n## What this skill does NOT do\n\n- Run an audit; that is the plugin's audit and drafting skills (`\u002Fharness-config:audit`,\n  `audit-automation-gaps`, `audit-instructions`, `audit-pass`, `audit-permission-grants`,\n  `audit-permission-state`, `audit-prompting-postures`, `draft-auto-mode-rules`, `unhobble`).\n- Write the plugin cache, Claude Code user settings, or `pluginConfigs`; `wsl-profile` prints a block and the user merges it.\n- Install system packages.\n- Write the consumer's `.gitignore`, stage anything, or edit an operator's suppression entries.\n- Download anything. `check` makes no network call; the audit skills' own doc\u002Fmarketplace fetches are\n  theirs, not setup's.\n","## Pre-computed context\n\n`check`'s tool probes ran at load time. Read these rows instead of re-issuing them; each shows the\ntool's path when present, or `absent` when missing:\n\n- `jq`: !`command -v jq 2>\u002Fdev\u002Fnull || echo absent`\n- `curl`: !`command -v curl 2>\u002Fdev\u002Fnull || echo absent`\n- `awk`: !`command -v awk 2>\u002Fdev\u002Fnull || echo absent`\n- `sort`: !`command -v sort 2>\u002Fdev\u002Fnull || echo absent`\n\nA row reading `[shell command execution disabled by policy]` carries no result: run that tool's\n`command -v` probe via Bash instead.\n\n- **Pointer**: for the placeholder a skipped load-time command leaves, fetch\n  [skills § Inject dynamic context](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fskills#inject-dynamic-context)\n  live.\n- **As of**: 2026-11-11\n- **Recheck trigger**: the placeholder text changes.\n\n## Purpose\n\nSetup per the uniform setup contract (`docs\u002Fplugin-philosophy.md` \"Setup is explicit and repeatable\" in\nthe marketplace repository): `check` inspects and reports, `apply` resolves. This plugin declares no\n`userConfig`, and has two setup concerns:\n\n- the external command-line tools its bundled scripts require, where `apply` is guidance-and-verify\n  with no write path: it points at platform install instructions and never installs a system package;\n- the **tracked consumer-project configuration** `audit` and `audit-pass` read, the `suppressions`\n  mapping of `\u003Chome>\u002Fharness-config.yaml`, the one file `apply` may write. `\u003Chome>` is the\n  convention home the repository binds in the pointer region of its `AGENTS.md` or `CLAUDE.md`\n  (`bash ${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresolve-convention-home.sh` prints it), else `docs\u002Fconventions`.\n\nAction routing: no argument or `check` runs the check; `apply` runs the check first, then remediation;\n`wsl-profile` runs only its own section. All are non-interactive, so never prompt when the action is given.\n\n## `check` (read-only)\n\nThe bundled scripts are the single source of truth for what this plugin requires.\n\n**Read it first.** Probe what it actually does, don't recite this file. Then read the\npre-computed tool rows, run the remaining probes via Bash, and report a PASS\u002FFAIL\u002FINFO table with one remediation line per FAIL. Do not modify anything.\n\nThe runtime scripts and their tools:\n\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit\u002Fscripts\u002Fcheck-plugin-drift.sh`: jq **and** curl\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit\u002Fscripts\u002Fcheck-structure.sh`, `check-hook-coverage.sh` and `fix-plugin-drift.sh`: jq\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit\u002Fscripts\u002Faudit-engine.sh`: jq plus awk and sort; `check-effort-pins.sh`: jq plus awk\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-automation-gaps\u002Fscripts\u002Finventory.sh`: jq plus awk\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-permission-grants\u002Fscripts\u002Fpermission-rule-check.sh`: jq plus awk and sort\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-permission-state\u002Fscripts\u002F*.sh`: jq (required; `permission-state.sh` exits 2 without it), awk and sort; `automode-block-lint.sh` and `automode-entry-diff.sh` add python3 for an optional lane\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fdraft-auto-mode-rules\u002Fscripts\u002Fdraft-automode-block.sh`: jq\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-pass\u002Fscripts\u002Frun-state.sh`: jq (falls back to python3, then to a scan that announces itself)\n- `${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fcheck-retirements.sh`: awk (no jq)\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-pass\u002Fscripts\u002Fstate-digest.sh` and `finding-identity.sh`: sort\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-instructions\u002Fscripts\u002Finstruction-scan.sh`: grep, tr and awk (no jq)\n- `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-instructions\u002Fscripts\u002Fconflict-scan.sh`: awk **and** sort (no jq)\n\nMost scripts that need `jq` probe for it, but only `conflict-scan.sh` and `instruction-scan.sh` probe\nfor `awk` and `sort`; the rest call those with no guard, so read each script's actual calls rather than trusting a single script's prerequisite block to\nspeak for the plugin.\n\n1. **`jq`**, from the pre-computed `jq` row. FAIL if absent: the JSON-parsing scripts need it (`inventory.sh` degrades\n   to an empty inventory; the others `exit 2` with an install remediation). Missing `jq` blocks every\n   skill whose scripts parse JSON (`audit`, `audit-automation-gaps`, `audit-permission-grants`,\n   `audit-permission-state`, `draft-auto-mode-rules`, and `audit-pass`'s run-state helper); `audit-instructions` scans markdown and is unaffected.\n2. **`curl`**, from the pre-computed `curl` row. FAIL if absent, but scoped: only the plugin-drift check\n   (`check-plugin-drift.sh`) uses it and `exit 2`s without it. The rest of `audit` and every other\n   skill still run; say so in the remediation line.\n3. **`awk` and `sort`**, from the pre-computed `awk` and `sort` rows. FAIL if either is absent, and **not**\n   scoped to one skill: `conflict-scan.sh` and `instruction-scan.sh` probe and `exit 2` naming the\n   missing one, while the other scripts in the list above that use them have no prerequisite check\n   at all, so their skills fail mid-run on a bare `command not found` rather than on a named\n   prerequisite. Say in the\n   remediation line that this FAIL reaches six skills (`audit`, `audit-automation-gaps`,\n   `audit-pass`, `audit-permission-grants`, `audit-permission-state` and `audit-instructions`), not\n   just `audit-instructions`. Report `awk` and `sort` by name rather than as one row, since a\n   minimal shell can carry one and not the other.\n4. **Bash shell**, INFO: the scripts are bash (arrays, `[[ ]]`, process substitution, `BASH_SOURCE`),\n   run through Claude Code's Bash tool. Report the resolved interpreter; FAIL only if no bash is\n   resolvable. Pointer: for which shell a platform's sessions get, native Windows included, fetch\n   [tools reference: PowerShell tool](https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Ftools-reference#powershell-tool)\n   live.\n5. **Network reachability**, INFO only: `audit`'s drift\u002Ffreshness fetches read\n   `raw.githubusercontent.com`, and a failed fetch degrades to SKIP rather than a setup failure. Do not\n   fetch here; `check` performs no network call.\n\n### The `audit-pass` suppression record\n\n`audit-pass` reads a tracked suppression record layered per the marketplace's config-cascade\nconvention. Read the operative shape from\n`${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Faudit-pass\u002Freference\u002Fsuppression.md` rather than inferring it. That\nreference ships inside this plugin, so it resolves in an installed cache where a path out to the\nmarketplace's own docs does not. The cross-consumer key contract is the marketplace's published\n**finding-suppression** convention, which is not a runtime dependency of this plugin. All layers\nabsent is a valid state (no suppressions), so report INFO, never FAIL, when none exists.\n\nAnchor at the repo root (`${CLAUDE_PROJECT_DIR}`, else `git rev-parse --show-toplevel`), never a\nCWD-relative read, which resolves a different (or missing) file depending on the subdirectory or\nnested worktree the skill was invoked from, then report one row per layer. The same\ntracked\u002Fignored question has opposite correct answers per layer, so verify each on its own terms:\n\n- **user-global** `~\u002F.claude\u002Faudit-pass.md`: outside the worktree; no git command applies. INFO only.\n- **team** `\u003Chome>\u002Fharness-config.yaml`: must be tracked, probed as the pair:\n  `git check-ignore -v` reports no match (a match is FAIL with the pattern) AND\n  `git ls-files --error-unmatch` exits 0. Untracked while present is a hard STOP:\n  teammates never receive the shared suppressions. Parse it with\n  `awk -v STRICT=1 -f ${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fyaml-subset.awk \u003Cfile>`, the parser the audit engine\n  uses: a non-zero exit is FAIL with the line it prints, because the engine then drops the whole team\n  layer. The common cause is an unquoted `anchor\u002Fv1` key; the parser takes a plain key only of\n  letters, digits, `_` and `-`, so the key is written `\"anchor\u002Fv1\":`.\n- **personal override** `.claude\u002Faudit-pass.local.md`: must be gitignored and never staged. Staged or\n  tracked is a FAIL: a personal deviation can reach team history.\n\nParse each present layer and report as malformed any entry missing **any** of its five required\nkeys: `check`, `claim`, `sites`, `reason`, `date`. Checking only `reason` and `date` would pass an\nentry that `audit-pass` itself rejects, so readiness would report green on configuration that cannot\nsuppress anything. Report as malformed too an entry whose stored constituents do not hash to its own\nkey: the constituents are authoritative and the key is derived from them. A malformed entry does not\nsuppress, and a silent partial parse would turn a formatting slip into a lost check.\n\nReport a **user-global or personal override entry for an id the team layer does not carry** as INFO\n`personal-only, not applied`, naming promotion to the team layer as what makes it take effect. The\nteam layer is the only one that enacts a suppression, so a personal-only entry that looks live is a\nfinding the operator believes is accepted and is not.\n\n## `apply` (idempotent)\n\nRun `check`, then for each FAIL give the platform install instructions from the README Requirements.\nThis skill never installs system packages:\n\n- **missing `jq`:** the platform's jq install (for example `winget install jqlang.jq`, `brew install\n  jq`, or `apt-get install jq`); rerun `check` after.\n- **missing `curl`:** the platform's curl install. Modern Windows and Git Bash already ship `curl`.\n  Only the plugin-drift check needs it, so the rest of the plugin works meanwhile.\n- **missing `awk` or `sort`:** both ship with every POSIX userland, so absence means the shell\n  environment is minimal rather than that one package is missing. Git Bash and Windows `busybox`\n  shims are where this shows up. Remediate by installing a full userland rather than the single tool:\n  Git for Windows, which bundles both; the distribution's `gawk`\u002F`mawk` and `coreutils` on Linux;\n  `brew install gawk coreutils` on macOS. Report the two separately, since a minimal shell can carry\n  one and not the other. The skills `check` step 3 names depend on them, and only\n  `conflict-scan.sh` and `instruction-scan.sh` `exit 2` cleanly, so do not offer the others as still\n  working meanwhile.\n- **no resolvable bash:** also not remediable by one package. The scripts use arrays, `[[ ]]`,\n  process substitution, and `BASH_SOURCE`, so they need a real bash on `PATH`: Git for Windows on\n  native Windows, the distribution's `bash` elsewhere. Nothing bundled runs until it resolves, so\n  say that this FAIL blocks the plugin rather than offering a partial workaround.\n\nThe network row stays INFO and has no `apply` entry on purpose: a failed fetch degrades to SKIP by\ndesign, so there is nothing to remediate.\n\nAfter any install, re-run the relevant probe via Bash (`command -v \u003Ctool>`; the pre-computed rows\npredate the install) and report its actual result. Never claim resolved\non the install command's exit code alone. Re-running `apply` once every probe passes changes nothing and\nreports \"already configured\".\n\nThen converge the one surface this plugin owns, conservatively:\n\n- **No suppression record anywhere**: leave it that way and say so. Absent is valid; an empty\n  scaffold is noise. Scaffold `\u003Chome>\u002Fharness-config.yaml` with the documented shape only on an\n  explicit request.\n- **Team layer present but untracked**: report the STOP and the exact `git add` the operator should\n  run. Never stage on their behalf.\n- **Personal override present but not ignored**: recommend the recursive `.claude\u002F**\u002F*.local.*` line and leave\n  the `.gitignore` edit to the consumer.\n- **Malformed or unrecognized entries**: report them and stop. Never rewrite, reorder, or drop an\n  operator's suppression: an entry this skill cannot reconcile is a question for the operator, and a\n  silent rewrite would hide the very finding the entry was suppressing.\n\nEvery write names the file and the exact change before making it, and preserves unrelated content.\n\n## `wsl-profile` (print only)\n\nAn opt-in settings profile for Claude Code inside WSL. Read\n[reference\u002Fwsl-profile.md](reference\u002Fwsl-profile.md) for what it holds and its limits.\n\n1. Run `bash ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsetup\u002Fscripts\u002Fwsl-profile.sh detect`. Exit 1 means this is\n   not a WSL host: say the profile does not apply and stop.\n2. Run `bash ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsetup\u002Fscripts\u002Fwsl-profile.sh print`. It fills in the\n   running user's paths and the Windows host's `\u002Fmnt\u002F\u003Cdrive>\u002FUsers\u002F\u003Cuser>` directories. Show the\n   block, relay its stderr notes (several Windows users, or placeholders left to fill in), and tell\n   the user to merge it into their own settings file.\n3. State the limit from the reference: deny rules do not stop a script that opens files itself; the\n   sandbox is the OS-level control.\n4. Name `appendWindowsPath=false` in `wsl.conf` and the PowerShell symlink as host steps the human\n   runs.\n\nThis action writes no file, edits no settings and never touches `wsl.conf` or creates the symlink. To\ncheck an edited profile, run `... wsl-profile.sh lint \u003Cfile>`.\n\n## Gotchas\n\n- **Never run a git command against the user-global layer.** `~\u002F.claude\u002Faudit-pass.md` is outside the\n  worktree, so `git check-ignore` and `git status` return a meaningless verdict there, or a\n  confidently wrong one when the home directory is itself a git repository.\n- **Missing config is not a failure.** All three suppression layers absent means no suppressions,\n  which is the normal state for a repo that has never suppressed a finding. INFO, never FAIL.\n- **Recommend the recursive gitignore line, and leave the edit to the consumer.** `.claude\u002F**\u002F*.local.*`\n  covers flat, folder-form, and profiled personal overrides alike; the narrower `.claude\u002F*.local.*`\n  silently misses any nested personal override. The consumer's ignore file is their artifact; this skill never writes it.\n- **An install command's exit code is not verification.** After any install, re-run the probe and\n  report its actual result.\n\n## What this skill does NOT do\n\n- Run an audit; that is the plugin's audit and drafting skills (`\u002Fharness-config:audit`,\n  `audit-automation-gaps`, `audit-instructions`, `audit-pass`, `audit-permission-grants`,\n  `audit-permission-state`, `audit-prompting-postures`, `draft-auto-mode-rules`, `unhobble`).\n- Write the plugin cache, Claude Code user settings, or `pluginConfigs`; `wsl-profile` prints a block and the user merges it.\n- Install system packages.\n- Write the consumer's `.gitignore`, stage anything, or edit an operator's suppression entries.\n- Download anything. `check` makes no network call; the audit skills' own doc\u002Fmarketplace fetches are\n  theirs, not setup's.\n",{"shell":24,"description":7,"allowed-tools":25,"argument-hint":31,"user-invocable":32,"disable-model-invocation":32},"bash",[26,27,28,29,30],"Bash(command -v jq*)","Bash(command -v curl*)","Bash(command -v awk*)","Bash(command -v sort*)","Bash(bash ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsetup\u002Fscripts\u002Fwsl-profile.sh *)","[check|apply|wsl-profile]",true,"main","d0e68c3f36b92a1d6381f0ba0060d7a0b8b886c5","plugins\u002Fharness-config\u002Fskills\u002Fsetup",7,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins","https:\u002F\u002Fgithub.com\u002Fmelodic-software","https:\u002F\u002Fmelodicsoftware.com","Independent software studio building developer tools, automation, and application services, with roots in music.","2026-11-15 05:15:06",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":32},[44,47,50],{"tool":45,"command":46},"npx","npx skills add melodic-software\u002Fclaude-code-plugins --skill setup",{"tool":48,"command":49},"bunx","bunx skills add melodic-software\u002Fclaude-code-plugins --skill setup",{"tool":51,"command":52},"pnpm","pnpm dlx skills add melodic-software\u002Fclaude-code-plugins --skill setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-config\u002Fskills\u002Fsetup\u002FSKILL.md",[55,61,65,71],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Fevals.json","REFERENCE","参考文档",4831,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-config\u002Fskills\u002Fsetup\u002Fevals\u002Fevals.json",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"reference\u002Fwsl-profile.md",3253,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-config\u002Fskills\u002Fsetup\u002Freference\u002Fwsl-profile.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fwsl-profile.sh","SCRIPT","脚本",3559,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-config\u002Fskills\u002Fsetup\u002Fscripts\u002Fwsl-profile.sh",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fwsl-profile.test.sh",4342,"https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-config\u002Fskills\u002Fsetup\u002Fscripts\u002Fwsl-profile.test.sh",[76,83,90,97,102,109],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DYYDG31B9YX7N9MB9QW2GW","track","Backlog reads through the bound tracker: search open and closed items, view one item with its comments and state history. Use when another skill searches or reads tracker items.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsession-flow\u002Fevals\u002Frecall-still-reports-reopened-bug\u002Fwork-items-stub\u002Fskills\u002Ftrack\u002FSKILL.md",[],[],{"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},"01M7DYXVBAVG3NV30PA7GKW9Q6","reviewer-media","Reviewer media for one pull request: decides whether it needs a narrated walkthrough, builds the storyboard from \u002Freview:explain-change's digest, has \u002Fexplainer-video:produce render it and hands the manifest to \u002Fsource-control:pull-request media. Use when asked for 'reviewer media', 'a walkthrough video for this PR', 'a produced video of this change', or when pull-request ready or monitor hands a PR over.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Freview\u002Fskills\u002Freviewer-media\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},"01M7DYRZ5YD44AMYH26YR25GZ8","route","Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-pin-without-override\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":98,"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":99,"categories":100,"keywords":101,"publishedAt":19},"01M7DYRTVT4FWTGDJY0HCCFJMZ","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fdiscovery\u002Fevals\u002Fex-model-override-from-route\u002Fmulti-agent-stub\u002Fskills\u002Froute\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7DYNZC8PNW3T27V2ADKECKJ","principles","Module-design vocabulary for architecture findings, and the checks built on it. Use when: 'what is a deep module', 'what is a seam', 'deep vs shallow module', 'what is the deletion test', 'leverage and locality', 'module design vocabulary', 'which word do we use for X in architecture findings'. Scanning a codebase for friction is \u002Farchitecture:improve.","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fskills\u002Fprinciples\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7DYNMCZNEWBFHV9KTSS6H60","write","Structured five-field bug report (title, steps to reproduce, expected vs actual, justified severity, suggested fix location) from an informal description, read-only. Use when the user names a defect they observed, or asks for one written up ('report a bug', 'file a bug', 'write this up as a bug').","https:\u002F\u002Fgithub.com\u002Fmelodic-software\u002Fclaude-code-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Farchitecture\u002Fevals\u002Fdeepening-defect-goes-to-bugs-write\u002Fbugs-stub\u002Fskills\u002Fwrite\u002FSKILL.md",[],[]]