[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M786VMBF5GH9FMER95QJ56SE":3,"skill-same:01M786VMBF5GH9FMER95QJ56SE":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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M786VMBF5GH9FMER95QJ56SE","sp-tasks",null,"Use when plan artifacts exist and execution needs dependency-aware tasks, guardrails, and parallelization guidance before implementation.","chenziyang110\u002Flaunchdeck","chenziyang110","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43693913?v=4","01M7863EBWK1D0P6A29YGEMAS4","Robin11","01M7863ECM1VB6RXDMHTW90D2T",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"sp-tasks\"\ndescription: \"Use when plan artifacts exist and execution needs dependency-aware tasks, guardrails, and parallelization guidance before implementation.\"\ncompatibility: \"Requires spec-kit project structure with .specify\u002F directory\"\nmetadata:\n  author: \"github-spec-kit\"\n  source: \"templates\u002Fcommands\u002Ftasks.md\"\n---\n## Invocation Syntax\n\n- In this integration, invoke workflow skills with `$sp-plan`-style syntax.\n- References such as `\u002Fsp.plan`, `\u002Fsp.tasks`, or `next_command: \u002Fsp.plan` are canonical workflow-state identifiers and handoff values.\n- Preserve those canonical state tokens exactly in artifacts and workflow state; do not rewrite them to this integration's invocation syntax.\n\n\n\n## Workflow Contract Summary\n\n- **When to use**: Planning artifacts already exist and the remaining gap is concrete execution slicing rather than more design work.\n- **Primary objective**: Produce `tasks.md` with dependency ordering, guardrail carry-forward, execution batches, and join points.\n- **Primary outputs**: `FEATURE_DIR\u002Ftask-index.json` as the canonical task graph for standard\u002Fheavy or any UI-bearing work plus rendered `tasks.md`; light non-UI leader-direct work may use only `tasks.md`. `handoff-to-tasks.json` is a compact agent transition when compatibility requires it. Worker packets are compiled just in time by `sp-implement`; task-generation lane records exist only when lanes were actually delegated.\n- **Default handoff**: \u002Fsp.implement for a clean completed task package; \u002Fsp.analyze only when a persisted legacy or diagnostic state explicitly records that route; \u002Fsp.plan, \u002Fsp.clarify, or \u002Fsp.deep-research when escalated remediation exposes missing upstream truth.\n- **Execution note**: This summary is routing metadata only. Follow the full contract below end-to-end rather than inferring behavior from the description alone.\n\n## Blocked Exit Contract\n\nIf blocked after safe recovery, read and follow\n`.specify\u002Ftemplates\u002Fworkflow-blocker-template.md` and its JSON schema. Never\nreturn only an error or “ask a human”; preserve state and keep agent-capable\nrepair agent-owned. Set `human_action_required: true` only for authority,\ncredentials, protected systems, human decisions\u002Freviews, or physical access.\nTailor steps, expected results, failure paths, evidence, and resume action to\nCI, visual review, or product decisions. Never claim completion.\n\nFor a feature runtime blocker, do not invent `resume_argv` or overwrite an\nexisting blocker. The CLI returns a read-only `show_argv` and structured\n`resolution_action`; `next_argv` stays empty while evidence is missing. After\nthe criteria are proven, attach sanitized evidence using the action's declared\ninput and execute its base argv. It restores the same owner and keeps the full\nblocker audit.\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nYou **MUST** consider the user input before proceeding (if not empty).\n\n## Objective\n\nCompile a ready plan contract into the smallest dependency-safe execution graph that preserves scope, boundaries, obligations, verification, and recovery.\n\n## Context\n\n- Primary authority: `plan-contract.json`; `tasks.md` is the project-facing view and `task-index.json` is canonical for standard\u002Fheavy and all UI-bearing work.\n- Read conditional plan\u002Fspec views only through a required ref or stale condition.\n- Task generation is artifact-only and does not authorize source\u002Ftest edits.\n\n## Process\n\n- If `FEATURE_DIR` is not explicit, run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify lane resolve --command tasks --ensure-worktree`; honor a materialized worktree and stop on `uncertain`.\n- Validate plan revision, target boundary, complete confirmed scope, interfaces, acceptance, `MP-*`, `CA-###`, capability, fidelity, and stop\u002Freopen refs.\n- Reject a target that silently falls back to the current repository when another implementation target was confirmed.\n- Select `light`, `standard`, or `heavy`; delegate only isolated decomposition lanes whose benefit exceeds handoff cost.\n- Build outcome-oriented tasks, dependency edges, safe parallel batches, and explicit join points. Every join point records validation target, command\u002Fcheck, pass condition, and recovery.\n- Run deterministic graph review; repair task-layer defects locally and route upstream truth defects to their owner.\n\n## Tiered Contract\n\n- `leader-direct`: id, objective, dependencies, expected path\u002Fdiscovery scope, acceptance, verification.\n- `delegated`: add bounded reads\u002Fwrites, forbidden drift, authoritative refs, done condition, and recovery.\n- `parallel\u002Fhigh-risk`: add exact write isolation, task-relevant obligation\u002Ffidelity refs, consumer evidence, join point, and stop\u002Freopen conditions.\n\nExact delegated packet shape lives in `.specify\u002Ftemplates\u002Ftask-packet-template.json`. `sp-implement` renders and validates only the current packet against live code; do not copy the schema into `tasks.md` or pre-generate all packets.\n\n## Output Contract\n\n- Light non-UI: compact `tasks.md` unless a graph adds real resume value.\n- Any UI-bearing work: minimal canonical `task-index.json` plus task-local UI contracts in rendered `tasks.md`.\n- Standard\u002Fheavy: canonical `task-index.json` plus rendered `tasks.md`.\n- Delegated decomposition only: one lane manifest plus lane results.\n- Consume every accepted task-generation lane result into a task, edge, batch, join point, guardrail, or explicit blocker\u002Fdeferral; chat-only lane output is not handoff truth.\n- Ready transition: canonical task ref, semantic delta, required refs, blockers\u002Frecovery, and exactly one next action.\n\n## Guardrails\n\n- Do not duplicate full upstream contracts, pre-generate every worker packet, or turn task generation into implementation.\n- Do not mark a task ready when dependencies, acceptance, required refs, verification, write isolation, or recovery are unresolved.\n- Route spec or plan truth defects upstream; repair only task-graph defects locally.\n\n## Senior Consequence Analysis Gate\n\nRun this gate whenever the request, artifact set, defect, or planned change can affect lifecycle operations, running objects, concurrent work, destructive behavior, shared state, downstream consumers, compatibility, security-sensitive behavior, or multiple plausible product behaviors.\n\nAlso trigger it for a new or changed entry point over an existing operation, a direct\u002Fbackground\u002Fheadless\u002Fsystem entry point, or a changed consumer or interaction owner. Build the result inventory from current result\u002Ferror definitions, existing consumers, state transitions, tests, and UI\u002Fwindow\u002Frequest\u002Fretry owners. Reusing an executor proves operation reuse; it does not prove that the new consumer preserves every terminal, recoverable, partial, cancelled, or user-input-required outcome.\n\nProject cognition first. Use the project cognition runtime to identify ownership, consumers, state surfaces, change-propagation facts, verification routes, conflicts, known unknowns, and coverage gaps. Senior consequence analysis second. Turn those facts into explicit product and implementation obligations instead of treating the graph as the decision-maker.\n\nProject cognition readiness provides navigation state; route recovery by `recommended_next_action.action_id`. If readiness is `query_ready`, read top-level `minimal_live_reads` first, then use lane-level `first_pass_paths` reasons. If readiness is `review`, inspect the returned `minimal_live_reads` before continuing and treat `coverage_diagnostics` as confidence and closeout signals. If readiness is `needs_rebuild`, preserve resumable non-rebuild actions such as `complete_scan_packets`; only `action_id=project_cognition.rebuild` may consume `rebuild_reasons[]` and `recommended_next_action.workflow_routes.classic.steps` as a rebuild handoff. That rebuild route remains reserved for brownfield first\u002Fmissing\u002Funusable baseline, schema failure, schema v1 or old broad-schema rebuild-required readiness, zero active-generation `path_index` rows outside `greenfield_empty`, missing or invalid `alias_index`, `explicit_rebuild_requested`, or `baseline_identity_invalid`. If readiness is `blocked`, report the blocked state and continue with live repository evidence unless the user's actual request is to fix cognition runtime state. If readiness is `unsupported_runtime`, continue with live evidence and record that compass intake was unavailable. If `baseline_kind=greenfield_empty`, continue with workflow artifacts and live requirements; do not recommend map-scan -> map-build solely because the graph has no paths. Carry relevant project cognition facts, returned `minimal_live_reads`, inference notes, and coverage gaps into the workflow's artifacts or durable state, but back consequence claims with live code, tests, scripts, configuration, or authoritative docs. Mutation closeout is separate from entry routing: entry stale may continue, but that does not allow source\u002Fruntime mutation workflows to defer closeout. Workflow-owned mutation closeout is not an external map-maintenance handoff; after changing project-related files or behavior, the workflow must run inline project cognition update from its changed paths, affected surfaces, and verification evidence, with `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe mark-dirty` only as fallback when inline update cannot complete. `sp-map-update` is for manual\u002Fexternal maintenance and follow-up repair; it is external map maintenance, not routine closeout for this workflow's own changes. In shared routing summaries, sp-map-update is for manual\u002Fexternal maintenance and ordinary existing-baseline gaps.\n\nRequired output when the gate triggers:\n\n- **Affected Object Map**: name each object, record, worker, queue, artifact, command, API, file surface, user-visible state, or downstream consumer that can be affected.\n- **State-Behavior Matrix**: describe behavior for each important lifecycle state, including created, queued, running, paused, failed, cancelled, completed, resumed, archived, missing, stale, or partially refreshed states when relevant.\n- **Dependency Impact Table**: map direct dependencies, indirect consumers, shared state, compatibility surfaces, validation routes, and adjacent workflows that can break if semantics change.\n- **Recovery And Validation Contract**: state rollback, retry, idempotency, cleanup, migration, observability, and validation evidence required before handoff or completion.\n- **Coverage Gaps**: list what project cognition or live evidence cannot prove, who must resolve each gap, the latest safe resolve phase, the stop-and-reopen condition, and the routing decision: current workflow may continue with an assumption, must ask the user, must route to clarification or deep research, or must request map maintenance.\n- **Consequence Obligations**: assign stable `CA-###` IDs to every obligation that must survive downstream handoff, task generation, worker packets, verification, or debug closeout. Each `CA-###` must include claim, affected objects, owner workflow, latest resolve phase, status, and stop-and-reopen condition.\n- **Entrypoint Outcome Contract**: when the entry-point trigger applies, persist `entrypoint_outcome_contract` in `spec-contract.json`. Keep live-evidence-backed result inventory separate from product dispositions, and map every preserved or adapted outcome to acceptance refs and `CA-###` consequence refs. Plan and Tasks consume those CA refs through the existing consequence chain; do not create a parallel outcome ledger downstream.\n\nStand down only for docs-only wording changes, trivial isolated fixes, or local refactors that cannot affect lifecycle operations, running state, destructive operations, shared state, downstream consumers, compatibility, security, or multiple behavior choices. Record the no-trigger reason or stand-down reason in the workflow's durable artifact or closeout before skipping the required outputs.\n\nIf the gate triggers and the current workflow cannot preserve the required outputs, stop and route to the workflow that can. Do not mark ready, resolved, handoff-ready, planning-ready, or complete while triggered consequence obligations remain unresolved, unmapped, or unsupported by validation evidence.\n\n## Agent Phase Handoff\n\nPhase handoff is an agent-only control surface. Human-facing explanation belongs in the visible reply or in project documents that have independent review value; it must not be duplicated into a handoff.\n\n- The previous phase's canonical JSON contract is the next phase's primary input.\n- Use the compact transition shape from `.specify\u002Ftemplates\u002Fagent-phase-transition-schema.json`: `status`, `source_ref`, `semantic_delta`, `required_refs`, `blockers`, `next_action`, and recovery only when blocked.\n- Carry the minimum sufficient context: include a fact only when omitting it could change the next action, lose a requirement or obligation, force rediscovery, weaken verification, or prevent safe recovery.\n- Preserve decisions, acceptance criteria, evidence provenance, `MP-*`, `CA-###`, and stop\u002Freopen conditions by stable reference. Do not copy their full bodies into every downstream artifact.\n- Protected `MP-*` and `CA-###` obligations must not drop between phases. A downstream phase may resolve or reopen them, but may not silently omit them.\n- Carry the locked implementation-target reference. A cross-project transition must not silently point to the current repository when the confirmed target differs.\n- Consume project rules and Learning through `learning start --command \u003Cclassic-command-name> -> list -> show`; run selected `show_argv` only. Constitution remains at `.specify\u002Fmemory\u002Fconstitution.md`; never parse Learning storage.\n- Capture at owning closeout only when the lesson would change a future action; prefer `learning capture-auto`.\n- A rendered Markdown view is never an agent handoff authority. Do not require Markdown\u002FJSON companion agreement.\n- Revalidate upstream truth only when its revision changed, evidence became stale, live repository facts contradict it, or the current phase discovers a scope, boundary, feasibility, or risk change.\n- If `semantic_delta` is empty, do not repeat upstream questions, approach selection, or user confirmation.\n\n## Deterministic Workflow Runtime\n\nFor a feature-bearing `specify -> plan -> tasks -> implement -> review -> accept` stage,\nthe CLI owns phase order in `FEATURE_DIR\u002Fworkflow-runtime.json`. Do not author\nor advance `workflow-runtime.json` by hand. `workflow-state.md` remains the rich\nworkflow-owned evidence and resume surface for Learning, clarification,\nresearch, analysis, and profile-specific details; the phase runtime must not overwrite\nor parse it as its revision authority.\n\n- After `FEATURE_DIR` is known, run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow show --feature-dir '\u003Cfeature-dir>' --format json`. If state is missing at the first feature stage, run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow enter --command specify --feature-dir '\u003Cfeature-dir>' --format json`.\n- On entry to `plan`, `tasks`, `implement`, `review`, or `accept`, use the current revision with `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow transition --to '\u003Cthis-stage>' --feature-dir '\u003Cfeature-dir>' --expected-revision '\u003Crevision>' --format json` before writing that stage's artifacts. The command validates the completed source-stage artifacts and refuses skips, stale revisions, or incomplete handoffs with exit `10`.\n- After the owning stage finishes its artifact closeout, run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow complete-stage --feature-dir '\u003Cfeature-dir>' --expected-revision '\u003Crevision>' --format json`. The runtime validates the stage artifacts, records non-terminal `status: completed`, and returns the one legal transition argv; do not edit phase state manually.\n- The destination command owns the returned transition. A completed stage recommends the next command but must not execute `workflow transition` to that next stage in the same invocation.\n- Use `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow next --feature-dir '\u003Cfeature-dir>' --format json` for the compact next action. While a stage is active its `next_argv` completes that stage; after completion it transitions to the successor. Execute only structured argv and do not reconstruct flags from prose.\n- When fresh evidence invalidates an earlier required stage, preserve the stale\n  artifacts for audit and reopen the highest invalid stage with\n  `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow reopen --to '\u003Cspecify|plan|tasks|implement|review>' --feature-dir '\u003Cfeature-dir>' --expected-revision '\u003Crevision>' --reason '\u003Ccompact-reason>' --evidence '\u003Csanitized-evidence>' --invalidated-artifacts '\u003Cartifact>' --format json`.\n  Repeat `--evidence` and `--invalidated-artifacts` as needed. The CLI permits\n  a strict backward move or reactivation of the same completed non-accept stage,\n  including `implement` and `review`; an active same-stage owner simply continues. Honor any\n  persisted blocker before retrying. Failed acceptance uses\n  `accept route-repair`, never generic reopen. Every non-human-access acceptance\n  failure first reopens Review; the Review Leader diagnoses it, dispatches an\n  independent Fix and revalidation cycle, and may reopen an upstream truth\n  owner only after proving that correct implementation is impossible under the\n  current requirement, design, or architecture truth. After any repair, rerun\n  the full frozen Human Acceptance Universe; preserve no stale human PASS.\n- After safe agent recovery is exhausted, persist the blocker through `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow block --input '\u003Cblocker-json-or->' --format json`. Obtain its exact input shape with `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify api schema workflow-block-input --format json`; the runtime rejects replacement of an unresolved blocker and returns the human tutorial, a safe read-only `show_argv`, and a structured `data.resolution_action`. While evidence is missing, `next_argv` is intentionally empty.\n- When the recorded unblock criteria are proven, append each sanitized evidence item to the runtime-returned `resolution_action.base_argv` using its declared `--resolution-evidence` required input, then execute that argv. This invokes `workflow resolve`, preserves the full prior blocker audit, and reactivates the same stage; do not reconstruct other flags or clear blocker state manually.\n- After explicit human acceptance, run the acceptance-owned `accept closeout` command and execute its successful response's `next_argv` verbatim. That revision-bound argv invokes `workflow closeout`; do not reconstruct it from prose or a remembered revision. It validates and snapshots acceptance evidence before marking the feature workflow complete.\n\nFor every blocked exit, including a pre-feature discussion that cannot use the\nfeature runtime yet, follow\n`.specify\u002Ftemplates\u002Fworkflow-blocker-template.md` and its schema. Report the\nexact cause, sanitized evidence, attempted recovery and result, affected scope,\nsmallest next action, observable unblock criteria, and exact resume point. Keep\nagent-capable repair agent-owned. When authority, credentials, a protected\nsystem, physical access, or human judgment is genuinely required, add the full\nHuman Action Guide: goal, prerequisites, safety notes, numbered exact actions,\nexpected result and safe failure branch for every action, independent\nverification, sanitized evidence to return, and the exact resume command.\n\n## Planning Cognition Policy\n\nUse project cognition as advisory navigation, never as sole proof. For an unchanged phase pass, run at most one `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe compass --intent plan` intake when the canonical context capsule lacks a required facet.\n\nRun or emulate:\n\n```text\nC:\\Users\\11034\\.specify\\bin\\project-cognition.exe compass --intent plan '--query=\"$ARGUMENTS\"' --format json\n```\n\n- Read and carry `epistemic_contract` in the phase context capsule. Require `graph_role=route_candidate_only`, `fact_source_of_truth=live_repository`, `live_verification_required=true`, `graph_only_claims_allowed=false`, and `unverified_claim_action=withhold`. The contract cannot authorize source changes and cannot prove current behavior.\n- Graph claims are indexed assertions. Even `verified_in_graph_generation` is only an active graph-generation state, not current repository truth; graph claims cannot authorize source changes and cannot set workflow `claim_ready=true`. Use related graph claims to narrow live reads, then prove or reject them from bounded repository evidence.\n- Reuse the returned `compass_state`, `minimal_live_reads`, `first_pass_paths`, lane `claim_refs`, `coverage_diagnostics`, and `expansion_ref` as the phase context capsule. Treat `route_confidence` only within `confidence_scope=route_candidate`; use top-level advanced-query `claim_signals` or `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe expand --section claim_evidence` for bounded `source_path`\u002F`span` evidence. These signals require live verification and cannot prove current repository truth. Read only the minimum live evidence needed for the active claim and let contradictory live evidence override the route candidate.\n- Interpret `claim_ranking` only as a bounded rerank of candidates already eligible through `match_score`; claims cannot create candidates and cannot replace live verification. Fresh supported or graph-generation-verified claims add at most `+1`, while stale and contradicted claims subtract `-1` and `-2`. On `stale_claim_signal` or `contradicted_claim_signal`, preserve `usable_with_review`, follow `reconcile_claims_with_minimal_live_reads`, and complete the lane action against live repository evidence.\n- When claim-specific bounded reads settle a stale or contradicted route, provide only reconciliation intent: workflow, stable `claim_id`, reason, repository-relative `source_path`, bounded line `span`, `supporting` or `contradicting` role, and optional claim-specific verification. Run `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe claim-reconcile prepare --input \u003Cintent.json> --format json`; the runtime owns all integrity fields and the prepared packet path. Execute the returned `apply_argv` exactly (`C:\\Users\\11034\\.specify\\bin\\project-cognition.exe claim-reconcile apply --input \u003Cprepared_packet_path> --format json`). Generic verification cannot re-promote a graph claim. If reconciliation is ready, rerun Compass once for the planning route; otherwise withhold the claim.\n- `fresh`, `stale`, `possibly_stale`, `needs_update`, and `partial_refresh` are planning advisories. Follow returned `minimal_live_reads` and prove the active claim from live evidence; do not stop solely because the index is stale.\n- Rebuild only for an unusable\u002Fmissing baseline or explicit rebuild condition. Do not turn ordinary planning into map maintenance.\n- Artifact-only specification, planning, and task generation do not mark project cognition dirty. A cognition follow-up is required only after actual source\u002Fruntime truth changes.\n- For UI-bearing work, use the same intake to locate likely real entry points,\n  token\u002Ftheme\u002Fcomponent owners, reusable patterns, required states, responsive\n  behavior, visual\u002Faccessibility tests, and design assets. Verify selected paths\n  live, then carry only the compact routes needed by downstream task packets.\n\n[AGENT] For project-cognition-backed semantic intake, routing, audit, resume, or final-claim gates, read `references\u002Fsemantic-work-contract.md`.\n\n## Adaptive Artifact-Phase Execution\n\nThis partial governs artifact-producing adaptive phases such as `sp-design`, `sp-plan`, and `sp-tasks`. `sp-implement` has its own task-level adaptive controller; debug, map, PRD, and other workflows keep their command-specific execution contracts.\n\nSelect the execution mode before dispatch:\n\n- `light`: low-risk, single-lane artifact work that is safe for leader-inline synthesis.\n- `standard`: bounded planning or task-generation work where native subagents should be used when available.\n- `heavy`: safety-critical, cross-boundary, high-risk, or hard-to-packetize work that requires safe native delegation before synthesis continues.\n\nRecord the adaptive decision fields exactly:\n\n- `execution_model: adaptive`\n- `execution_mode: light | standard | heavy`\n- `workflow_status: ready | blocked`\n- `dispatch_shape: leader-inline | one-subagent | parallel-subagents | subagent-blocked`\n- `execution_surface: leader-inline | native-subagents | none`\n- `capability_degraded: false | true`\n- `blocked_reason: required when blocked`\n\nUse `choose_subagent_dispatch(command_name=\"plan\" | \"tasks\", snapshot, workload_shape)` as the shared policy contract. Derive `workload_shape.lightweight_safe` from workload shape and risk keys; do not invent a separate template-only boolean.\n\nDispatch rules:\n\n- Light mode records `dispatch_shape: leader-inline`, `execution_surface: leader-inline`, `workflow_status: ready`, and `capability_degraded: false`.\n- Standard mode uses native subagents when available: one validated lane records `one-subagent`; two or more isolated lanes record `parallel-subagents`.\n- Standard mode may degrade to leader-inline only when native subagents are unavailable and no high-risk trigger is present; record `capability_degraded: true`.\n- Heavy mode must use native subagents with safely packetized lanes. If native subagents are unavailable, or if the work cannot be packetized safely, record `workflow_status: blocked`, `dispatch_shape: subagent-blocked`, `execution_surface: none`, and `blocked_reason`.\n\nArtifact-writing delegated lanes must use writable, execution-capable native subagents. If the runtime exposes role, sandbox, or permission choices, select a role\u002Fsandbox that can write the declared handoff file. Do not dispatch a read-only explorer, reviewer, or diagnostic lane when the lane must write a filesystem handoff; read-only lanes may provide supplemental evidence, but they do not satisfy `one-subagent` or `parallel-subagents` handoff requirements. The lane contract's allowed write scope must include the exact expected handoff path and must forbid unrelated writes unless the command explicitly assigns an additional generated artifact. If a delegated lane returns prose, idle state, or an unwritten handoff, stop or re-dispatch with a writable lane and the valid handoff path.\n\nDelegated lanes still require structured handoffs before synthesis. If delegated lanes were used, consume the one lane manifest and every accepted lane result before final output; do not duplicate the same events into evidence-index and checkpoint logs. If no lanes were delegated, report the delegated-lane field as `none`.\n\nManaged-team fallback is not part of adaptive plan\u002Ftasks dispatch. Do not route blocked adaptive planning or task generation to `sp-teams`, managed-team lifecycle language, or a durable team fallback from this command.\n\n## Main Flow\n\n1. Run `.specify\u002Fscripts\u002Fpowershell\u002Fcheck-prerequisites.ps1 -Json` to resolve `FEATURE_DIR` and prerequisites without task writes, then enter `tasks` through the deterministic workflow transition. The CLI owns phase state; keep implementation blocked until this task-generation stage completes.\n2. Read `plan-contract.json` first, reuse its context capsule and referenced spec obligations, and open project-facing or live files only for named required references or stale evidence.\n3. Preserve complete-first scope and map every `CA-###`, `MP-*`, preserved create\u002Fscaffold or other capability operation, reference-fidelity item, and user-observable UI\u002FTUI\u002FCLI\u002FAPI\u002Fruntime path before finalizing `tasks.md`. Every UI-bearing task—not only screenshot-driven work—materializes the exact current object referenced by `.specify\u002Ftemplates\u002Ftask-index-template.json#\u002Fui_contract_schema_ref` from `.specify\u002Ftemplates\u002Ftask-packet-template.json#\u002Fui_contract`, then renders Design Quality Coverage plus compact per-task `Scope Boundaries` and `UI Implementation Contract` projections: work\u002Fsurface\u002Fplatform types, subject\u002Faudience\u002Fjob, three theses, signature, approved visual ref, task-relevant reference\u002Fcontent\u002Fimage records, `fidelity_level`, states, must-preserve\u002Fadapt\u002Fnot rules, `required_evidence`, difference inventory, accepted deviations, and real-entrypoint proof under `real_entrypoint_evidence`. Required evidence includes `structure_snapshot`, `visual_capture`, `runtime_diagnostics`, and comparison\u002Fhuman review; synthetic component proof is insufficient.\n4. Use `choose_subagent_dispatch(command_name=\"tasks\", snapshot, workload_shape)` only for isolated task-generation lanes. When lanes are delegated, write one `task-generation\u002Flane-manifest.json` plus one result per lane under `task-generation\u002Fhandoffs\u002F`; do not duplicate the same events into evidence-index and checkpoint logs.\n5. Use task-index.json as the canonical task graph for standard\u002Fheavy and every UI-bearing task set, then render `tasks.md`; only light non-UI leader-direct work may remain a compact `tasks.md`. A ready version-2 index is mandatory whenever the plan has acceptance refs: its top-level `acceptance_refs` must be the complete unique ordered list `plan-contract.json#\u002Facceptance_refs\u002F0..N-1`, never copied spec refs or a selected subset. Record every official entrypoint in `official_entrypoints`, a minimal complete `system_review_scenarios` matrix, and stable `review_obligations` covering every entrypoint, acceptance\u002Fcapability\u002Fmust-preserve\u002Fconsequence\u002Ffidelity reference, changed user-observable journey, consumer surface, required UI state, wiring path, and affected regression path. Every required obligation maps to one or more scenario ids so `sp-review` can prove zero uncovered scope instead of reconstructing executable acceptance from prose. Each `acceptance_ref` must have at least one dedicated required system-review scenario whose required acceptance-source set is exactly that one ref; a broad regression scenario may be additional evidence but cannot serve as any ref's dedicated witness. Separately freeze a non-empty Human Acceptance Universe in `human_acceptance_obligations` and `human_acceptance_scenarios`: cover every new or changed requirement that a human can exercise end to end; every obligation source is one canonical task-index `acceptance_refs` value, and every scenario records a non-empty human `actor`, official entrypoint, starting state, human action, observable terminal outcome, required\u002Foptional status, Review-scenario linkage, and obligation mapping. Every required human scenario links at least one dedicated required Review scenario for its own `acceptance_ref`; require zero uncovered required human obligations. Human performs these requirement journeys later in `sp-accept`; they are not a copy of startup, wiring, diagnostics, or broad regression scenarios, so do not repeat System Review. Do not pre-generate a full worker packet for every task. Record enough task shape for `sp-implement` to compile delegated packets just in time from the current repository state.\n   Set root `validation_policy` to `mode: feature_epochs`, `max_epochs: 3`, `budget_scope: implement-review`, the shared `budget_ref`, and `heavy_gate_owner: leader`. Keep full-suite, build, integration, E2E, and visual gates in feature-level `validation`\u002Ftask `verification`; put only cheap changed-scope checks safe to run for one Txx in that task's `task_checks`. Workers never inherit the heavy gates.\n6. Run deterministic task-graph validation for coverage, dependency cycles, write-set safety, acceptance, and verification. Use agent review only when ambiguity or high-risk judgment remains; repair task-layer defects or escalate when upstream truth is missing.\n7. Run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify hook validate-artifacts --command tasks --feature-dir '\u003Cfeature-dir>' --format json`, repair or reopen the owning upstream phase on failure, and hand off directly to `$sp-implement` only after a clean result and `next_command: \u002Fsp.implement`.\n\nDo not edit production source or tests, migrations, or runtime configuration. This stage owns only the executable task graph and its task-generation evidence; implementation begins only in a separately invoked `$sp-implement` workflow.\n\n## Detailed References\n\nRead [Reference index](references\u002FINDEX.md) before applying detailed contracts.\n\n- [plan intake](references\u002Fplan-intake.md)\n- [task generation sequence](references\u002Ftask-generation-sequence.md)\n- [task packet schema](references\u002Ftask-packet-schema.md)\n- [dependencies and parallel safety](references\u002Fdependencies-and-parallel-safety.md)\n- [must preserve ledger](references\u002Fmust-preserve-ledger.md)\n- [review and repair](references\u002Freview-and-repair.md)\n\n## Codex Subagent Capability Discovery\n\n- Execution model: preserve the workflow's existing `subagent-mandatory`, `subagents-first`, `adaptive`, or `subagent-assisted` policy.\n- Dispatch shape: preserve the workflow's existing dispatch shape; use `subagent-blocked` only after the discovery step below fails or is unsafe.\n- Execution surface: prefer `native-subagents` when the current runtime supports it; use `none` only after recording the unavailable or unsafe surface.\n- Native subagent capability discovery: Before recording `subagent-blocked`, confirm the current runtime exposes `spawn_agent`, `wait_agent`, and `close_agent`; if they are not visible, use the active tool discovery mechanism for multi-agent or subagent tools first.\n- Do not record `subagent-blocked` until this capability discovery step is complete and the exact unavailable or unsafe surface is recorded.\n- Native subagent dispatch: Dispatch bounded subagents through `spawn_agent`.\n- Join behavior: Rejoin with `wait_agent`, integrate, then `close_agent`.\n- Preserve this workflow's existing packet, handoff, artifact, and result schema; this section only governs capability discovery before dispatch or blocked-state recording.\n\n## Project Cognition Freshness Closeout\n\n- This workflow is artifact-only unless the user explicitly requested source\u002Fruntime\u002Ftemplate\u002Fconfig\u002Ftest\u002Fgenerated-asset changes; do not call `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe mark-dirty --help`, `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe complete-refresh --help`, or `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe validate-build --format json` just because `sp-specify`, `sp-plan`, or `sp-tasks` wrote planning artifacts.\n- If this planning workflow makes actual source\u002Fruntime\u002Ftemplate\u002Fconfig\u002Ftest\u002Fgenerated-asset changes in the current run, it stops being artifact-only for closeout: run inline project cognition update from the workflow-owned changed paths and affected surfaces.\n- Git-baseline freshness only changes after source\u002Fruntime\u002Ftemplate\u002Fconfig\u002Ftest\u002Fgenerated-asset changes are recorded; planning-only artifact edits do not require `project-cognition complete-refresh`, and manual override\u002Ffallback belongs only to an explicit map-maintenance recovery path.\n- Inline project cognition update uses `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe delta append --help` followed by `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe update --delta-session '\"$DELTA_SESSION_ID\"' --reason workflow-finalize --format json` when a delta session exists, or `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe update --payload-file '\".specify\u002Fproject-cognition\u002Fupdates\u002F\u003Cupdate-id>.json\"' --reason workflow-finalize --format json` when no delta session exists.\n- The payload-file path must include changed_paths, behavior_surfaces, generated_surfaces, state_contracts, verification, known_unknowns, and confidence_notes so the update is equivalent to `sp-map-update`, not just a path stamp; `verification_evidence` and `generated_surface_notes` are accepted compatibility aliases.\n- Use `known_unknowns` only for blockers that make the cognition update unsafe to trust. If unrelated dirty or untracked working-tree paths were excluded by explicit workflow-owned paths, record that as `confidence_notes` or `boundary.initial_dirty_paths`, not as blocking `known_unknowns`.\n- clean closeout keys on `result_state`, not `update_id`, `last_update_id`, or freshness alone. Treat `ready` and `no_op` as clean, `partial_refresh` as recorded but not fully clean, `needs_rebuild` as a map-scan\u002Fmap-build route, `blocked` as blocked, and `recorded` as legacy recorded-only output that is never clean completion.\n- Use `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe mark-dirty --reason '\"\u003Creason>\"' --format json` only when inline update cannot complete.\n- `sp-map-update` is for manual\u002Fexternal maintenance and follow-up repair, not routine cleanup for changes this workflow just made; run `\u002Fsp-map-scan` followed by `\u002Fsp-map-build` only for brownfield first\u002Fmissing\u002Funusable baseline, schema failure, schema v1 or old broad-schema rebuild-required readiness, zero active-generation `path_index` rows outside `greenfield_empty`, missing or invalid `alias_index`, `explicit_rebuild_requested`, or `baseline_identity_invalid`.\n\n## Codex Adaptive Dispatch\n\nWhen running `sp-tasks` in Codex, apply the adaptive dispatch decision recorded by `choose_subagent_dispatch`.\n- Light mode records `dispatch_shape: leader-inline` and `execution_surface: leader-inline`; do not spawn task-generation lanes for light work.\n- Standard mode uses `spawn_agent` for bounded lanes when `dispatch_shape` is `one-subagent` or `parallel-subagents`.\n- Standard native-unavailable degradation records `execution_surface: leader-inline` and `capability_degraded: true` only when no high-risk trigger is present.\n- Heavy or safety-critical blocked work records `dispatch_shape: subagent-blocked` and `execution_surface: none` with `blocked_reason`.\n- Launch all independent lanes in the current `parallel-subagents` wave before waiting.\n- Suggested bounded lanes include story and phase decomposition, dependency graph analysis, and write-set or parallel-safety analysis.\n- Use `wait_agent` only at the documented join points before writing `tasks.md` and before emitting canonical parallel batches and join points.\n- Use `close_agent` after integrating finished subagent results.\n","## Invocation Syntax\n\n- In this integration, invoke workflow skills with `$sp-plan`-style syntax.\n- References such as `\u002Fsp.plan`, `\u002Fsp.tasks`, or `next_command: \u002Fsp.plan` are canonical workflow-state identifiers and handoff values.\n- Preserve those canonical state tokens exactly in artifacts and workflow state; do not rewrite them to this integration's invocation syntax.\n\n\n\n## Workflow Contract Summary\n\n- **When to use**: Planning artifacts already exist and the remaining gap is concrete execution slicing rather than more design work.\n- **Primary objective**: Produce `tasks.md` with dependency ordering, guardrail carry-forward, execution batches, and join points.\n- **Primary outputs**: `FEATURE_DIR\u002Ftask-index.json` as the canonical task graph for standard\u002Fheavy or any UI-bearing work plus rendered `tasks.md`; light non-UI leader-direct work may use only `tasks.md`. `handoff-to-tasks.json` is a compact agent transition when compatibility requires it. Worker packets are compiled just in time by `sp-implement`; task-generation lane records exist only when lanes were actually delegated.\n- **Default handoff**: \u002Fsp.implement for a clean completed task package; \u002Fsp.analyze only when a persisted legacy or diagnostic state explicitly records that route; \u002Fsp.plan, \u002Fsp.clarify, or \u002Fsp.deep-research when escalated remediation exposes missing upstream truth.\n- **Execution note**: This summary is routing metadata only. Follow the full contract below end-to-end rather than inferring behavior from the description alone.\n\n## Blocked Exit Contract\n\nIf blocked after safe recovery, read and follow\n`.specify\u002Ftemplates\u002Fworkflow-blocker-template.md` and its JSON schema. Never\nreturn only an error or “ask a human”; preserve state and keep agent-capable\nrepair agent-owned. Set `human_action_required: true` only for authority,\ncredentials, protected systems, human decisions\u002Freviews, or physical access.\nTailor steps, expected results, failure paths, evidence, and resume action to\nCI, visual review, or product decisions. Never claim completion.\n\nFor a feature runtime blocker, do not invent `resume_argv` or overwrite an\nexisting blocker. The CLI returns a read-only `show_argv` and structured\n`resolution_action`; `next_argv` stays empty while evidence is missing. After\nthe criteria are proven, attach sanitized evidence using the action's declared\ninput and execute its base argv. It restores the same owner and keeps the full\nblocker audit.\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nYou **MUST** consider the user input before proceeding (if not empty).\n\n## Objective\n\nCompile a ready plan contract into the smallest dependency-safe execution graph that preserves scope, boundaries, obligations, verification, and recovery.\n\n## Context\n\n- Primary authority: `plan-contract.json`; `tasks.md` is the project-facing view and `task-index.json` is canonical for standard\u002Fheavy and all UI-bearing work.\n- Read conditional plan\u002Fspec views only through a required ref or stale condition.\n- Task generation is artifact-only and does not authorize source\u002Ftest edits.\n\n## Process\n\n- If `FEATURE_DIR` is not explicit, run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify lane resolve --command tasks --ensure-worktree`; honor a materialized worktree and stop on `uncertain`.\n- Validate plan revision, target boundary, complete confirmed scope, interfaces, acceptance, `MP-*`, `CA-###`, capability, fidelity, and stop\u002Freopen refs.\n- Reject a target that silently falls back to the current repository when another implementation target was confirmed.\n- Select `light`, `standard`, or `heavy`; delegate only isolated decomposition lanes whose benefit exceeds handoff cost.\n- Build outcome-oriented tasks, dependency edges, safe parallel batches, and explicit join points. Every join point records validation target, command\u002Fcheck, pass condition, and recovery.\n- Run deterministic graph review; repair task-layer defects locally and route upstream truth defects to their owner.\n\n## Tiered Contract\n\n- `leader-direct`: id, objective, dependencies, expected path\u002Fdiscovery scope, acceptance, verification.\n- `delegated`: add bounded reads\u002Fwrites, forbidden drift, authoritative refs, done condition, and recovery.\n- `parallel\u002Fhigh-risk`: add exact write isolation, task-relevant obligation\u002Ffidelity refs, consumer evidence, join point, and stop\u002Freopen conditions.\n\nExact delegated packet shape lives in `.specify\u002Ftemplates\u002Ftask-packet-template.json`. `sp-implement` renders and validates only the current packet against live code; do not copy the schema into `tasks.md` or pre-generate all packets.\n\n## Output Contract\n\n- Light non-UI: compact `tasks.md` unless a graph adds real resume value.\n- Any UI-bearing work: minimal canonical `task-index.json` plus task-local UI contracts in rendered `tasks.md`.\n- Standard\u002Fheavy: canonical `task-index.json` plus rendered `tasks.md`.\n- Delegated decomposition only: one lane manifest plus lane results.\n- Consume every accepted task-generation lane result into a task, edge, batch, join point, guardrail, or explicit blocker\u002Fdeferral; chat-only lane output is not handoff truth.\n- Ready transition: canonical task ref, semantic delta, required refs, blockers\u002Frecovery, and exactly one next action.\n\n## Guardrails\n\n- Do not duplicate full upstream contracts, pre-generate every worker packet, or turn task generation into implementation.\n- Do not mark a task ready when dependencies, acceptance, required refs, verification, write isolation, or recovery are unresolved.\n- Route spec or plan truth defects upstream; repair only task-graph defects locally.\n\n## Senior Consequence Analysis Gate\n\nRun this gate whenever the request, artifact set, defect, or planned change can affect lifecycle operations, running objects, concurrent work, destructive behavior, shared state, downstream consumers, compatibility, security-sensitive behavior, or multiple plausible product behaviors.\n\nAlso trigger it for a new or changed entry point over an existing operation, a direct\u002Fbackground\u002Fheadless\u002Fsystem entry point, or a changed consumer or interaction owner. Build the result inventory from current result\u002Ferror definitions, existing consumers, state transitions, tests, and UI\u002Fwindow\u002Frequest\u002Fretry owners. Reusing an executor proves operation reuse; it does not prove that the new consumer preserves every terminal, recoverable, partial, cancelled, or user-input-required outcome.\n\nProject cognition first. Use the project cognition runtime to identify ownership, consumers, state surfaces, change-propagation facts, verification routes, conflicts, known unknowns, and coverage gaps. Senior consequence analysis second. Turn those facts into explicit product and implementation obligations instead of treating the graph as the decision-maker.\n\nProject cognition readiness provides navigation state; route recovery by `recommended_next_action.action_id`. If readiness is `query_ready`, read top-level `minimal_live_reads` first, then use lane-level `first_pass_paths` reasons. If readiness is `review`, inspect the returned `minimal_live_reads` before continuing and treat `coverage_diagnostics` as confidence and closeout signals. If readiness is `needs_rebuild`, preserve resumable non-rebuild actions such as `complete_scan_packets`; only `action_id=project_cognition.rebuild` may consume `rebuild_reasons[]` and `recommended_next_action.workflow_routes.classic.steps` as a rebuild handoff. That rebuild route remains reserved for brownfield first\u002Fmissing\u002Funusable baseline, schema failure, schema v1 or old broad-schema rebuild-required readiness, zero active-generation `path_index` rows outside `greenfield_empty`, missing or invalid `alias_index`, `explicit_rebuild_requested`, or `baseline_identity_invalid`. If readiness is `blocked`, report the blocked state and continue with live repository evidence unless the user's actual request is to fix cognition runtime state. If readiness is `unsupported_runtime`, continue with live evidence and record that compass intake was unavailable. If `baseline_kind=greenfield_empty`, continue with workflow artifacts and live requirements; do not recommend map-scan -> map-build solely because the graph has no paths. Carry relevant project cognition facts, returned `minimal_live_reads`, inference notes, and coverage gaps into the workflow's artifacts or durable state, but back consequence claims with live code, tests, scripts, configuration, or authoritative docs. Mutation closeout is separate from entry routing: entry stale may continue, but that does not allow source\u002Fruntime mutation workflows to defer closeout. Workflow-owned mutation closeout is not an external map-maintenance handoff; after changing project-related files or behavior, the workflow must run inline project cognition update from its changed paths, affected surfaces, and verification evidence, with `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe mark-dirty` only as fallback when inline update cannot complete. `sp-map-update` is for manual\u002Fexternal maintenance and follow-up repair; it is external map maintenance, not routine closeout for this workflow's own changes. In shared routing summaries, sp-map-update is for manual\u002Fexternal maintenance and ordinary existing-baseline gaps.\n\nRequired output when the gate triggers:\n\n- **Affected Object Map**: name each object, record, worker, queue, artifact, command, API, file surface, user-visible state, or downstream consumer that can be affected.\n- **State-Behavior Matrix**: describe behavior for each important lifecycle state, including created, queued, running, paused, failed, cancelled, completed, resumed, archived, missing, stale, or partially refreshed states when relevant.\n- **Dependency Impact Table**: map direct dependencies, indirect consumers, shared state, compatibility surfaces, validation routes, and adjacent workflows that can break if semantics change.\n- **Recovery And Validation Contract**: state rollback, retry, idempotency, cleanup, migration, observability, and validation evidence required before handoff or completion.\n- **Coverage Gaps**: list what project cognition or live evidence cannot prove, who must resolve each gap, the latest safe resolve phase, the stop-and-reopen condition, and the routing decision: current workflow may continue with an assumption, must ask the user, must route to clarification or deep research, or must request map maintenance.\n- **Consequence Obligations**: assign stable `CA-###` IDs to every obligation that must survive downstream handoff, task generation, worker packets, verification, or debug closeout. Each `CA-###` must include claim, affected objects, owner workflow, latest resolve phase, status, and stop-and-reopen condition.\n- **Entrypoint Outcome Contract**: when the entry-point trigger applies, persist `entrypoint_outcome_contract` in `spec-contract.json`. Keep live-evidence-backed result inventory separate from product dispositions, and map every preserved or adapted outcome to acceptance refs and `CA-###` consequence refs. Plan and Tasks consume those CA refs through the existing consequence chain; do not create a parallel outcome ledger downstream.\n\nStand down only for docs-only wording changes, trivial isolated fixes, or local refactors that cannot affect lifecycle operations, running state, destructive operations, shared state, downstream consumers, compatibility, security, or multiple behavior choices. Record the no-trigger reason or stand-down reason in the workflow's durable artifact or closeout before skipping the required outputs.\n\nIf the gate triggers and the current workflow cannot preserve the required outputs, stop and route to the workflow that can. Do not mark ready, resolved, handoff-ready, planning-ready, or complete while triggered consequence obligations remain unresolved, unmapped, or unsupported by validation evidence.\n\n## Agent Phase Handoff\n\nPhase handoff is an agent-only control surface. Human-facing explanation belongs in the visible reply or in project documents that have independent review value; it must not be duplicated into a handoff.\n\n- The previous phase's canonical JSON contract is the next phase's primary input.\n- Use the compact transition shape from `.specify\u002Ftemplates\u002Fagent-phase-transition-schema.json`: `status`, `source_ref`, `semantic_delta`, `required_refs`, `blockers`, `next_action`, and recovery only when blocked.\n- Carry the minimum sufficient context: include a fact only when omitting it could change the next action, lose a requirement or obligation, force rediscovery, weaken verification, or prevent safe recovery.\n- Preserve decisions, acceptance criteria, evidence provenance, `MP-*`, `CA-###`, and stop\u002Freopen conditions by stable reference. Do not copy their full bodies into every downstream artifact.\n- Protected `MP-*` and `CA-###` obligations must not drop between phases. A downstream phase may resolve or reopen them, but may not silently omit them.\n- Carry the locked implementation-target reference. A cross-project transition must not silently point to the current repository when the confirmed target differs.\n- Consume project rules and Learning through `learning start --command \u003Cclassic-command-name> -> list -> show`; run selected `show_argv` only. Constitution remains at `.specify\u002Fmemory\u002Fconstitution.md`; never parse Learning storage.\n- Capture at owning closeout only when the lesson would change a future action; prefer `learning capture-auto`.\n- A rendered Markdown view is never an agent handoff authority. Do not require Markdown\u002FJSON companion agreement.\n- Revalidate upstream truth only when its revision changed, evidence became stale, live repository facts contradict it, or the current phase discovers a scope, boundary, feasibility, or risk change.\n- If `semantic_delta` is empty, do not repeat upstream questions, approach selection, or user confirmation.\n\n## Deterministic Workflow Runtime\n\nFor a feature-bearing `specify -> plan -> tasks -> implement -> review -> accept` stage,\nthe CLI owns phase order in `FEATURE_DIR\u002Fworkflow-runtime.json`. Do not author\nor advance `workflow-runtime.json` by hand. `workflow-state.md` remains the rich\nworkflow-owned evidence and resume surface for Learning, clarification,\nresearch, analysis, and profile-specific details; the phase runtime must not overwrite\nor parse it as its revision authority.\n\n- After `FEATURE_DIR` is known, run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow show --feature-dir '\u003Cfeature-dir>' --format json`. If state is missing at the first feature stage, run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow enter --command specify --feature-dir '\u003Cfeature-dir>' --format json`.\n- On entry to `plan`, `tasks`, `implement`, `review`, or `accept`, use the current revision with `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow transition --to '\u003Cthis-stage>' --feature-dir '\u003Cfeature-dir>' --expected-revision '\u003Crevision>' --format json` before writing that stage's artifacts. The command validates the completed source-stage artifacts and refuses skips, stale revisions, or incomplete handoffs with exit `10`.\n- After the owning stage finishes its artifact closeout, run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow complete-stage --feature-dir '\u003Cfeature-dir>' --expected-revision '\u003Crevision>' --format json`. The runtime validates the stage artifacts, records non-terminal `status: completed`, and returns the one legal transition argv; do not edit phase state manually.\n- The destination command owns the returned transition. A completed stage recommends the next command but must not execute `workflow transition` to that next stage in the same invocation.\n- Use `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow next --feature-dir '\u003Cfeature-dir>' --format json` for the compact next action. While a stage is active its `next_argv` completes that stage; after completion it transitions to the successor. Execute only structured argv and do not reconstruct flags from prose.\n- When fresh evidence invalidates an earlier required stage, preserve the stale\n  artifacts for audit and reopen the highest invalid stage with\n  `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow reopen --to '\u003Cspecify|plan|tasks|implement|review>' --feature-dir '\u003Cfeature-dir>' --expected-revision '\u003Crevision>' --reason '\u003Ccompact-reason>' --evidence '\u003Csanitized-evidence>' --invalidated-artifacts '\u003Cartifact>' --format json`.\n  Repeat `--evidence` and `--invalidated-artifacts` as needed. The CLI permits\n  a strict backward move or reactivation of the same completed non-accept stage,\n  including `implement` and `review`; an active same-stage owner simply continues. Honor any\n  persisted blocker before retrying. Failed acceptance uses\n  `accept route-repair`, never generic reopen. Every non-human-access acceptance\n  failure first reopens Review; the Review Leader diagnoses it, dispatches an\n  independent Fix and revalidation cycle, and may reopen an upstream truth\n  owner only after proving that correct implementation is impossible under the\n  current requirement, design, or architecture truth. After any repair, rerun\n  the full frozen Human Acceptance Universe; preserve no stale human PASS.\n- After safe agent recovery is exhausted, persist the blocker through `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify workflow block --input '\u003Cblocker-json-or->' --format json`. Obtain its exact input shape with `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify api schema workflow-block-input --format json`; the runtime rejects replacement of an unresolved blocker and returns the human tutorial, a safe read-only `show_argv`, and a structured `data.resolution_action`. While evidence is missing, `next_argv` is intentionally empty.\n- When the recorded unblock criteria are proven, append each sanitized evidence item to the runtime-returned `resolution_action.base_argv` using its declared `--resolution-evidence` required input, then execute that argv. This invokes `workflow resolve`, preserves the full prior blocker audit, and reactivates the same stage; do not reconstruct other flags or clear blocker state manually.\n- After explicit human acceptance, run the acceptance-owned `accept closeout` command and execute its successful response's `next_argv` verbatim. That revision-bound argv invokes `workflow closeout`; do not reconstruct it from prose or a remembered revision. It validates and snapshots acceptance evidence before marking the feature workflow complete.\n\nFor every blocked exit, including a pre-feature discussion that cannot use the\nfeature runtime yet, follow\n`.specify\u002Ftemplates\u002Fworkflow-blocker-template.md` and its schema. Report the\nexact cause, sanitized evidence, attempted recovery and result, affected scope,\nsmallest next action, observable unblock criteria, and exact resume point. Keep\nagent-capable repair agent-owned. When authority, credentials, a protected\nsystem, physical access, or human judgment is genuinely required, add the full\nHuman Action Guide: goal, prerequisites, safety notes, numbered exact actions,\nexpected result and safe failure branch for every action, independent\nverification, sanitized evidence to return, and the exact resume command.\n\n## Planning Cognition Policy\n\nUse project cognition as advisory navigation, never as sole proof. For an unchanged phase pass, run at most one `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe compass --intent plan` intake when the canonical context capsule lacks a required facet.\n\nRun or emulate:\n\n```text\nC:\\Users\\11034\\.specify\\bin\\project-cognition.exe compass --intent plan '--query=\"$ARGUMENTS\"' --format json\n```\n\n- Read and carry `epistemic_contract` in the phase context capsule. Require `graph_role=route_candidate_only`, `fact_source_of_truth=live_repository`, `live_verification_required=true`, `graph_only_claims_allowed=false`, and `unverified_claim_action=withhold`. The contract cannot authorize source changes and cannot prove current behavior.\n- Graph claims are indexed assertions. Even `verified_in_graph_generation` is only an active graph-generation state, not current repository truth; graph claims cannot authorize source changes and cannot set workflow `claim_ready=true`. Use related graph claims to narrow live reads, then prove or reject them from bounded repository evidence.\n- Reuse the returned `compass_state`, `minimal_live_reads`, `first_pass_paths`, lane `claim_refs`, `coverage_diagnostics`, and `expansion_ref` as the phase context capsule. Treat `route_confidence` only within `confidence_scope=route_candidate`; use top-level advanced-query `claim_signals` or `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe expand --section claim_evidence` for bounded `source_path`\u002F`span` evidence. These signals require live verification and cannot prove current repository truth. Read only the minimum live evidence needed for the active claim and let contradictory live evidence override the route candidate.\n- Interpret `claim_ranking` only as a bounded rerank of candidates already eligible through `match_score`; claims cannot create candidates and cannot replace live verification. Fresh supported or graph-generation-verified claims add at most `+1`, while stale and contradicted claims subtract `-1` and `-2`. On `stale_claim_signal` or `contradicted_claim_signal`, preserve `usable_with_review`, follow `reconcile_claims_with_minimal_live_reads`, and complete the lane action against live repository evidence.\n- When claim-specific bounded reads settle a stale or contradicted route, provide only reconciliation intent: workflow, stable `claim_id`, reason, repository-relative `source_path`, bounded line `span`, `supporting` or `contradicting` role, and optional claim-specific verification. Run `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe claim-reconcile prepare --input \u003Cintent.json> --format json`; the runtime owns all integrity fields and the prepared packet path. Execute the returned `apply_argv` exactly (`C:\\Users\\11034\\.specify\\bin\\project-cognition.exe claim-reconcile apply --input \u003Cprepared_packet_path> --format json`). Generic verification cannot re-promote a graph claim. If reconciliation is ready, rerun Compass once for the planning route; otherwise withhold the claim.\n- `fresh`, `stale`, `possibly_stale`, `needs_update`, and `partial_refresh` are planning advisories. Follow returned `minimal_live_reads` and prove the active claim from live evidence; do not stop solely because the index is stale.\n- Rebuild only for an unusable\u002Fmissing baseline or explicit rebuild condition. Do not turn ordinary planning into map maintenance.\n- Artifact-only specification, planning, and task generation do not mark project cognition dirty. A cognition follow-up is required only after actual source\u002Fruntime truth changes.\n- For UI-bearing work, use the same intake to locate likely real entry points,\n  token\u002Ftheme\u002Fcomponent owners, reusable patterns, required states, responsive\n  behavior, visual\u002Faccessibility tests, and design assets. Verify selected paths\n  live, then carry only the compact routes needed by downstream task packets.\n\n[AGENT] For project-cognition-backed semantic intake, routing, audit, resume, or final-claim gates, read `references\u002Fsemantic-work-contract.md`.\n\n## Adaptive Artifact-Phase Execution\n\nThis partial governs artifact-producing adaptive phases such as `sp-design`, `sp-plan`, and `sp-tasks`. `sp-implement` has its own task-level adaptive controller; debug, map, PRD, and other workflows keep their command-specific execution contracts.\n\nSelect the execution mode before dispatch:\n\n- `light`: low-risk, single-lane artifact work that is safe for leader-inline synthesis.\n- `standard`: bounded planning or task-generation work where native subagents should be used when available.\n- `heavy`: safety-critical, cross-boundary, high-risk, or hard-to-packetize work that requires safe native delegation before synthesis continues.\n\nRecord the adaptive decision fields exactly:\n\n- `execution_model: adaptive`\n- `execution_mode: light | standard | heavy`\n- `workflow_status: ready | blocked`\n- `dispatch_shape: leader-inline | one-subagent | parallel-subagents | subagent-blocked`\n- `execution_surface: leader-inline | native-subagents | none`\n- `capability_degraded: false | true`\n- `blocked_reason: required when blocked`\n\nUse `choose_subagent_dispatch(command_name=\"plan\" | \"tasks\", snapshot, workload_shape)` as the shared policy contract. Derive `workload_shape.lightweight_safe` from workload shape and risk keys; do not invent a separate template-only boolean.\n\nDispatch rules:\n\n- Light mode records `dispatch_shape: leader-inline`, `execution_surface: leader-inline`, `workflow_status: ready`, and `capability_degraded: false`.\n- Standard mode uses native subagents when available: one validated lane records `one-subagent`; two or more isolated lanes record `parallel-subagents`.\n- Standard mode may degrade to leader-inline only when native subagents are unavailable and no high-risk trigger is present; record `capability_degraded: true`.\n- Heavy mode must use native subagents with safely packetized lanes. If native subagents are unavailable, or if the work cannot be packetized safely, record `workflow_status: blocked`, `dispatch_shape: subagent-blocked`, `execution_surface: none`, and `blocked_reason`.\n\nArtifact-writing delegated lanes must use writable, execution-capable native subagents. If the runtime exposes role, sandbox, or permission choices, select a role\u002Fsandbox that can write the declared handoff file. Do not dispatch a read-only explorer, reviewer, or diagnostic lane when the lane must write a filesystem handoff; read-only lanes may provide supplemental evidence, but they do not satisfy `one-subagent` or `parallel-subagents` handoff requirements. The lane contract's allowed write scope must include the exact expected handoff path and must forbid unrelated writes unless the command explicitly assigns an additional generated artifact. If a delegated lane returns prose, idle state, or an unwritten handoff, stop or re-dispatch with a writable lane and the valid handoff path.\n\nDelegated lanes still require structured handoffs before synthesis. If delegated lanes were used, consume the one lane manifest and every accepted lane result before final output; do not duplicate the same events into evidence-index and checkpoint logs. If no lanes were delegated, report the delegated-lane field as `none`.\n\nManaged-team fallback is not part of adaptive plan\u002Ftasks dispatch. Do not route blocked adaptive planning or task generation to `sp-teams`, managed-team lifecycle language, or a durable team fallback from this command.\n\n## Main Flow\n\n1. Run `.specify\u002Fscripts\u002Fpowershell\u002Fcheck-prerequisites.ps1 -Json` to resolve `FEATURE_DIR` and prerequisites without task writes, then enter `tasks` through the deterministic workflow transition. The CLI owns phase state; keep implementation blocked until this task-generation stage completes.\n2. Read `plan-contract.json` first, reuse its context capsule and referenced spec obligations, and open project-facing or live files only for named required references or stale evidence.\n3. Preserve complete-first scope and map every `CA-###`, `MP-*`, preserved create\u002Fscaffold or other capability operation, reference-fidelity item, and user-observable UI\u002FTUI\u002FCLI\u002FAPI\u002Fruntime path before finalizing `tasks.md`. Every UI-bearing task—not only screenshot-driven work—materializes the exact current object referenced by `.specify\u002Ftemplates\u002Ftask-index-template.json#\u002Fui_contract_schema_ref` from `.specify\u002Ftemplates\u002Ftask-packet-template.json#\u002Fui_contract`, then renders Design Quality Coverage plus compact per-task `Scope Boundaries` and `UI Implementation Contract` projections: work\u002Fsurface\u002Fplatform types, subject\u002Faudience\u002Fjob, three theses, signature, approved visual ref, task-relevant reference\u002Fcontent\u002Fimage records, `fidelity_level`, states, must-preserve\u002Fadapt\u002Fnot rules, `required_evidence`, difference inventory, accepted deviations, and real-entrypoint proof under `real_entrypoint_evidence`. Required evidence includes `structure_snapshot`, `visual_capture`, `runtime_diagnostics`, and comparison\u002Fhuman review; synthetic component proof is insufficient.\n4. Use `choose_subagent_dispatch(command_name=\"tasks\", snapshot, workload_shape)` only for isolated task-generation lanes. When lanes are delegated, write one `task-generation\u002Flane-manifest.json` plus one result per lane under `task-generation\u002Fhandoffs\u002F`; do not duplicate the same events into evidence-index and checkpoint logs.\n5. Use task-index.json as the canonical task graph for standard\u002Fheavy and every UI-bearing task set, then render `tasks.md`; only light non-UI leader-direct work may remain a compact `tasks.md`. A ready version-2 index is mandatory whenever the plan has acceptance refs: its top-level `acceptance_refs` must be the complete unique ordered list `plan-contract.json#\u002Facceptance_refs\u002F0..N-1`, never copied spec refs or a selected subset. Record every official entrypoint in `official_entrypoints`, a minimal complete `system_review_scenarios` matrix, and stable `review_obligations` covering every entrypoint, acceptance\u002Fcapability\u002Fmust-preserve\u002Fconsequence\u002Ffidelity reference, changed user-observable journey, consumer surface, required UI state, wiring path, and affected regression path. Every required obligation maps to one or more scenario ids so `sp-review` can prove zero uncovered scope instead of reconstructing executable acceptance from prose. Each `acceptance_ref` must have at least one dedicated required system-review scenario whose required acceptance-source set is exactly that one ref; a broad regression scenario may be additional evidence but cannot serve as any ref's dedicated witness. Separately freeze a non-empty Human Acceptance Universe in `human_acceptance_obligations` and `human_acceptance_scenarios`: cover every new or changed requirement that a human can exercise end to end; every obligation source is one canonical task-index `acceptance_refs` value, and every scenario records a non-empty human `actor`, official entrypoint, starting state, human action, observable terminal outcome, required\u002Foptional status, Review-scenario linkage, and obligation mapping. Every required human scenario links at least one dedicated required Review scenario for its own `acceptance_ref`; require zero uncovered required human obligations. Human performs these requirement journeys later in `sp-accept`; they are not a copy of startup, wiring, diagnostics, or broad regression scenarios, so do not repeat System Review. Do not pre-generate a full worker packet for every task. Record enough task shape for `sp-implement` to compile delegated packets just in time from the current repository state.\n   Set root `validation_policy` to `mode: feature_epochs`, `max_epochs: 3`, `budget_scope: implement-review`, the shared `budget_ref`, and `heavy_gate_owner: leader`. Keep full-suite, build, integration, E2E, and visual gates in feature-level `validation`\u002Ftask `verification`; put only cheap changed-scope checks safe to run for one Txx in that task's `task_checks`. Workers never inherit the heavy gates.\n6. Run deterministic task-graph validation for coverage, dependency cycles, write-set safety, acceptance, and verification. Use agent review only when ambiguity or high-risk judgment remains; repair task-layer defects or escalate when upstream truth is missing.\n7. Run `uvx --from git+https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Fspec-kit-plus.git@6fbbf08a0b6833bb783ec6b418d567776b197ae4 specify hook validate-artifacts --command tasks --feature-dir '\u003Cfeature-dir>' --format json`, repair or reopen the owning upstream phase on failure, and hand off directly to `$sp-implement` only after a clean result and `next_command: \u002Fsp.implement`.\n\nDo not edit production source or tests, migrations, or runtime configuration. This stage owns only the executable task graph and its task-generation evidence; implementation begins only in a separately invoked `$sp-implement` workflow.\n\n## Detailed References\n\nRead [Reference index](references\u002FINDEX.md) before applying detailed contracts.\n\n- [plan intake](references\u002Fplan-intake.md)\n- [task generation sequence](references\u002Ftask-generation-sequence.md)\n- [task packet schema](references\u002Ftask-packet-schema.md)\n- [dependencies and parallel safety](references\u002Fdependencies-and-parallel-safety.md)\n- [must preserve ledger](references\u002Fmust-preserve-ledger.md)\n- [review and repair](references\u002Freview-and-repair.md)\n\n## Codex Subagent Capability Discovery\n\n- Execution model: preserve the workflow's existing `subagent-mandatory`, `subagents-first`, `adaptive`, or `subagent-assisted` policy.\n- Dispatch shape: preserve the workflow's existing dispatch shape; use `subagent-blocked` only after the discovery step below fails or is unsafe.\n- Execution surface: prefer `native-subagents` when the current runtime supports it; use `none` only after recording the unavailable or unsafe surface.\n- Native subagent capability discovery: Before recording `subagent-blocked`, confirm the current runtime exposes `spawn_agent`, `wait_agent`, and `close_agent`; if they are not visible, use the active tool discovery mechanism for multi-agent or subagent tools first.\n- Do not record `subagent-blocked` until this capability discovery step is complete and the exact unavailable or unsafe surface is recorded.\n- Native subagent dispatch: Dispatch bounded subagents through `spawn_agent`.\n- Join behavior: Rejoin with `wait_agent`, integrate, then `close_agent`.\n- Preserve this workflow's existing packet, handoff, artifact, and result schema; this section only governs capability discovery before dispatch or blocked-state recording.\n\n## Project Cognition Freshness Closeout\n\n- This workflow is artifact-only unless the user explicitly requested source\u002Fruntime\u002Ftemplate\u002Fconfig\u002Ftest\u002Fgenerated-asset changes; do not call `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe mark-dirty --help`, `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe complete-refresh --help`, or `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe validate-build --format json` just because `sp-specify`, `sp-plan`, or `sp-tasks` wrote planning artifacts.\n- If this planning workflow makes actual source\u002Fruntime\u002Ftemplate\u002Fconfig\u002Ftest\u002Fgenerated-asset changes in the current run, it stops being artifact-only for closeout: run inline project cognition update from the workflow-owned changed paths and affected surfaces.\n- Git-baseline freshness only changes after source\u002Fruntime\u002Ftemplate\u002Fconfig\u002Ftest\u002Fgenerated-asset changes are recorded; planning-only artifact edits do not require `project-cognition complete-refresh`, and manual override\u002Ffallback belongs only to an explicit map-maintenance recovery path.\n- Inline project cognition update uses `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe delta append --help` followed by `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe update --delta-session '\"$DELTA_SESSION_ID\"' --reason workflow-finalize --format json` when a delta session exists, or `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe update --payload-file '\".specify\u002Fproject-cognition\u002Fupdates\u002F\u003Cupdate-id>.json\"' --reason workflow-finalize --format json` when no delta session exists.\n- The payload-file path must include changed_paths, behavior_surfaces, generated_surfaces, state_contracts, verification, known_unknowns, and confidence_notes so the update is equivalent to `sp-map-update`, not just a path stamp; `verification_evidence` and `generated_surface_notes` are accepted compatibility aliases.\n- Use `known_unknowns` only for blockers that make the cognition update unsafe to trust. If unrelated dirty or untracked working-tree paths were excluded by explicit workflow-owned paths, record that as `confidence_notes` or `boundary.initial_dirty_paths`, not as blocking `known_unknowns`.\n- clean closeout keys on `result_state`, not `update_id`, `last_update_id`, or freshness alone. Treat `ready` and `no_op` as clean, `partial_refresh` as recorded but not fully clean, `needs_rebuild` as a map-scan\u002Fmap-build route, `blocked` as blocked, and `recorded` as legacy recorded-only output that is never clean completion.\n- Use `C:\\Users\\11034\\.specify\\bin\\project-cognition.exe mark-dirty --reason '\"\u003Creason>\"' --format json` only when inline update cannot complete.\n- `sp-map-update` is for manual\u002Fexternal maintenance and follow-up repair, not routine cleanup for changes this workflow just made; run `\u002Fsp-map-scan` followed by `\u002Fsp-map-build` only for brownfield first\u002Fmissing\u002Funusable baseline, schema failure, schema v1 or old broad-schema rebuild-required readiness, zero active-generation `path_index` rows outside `greenfield_empty`, missing or invalid `alias_index`, `explicit_rebuild_requested`, or `baseline_identity_invalid`.\n\n## Codex Adaptive Dispatch\n\nWhen running `sp-tasks` in Codex, apply the adaptive dispatch decision recorded by `choose_subagent_dispatch`.\n- Light mode records `dispatch_shape: leader-inline` and `execution_surface: leader-inline`; do not spawn task-generation lanes for light work.\n- Standard mode uses `spawn_agent` for bounded lanes when `dispatch_shape` is `one-subagent` or `parallel-subagents`.\n- Standard native-unavailable degradation records `execution_surface: leader-inline` and `capability_degraded: true` only when no high-risk trigger is present.\n- Heavy or safety-critical blocked work records `dispatch_shape: subagent-blocked` and `execution_surface: none` with `blocked_reason`.\n- Launch all independent lanes in the current `parallel-subagents` wave before waiting.\n- Suggested bounded lanes include story and phase decomposition, dependency graph analysis, and write-set or parallel-safety analysis.\n- Use `wait_agent` only at the documented join points before writing `tasks.md` and before emitting canonical parallel batches and join points.\n- Use `close_agent` after integrating finished subagent results.\n",{"name":5,"metadata":24,"description":7,"compatibility":27},{"author":25,"source":26},"github-spec-kit","templates\u002Fcommands\u002Ftasks.md","Requires spec-kit project structure with .specify\u002F directory","main","021f5cbe02157229460a577e9a585f2da6d78cb0",".codex\u002Fskills\u002Fsp-tasks","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck","https:\u002F\u002Fgithub.com\u002Fchenziyang110","2026-08-07 18:10:54",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add chenziyang110\u002Flaunchdeck --skill sp-tasks",{"tool":40,"command":41},"bunx","bunx skills add chenziyang110\u002Flaunchdeck --skill sp-tasks",{"tool":43,"command":44},"pnpm","pnpm dlx skills add chenziyang110\u002Flaunchdeck --skill sp-tasks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002FSKILL.md",true,[48,54,58,62,66,70,74,78],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fdependencies-and-parallel-safety.md","REFERENCE","参考文档",6919,"https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002Freferences\u002Fdependencies-and-parallel-safety.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002FINDEX.md",1609,"https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002Freferences\u002FINDEX.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fmust-preserve-ledger.md",5601,"https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002Freferences\u002Fmust-preserve-ledger.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fplan-intake.md",1727,"https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002Freferences\u002Fplan-intake.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Freview-and-repair.md",2650,"https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002Freferences\u002Freview-and-repair.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fsemantic-work-contract.md",32453,"https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002Freferences\u002Fsemantic-work-contract.md",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Ftask-generation-sequence.md",3929,"https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002Freferences\u002Ftask-generation-sequence.md",{"path":79,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Ftask-packet-schema.md",2930,"https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fsp-tasks\u002Freferences\u002Ftask-packet-schema.md",[83,90,96,102,109,118],{"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},"01M7875F3HQ1GF5F6BR36KY3JE","launchdeck-agent","Codex host adapter contract fixture for Launchdeck.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fagent-hosts\u002Fcodex\u002Fskill\u002FSKILL.md",[],[],{"skillNo":91,"name":85,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7875DV2DQR33K1NFJHKAMZP","Claude host adapter contract fixture for Launchdeck.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fagent-hosts\u002Fclaude\u002Fskill\u002FSKILL.md",[],[],{"skillNo":97,"name":85,"nameZh":6,"description":98,"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},"01M78759JQ7A6FQ8KDQTNYS3X9","Use this skill aggressively for local project lifecycle operations even when the user does not mention Launchdeck: start this project, run the dev server, dev, build, test, restart service, stop service, show logs, inspect ports, port is occupied, clean cache; and when the user explicitly asks to configure this local project for Launchdeck or create or generate a project-adapted `.launchdeck.yml`, including 为这个项目生成 Launchdeck 配置. Do not use for ordinary code edits, docs-only work, general explanations, API design discussion, or production deployment unless the user also asks to operate or configure a local project or service.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002Fagent\u002Finstaller-payload\u002Fskill\u002Flaunchdeck-agent\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},"01M78753ZJQ7G2CZT1W1G8WRJV","zig-testing","Use ONLY when user explicitly requests Zig test code, built-in test runner configuration,\ntest failure diagnosis, or coverage for Zig projects.\n\nTriggers: \"write test zig\", \"zig test\", \"testing.allocator\", \"zig coverage\",\n\"comptime test\", \"zig expectError\", \"zig snapshot test\", \"zig fuzz\".\n\nDo NOT activate for: general Zig coding without test context, build.zig configuration\nfor non-test targets, Zig compiler errors, or Zig build system setup.","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fzig-testing\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":113,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M78750JXY4Z5D5W1EX3PQ31Z","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fwebapp-testing\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},"01M7874X2T83EQQFRCEY5SJJVC","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fchenziyang110\u002Flaunchdeck\u002Fblob\u002Fmain\u002F.specify\u002Ftemplates\u002Fpassive-skills\u002Fverification-before-completion\u002FSKILL.md",[],[]]