[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DK3WPZ81MP0WDNPZYQX7DP":3,"skill-same:01M7DK3WPZ81MP0WDNPZYQX7DP":51},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M7DK3WPZ81MP0WDNPZYQX7DP","dh-execute-plan-task",null,"Execute a single sub-task from plan.md: select the active one (In Progress phase first), resolve its `Delegated to agent`, implement (TDD), validate via dh-execute-cli, update status; project-type aware. Use for the next sub-task or continuing work — not orchestration.","andrescevp\u002Fdevelopment-harness","andrescevp","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10025841?v=4","01M7DK1Q07H5GT5R4JSGMWV1DE","Andres Cevallos","01M7DK1Q18W9DHVMV4HZ4BQAY3",8,"MIT","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-execute-plan-task\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dh-execute-plan-task\ndescription: >\n  Execute a single sub-task from plan.md: select the active one (In Progress phase first), resolve its `Delegated to agent`, implement (TDD), validate via dh-execute-cli, update status; project-type aware. Use for the next sub-task or continuing work — not orchestration.\nlicense: MIT\ncompatibility: opencode, copilot, antigravity\nallowed-tools: read, write, edit, bash\nmetadata:\n  audience: developers\n  workflow: development\n---\n\nExecute one self-contained sub-task from `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Fplan.md`.\n\n## Core Rules\n\n- Read the plan with the `dh_plan_read` tool (`{ slug }` → structured JSON: meta, phases[].title\u002Fstatus, subTasks[].phase\u002Ftitle\u002Fstatus) to find the active sub-task. Fallback when the tool is unavailable: read `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Fplan.md` manually, following the phased template markers (`## Phases` → `### Phase N: \u003Ctitle>` → `#### Sub-Task N.M: \u003Ctitle>` with `- **Status:**` bullets). If the plan does not exist, stop and report that no plan was found — suggest running the `dh-planning` skill first. These tools are exposed by the project-scope `dh` MCP server; under Code Mode they are called as `tools.dh.\u003Ctool>`, and `dh_\u003Ctool>` is the tool's normalized name (permission actions match `dh_*`).\n- Treat the sub-task entry in plan.md as the full implementation brief.\n- **Resolve the sub-task's delegated agent:** read `delegatedTo` from `dh_plan_read` for the active sub-task. It must name an agent recorded in `## Agent Selection`. If the field is missing, empty, or points to an unknown\u002Funavailable agent, STOP and report the gap — never execute the sub-task or substitute an agent silently.\n- **One responsible agent per sub-task:** the `Delegated to agent` value is the single executor for that sub-task. Implementation work normally names the selected implementation agent; documentation or test-only sub-tasks may name the documentation or testing\u002FQA agent. There is no complexity- or type-based builder split.\n- **Review stays separate:** resolve the review agent from `## Agent Selection`; the delegated agent does not review its own work.\n- **Detect project type** before the post-steps: it determines whether `dh-domain-check`, `dh-simplify`, and `dh-create-documentation` run (software projects only) — it does NOT change who implements.\n- For **software projects**: run `dh-domain-check` before complex implementation, `dh-simplify` after validation, and `dh-create-documentation` for new modules\u002FAPIs.\n- For **non-software projects**: skip the `dh-simplify`, `dh-domain-check`, and `dh-create-documentation` steps entirely; implementation still goes to the sub-task's delegated agent.\n- Use the `dh-execute-cli` skill for tests, linters, and builds.\n- Delegate review to the plan's selected review agent for code quality and acceptance criteria checks.\n- Do not modify files outside the sub-task scope.\n- Update the sub-task status only after review passes — via `dh_plan_update_status` (`target: \"subtask\"`, status `Completed`); fallback: manual plan.md edit per the marker rules.\n- If the sub-task has dependencies on earlier sub-tasks, verify they are Completed before starting.\n\n## Project Type Detection\n\nCheck the project root for software marker files to determine project type. This must be done before any agent delegation.\n\n**Software project markers** (any of these files present in project root):\n`package.json`, `pyproject.toml`, `Cargo.toml`, `composer.json`, `go.mod`, `CMakeLists.txt`, `setup.py`, `setup.cfg`, `Gemfile`, `project.clj`, `deps.edn`, `mix.exs`, `pubspec.yaml`, `Build.scala`, `build.gradle`, `*.csproj`, `*.sln`\n\n**Detection logic:**\n1. Run `ls \u003Cproject-root>\u002F` and check for any of the marker files above.\n2. If a marker file is found → **software project** (run `dh-domain-check` before complex implementation, `dh-simplify` after validation, `dh-create-documentation` for new modules\u002FAPIs).\n3. If no marker files found → **non-software project** (skip `dh-domain-check`, `dh-simplify`, and `dh-create-documentation`).\n4. If uncertain (e.g., a `Makefile` with no other code), check for source code directories (`src\u002F`, `lib\u002F`, `app\u002F`) as secondary indicators.\n\nDelegation is IDENTICAL for both types: **every sub-task is executed by its\n`Delegated to agent`** (normally the selected implementation agent).\n\n> **Why this matters:** Non-software projects (docs repos, config repos, design assets) don't benefit from architecture\u002Fengineering agents or code-level simplification. Using the wrong agent type wastes context and produces irrelevant findings.\n\n## Workflow\n\n### Step 0: Resolve the delegated agent\n\nRead `## Agent Selection` in `plan.md` and confirm the sub-task's `Delegated to agent` names one of its agents. If the section or the field is absent, empty, or stale, STOP and ask the planner\u002Fuser to fix the plan — do not run the selection protocol as a substitute for the missing field. If the named agent is unavailable and no bundled capability covers the role, stop and report the gap.\n\n### Step 1: Select the active sub-task\n\nRead the plan with the `dh_plan_read` tool (`{ slug }`) and find exactly one sub-task using this phase-aware order. Fallback when the tool is unavailable: read `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Fplan.md` manually per the marker rules:\n\n1. Pick the FIRST phase marked `In Progress`; within it, pick its FIRST sub-task marked `In Progress` or `Pending`. If that sub-task is already `In Progress` (set by the orchestrator), skip marking and proceed directly to implementation.\n2. If no phase is `In Progress`, take the first sub-task of the first `Pending` phase and mark it `In Progress` via `dh_plan_update_status` (`target: \"subtask\"`, status `In Progress`) — the phase follows the lifecycle (it becomes `In Progress` when its first sub-task starts). Fallback: manual plan.md edit per the marker rules.\n3. If multiple phases are `In Progress`, or multiple sub-tasks within the active phase are `In Progress`, stop and ask which to continue.\n4. If no `In Progress` or `Pending` sub-tasks remain, report that the plan has no remaining work.\n\n### Step 2: Implement the sub-task\n\nFollow the sub-task's instructions, in-scope list, and implementation suggestions. **The sub-task's `Delegated to agent` is the single responsible executor**:\n\n- Delegate the FULL sub-task brief to that agent — for complex work (multi-file, architectural decisions, new modules), run the `dh-domain-check` skill first and include its findings in the delegation. When the project graph is indexed, use `dh-code-query` on the affected symbols (`definition`, `callers`, `importers`, `tests-reaching`) to include impact and test evidence in the brief.\n- Route implementation work through the `dh-coding` skill inside that agent's pass (test-first TDD; `CODE_RULES.md` at project root when present).\n- Route documentation sub-tasks through `dh-create-documentation` and test-only work through the project's testing guidance, still under the named agent.\n- **TDD**: the failing test is written first, then the minimal change to make it pass — performed inside the delegated agent's pass.\n- Do NOT implement sub-task work directly and do NOT seek another builder: the `Delegated to agent` is the only executor for this sub-task.\n\n**General rules:**\n- Stay within the sub-task's in-scope boundaries. Do not widen scope.\n- Never mark a phase `Completed` yourself while any sub-task in it is still open (phase coordination belongs to the orchestrator or the gated tool).\n\n### Step 3: Run validation\n\nUse the `dh-execute-cli` skill to run the smallest relevant validation for the changed code:\n\n- Run tests related to the changed files.\n- Run linters and static analysis.\n- Fix any failures before proceeding. If validation fails 3 consecutive times, stop and report the failure with full error output — do not proceed to review.\n\nWhen stopping on a hard blocker, recommend `dh-pause-plan` so the phase\u002Fsub-task, git state, decisions, and next steps are preserved in `handoff.md` before the session ends.\n\n### Step 3a: Simplify code (software projects only)\n\n**For software projects only** — after validation passes and before requesting review:\n\nRun the `dh-simplify` skill to review all changed code for reuse opportunities, quality issues, and efficiency improvements. This ensures code is clean before it reaches review.\n\n1. Invoke the `dh-simplify` skill with the full diff context from the sub-task implementation.\n2. Wait for all three simplify agents (code reuse, quality, efficiency) to report findings.\n3. Fix all P0\u002FP1 issues found by simplify. For P2\u002FP3 findings, use judgment — fix if meaningful, defer if low impact.\n4. If fixes were made, re-run validation via the `dh-execute-cli` skill to ensure nothing broke.\n5. **For non-software projects:** skip this entire step — the `dh-simplify` skill is code-focused and would produce irrelevant findings.\n\n### Step 3b: Generate documentation (software projects only)\n\n**For software projects only** — after `dh-simplify` and before requesting review:\n\nRun the `dh-create-documentation` skill to generate or update API references, module docs, architecture overviews, or any documentation relevant to the new or changed code.\n\n1. If the sub-task introduces new modules, APIs, public interfaces, or configuration schemas, invoke `dh-create-documentation` to produce the corresponding docs.\n2. If the sub-task modifies existing documented interfaces, update the related documentation rather than creating from scratch.\n3. If the sub-task has no public-facing changes (e.g., internal refactors, bug fixes), skip this step.\n4. **For non-software projects:** skip this entire step — documentation needs for config\u002Fdocs repos are handled differently.\n\n### Step 4: Request review\n\n(Orchestration note) When invoked from `dh-execute-plan` orchestrator, skip this step — the orchestrator runs the `dh-review` skill after this sub-task completes. When invoked standalone, ask the plan's selected review agent to review the changes against the active sub-task's acceptance criteria, scope boundaries, and done-when conditions. The reviewer writes findings to `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Ftasks\u002Freview.md`.\n\n### Step 5: Address review feedback\n\nRead the review and address findings:\n\n- For P0\u002FP1 (blocking\u002Fhigh): fix immediately, then proceed to Step 5a.\n- For P2\u002FP3: use judgment — fix if meaningful, defer if low impact.\n- After fixes, re-run the relevant validation with the `dh-execute-cli` skill.\n- Update `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Ftasks\u002Freview.md` marking each finding as `Addressed` or `Not Addressed` with a brief rationale.\n- If re-validation fails 2 additional times after initial fixes, stop and report the failure with full error output — do not proceed; recommend `dh-pause-plan` to preserve state in `handoff.md` (resume with `dh-resume-plan`).\n\n### Step 5a: Confirm review resolution\n\n- If the reviewer approved (no outstanding P0\u002FP1 findings), proceed to Step 6.\n- If P0\u002FP1 findings remain unaddressed, fix them and request a re-review from the selected review agent (loop back to Step 4).\n- If P0\u002FP1 findings cannot be resolved in-session, recommend `dh-pause-plan` before stopping; do not mark the sub-task or phase `Completed`.\n- If only P2\u002FP3 findings remain and you have addressed or explicitly deferred them with rationale, proceed to Step 6.\n\n### Step 6: Update plan status\n\n1. (Orchestration note) When invoked from `dh-execute-plan` orchestrator, skip both status updates — the orchestrator marks Complete after its external review passes and handles sequencing. When invoked standalone, mark the current sub-task as `Completed` via `dh_plan_update_status` (`target: \"subtask\"`, status `Completed`); fallback: manual plan.md edit per the marker rules.\n2. **Phase coordination:** after the sub-task is `Completed`, check whether ALL sub-tasks of its phase are now `Completed`. If so, tell the orchestrator (`dh-execute-plan`) that the phase is ready to close; when running standalone, close it via `dh_plan_update_status` (`target: \"phase\"`, status `Completed`). Never mark a phase `Completed` yourself while any sub-task in it is still open.\n3. When standalone: if a next sub-task exists and is `Pending`, mark it as `In Progress`.\n4. When standalone: update `.\u002Fdocs\u002Fplans\u002Findex.md` with the latest status if this was the final sub-task.\n\n## Execution Delegation Guide\n\n**Per-sub-task executor policy:** every sub-task is implemented by its\n`Delegated to agent`. Implementation sub-tasks normally name the plan's\nselected implementation agent; documentation, test-only, and similar\nsub-tasks name the matching selected role. There is no builder split beyond\nthat explicit field.\n\n| Work | Delegate to | Post-steps |\n|---|---|---|\n| Software (complex, architectural) | sub-task's `Delegated to agent` | `dh-domain-check` first, then `dh-simplify` + `dh-create-documentation` |\n| Software (other) | sub-task's `Delegated to agent` | `dh-simplify` after validation |\n| Non-software | sub-task's `Delegated to agent` | none (skip `dh-simplify`\u002F`dh-domain-check`\u002F`dh-create-documentation`) |\n\nValidation always runs through the `dh-execute-cli` skill; review through the\nplan's selected review agent.\n\n## Loop Integration (bundled)\n\nThis copy is bundled in the plugin; the harness runtime contract (full loop\n1–5) lives in repo-root AGENTS.md and in `dh-execute-plan`'s Loop Integration\nsection. Executing a sub-task sits inside loop step 2:\n\n- 2.1 delegate code implementation through the `dh-coding` skill (software\n  work); run `dh-domain-check` before complex implementation.\n- 2.2 run `dh-simplify` after validation (software projects only).\n- 2.3 `dh-review` + `dh-code-review` verify the sub-task before it is marked `Completed`.\n- 2.4 **Hard blockers halt automation.** Repeated validation failures (3\n  consecutive strikes), unresolved P0\u002FP1 review findings, or missing\n  preconditions that cannot be worked around → STOP: report the blocker and\n  ask the user for guidance. Never silently continue, never skip the blocked\n  step, and never mark sub-tasks `Completed` around a blocker. A blocked\n  sub-task also blocks its phase — do not mark the phase `Completed` around a\n  blocker. Before stopping for a hard blocker or ending the session, run\n  `dh-pause-plan` to preserve the phase\u002Fsub-task, git state, decisions,\n  blockers, and next steps in `handoff.md`; resume later with `dh-resume-plan`.\n\n## References\n\n- Fast variant: `dh-execute-plan-task-fast` executes one sub-task from `plan_fast.md` with dual-plan status writes, per-task skipped-check rows, and no per-task gates.\n- [`..\u002Fdh-planning\u002Freferences\u002Fagent-selection.md`](..\u002Fdh-planning\u002Freferences\u002Fagent-selection.md): capability→agent resolution (discovery, ranking, fallback, re-validation).\n- `dh-execute-cli` skill: runs commands, tests, linters, and builds with logged, compact output.\n- `dh-domain-check` skill: validates architecture against DDD bounded contexts and SOLID principles before complex implementation (software projects only).\n- `dh-simplify` skill: reviews changed code for reuse, quality, and efficiency after validation (software projects only).\n- `dh-create-documentation` skill: generates docs for new modules, APIs, and interfaces after simplify (software projects only).\n\n## Doc search\n\n**Documentation management:** delegate create \u002F update \u002F delete \u002F retrieve of generated documents (excluding docs\u002Fplans) to the best available documentation agent (bundled documentation capability as fallback) — the main and only documentation owner (see dh-create-documentation).\n\nSearch generated documentation quickly: `notesmd-cli search-content \"\u003Cterm>\" --vault \"\u003Cproject-name>\"` or `obsidian search query=\"\u003Cterm>\"` (fallback: `rg --glob '*.md' \"\u003Cterm>\" docs\u002F`).\n","Execute one self-contained sub-task from `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Fplan.md`.\n\n## Core Rules\n\n- Read the plan with the `dh_plan_read` tool (`{ slug }` → structured JSON: meta, phases[].title\u002Fstatus, subTasks[].phase\u002Ftitle\u002Fstatus) to find the active sub-task. Fallback when the tool is unavailable: read `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Fplan.md` manually, following the phased template markers (`## Phases` → `### Phase N: \u003Ctitle>` → `#### Sub-Task N.M: \u003Ctitle>` with `- **Status:**` bullets). If the plan does not exist, stop and report that no plan was found — suggest running the `dh-planning` skill first. These tools are exposed by the project-scope `dh` MCP server; under Code Mode they are called as `tools.dh.\u003Ctool>`, and `dh_\u003Ctool>` is the tool's normalized name (permission actions match `dh_*`).\n- Treat the sub-task entry in plan.md as the full implementation brief.\n- **Resolve the sub-task's delegated agent:** read `delegatedTo` from `dh_plan_read` for the active sub-task. It must name an agent recorded in `## Agent Selection`. If the field is missing, empty, or points to an unknown\u002Funavailable agent, STOP and report the gap — never execute the sub-task or substitute an agent silently.\n- **One responsible agent per sub-task:** the `Delegated to agent` value is the single executor for that sub-task. Implementation work normally names the selected implementation agent; documentation or test-only sub-tasks may name the documentation or testing\u002FQA agent. There is no complexity- or type-based builder split.\n- **Review stays separate:** resolve the review agent from `## Agent Selection`; the delegated agent does not review its own work.\n- **Detect project type** before the post-steps: it determines whether `dh-domain-check`, `dh-simplify`, and `dh-create-documentation` run (software projects only) — it does NOT change who implements.\n- For **software projects**: run `dh-domain-check` before complex implementation, `dh-simplify` after validation, and `dh-create-documentation` for new modules\u002FAPIs.\n- For **non-software projects**: skip the `dh-simplify`, `dh-domain-check`, and `dh-create-documentation` steps entirely; implementation still goes to the sub-task's delegated agent.\n- Use the `dh-execute-cli` skill for tests, linters, and builds.\n- Delegate review to the plan's selected review agent for code quality and acceptance criteria checks.\n- Do not modify files outside the sub-task scope.\n- Update the sub-task status only after review passes — via `dh_plan_update_status` (`target: \"subtask\"`, status `Completed`); fallback: manual plan.md edit per the marker rules.\n- If the sub-task has dependencies on earlier sub-tasks, verify they are Completed before starting.\n\n## Project Type Detection\n\nCheck the project root for software marker files to determine project type. This must be done before any agent delegation.\n\n**Software project markers** (any of these files present in project root):\n`package.json`, `pyproject.toml`, `Cargo.toml`, `composer.json`, `go.mod`, `CMakeLists.txt`, `setup.py`, `setup.cfg`, `Gemfile`, `project.clj`, `deps.edn`, `mix.exs`, `pubspec.yaml`, `Build.scala`, `build.gradle`, `*.csproj`, `*.sln`\n\n**Detection logic:**\n1. Run `ls \u003Cproject-root>\u002F` and check for any of the marker files above.\n2. If a marker file is found → **software project** (run `dh-domain-check` before complex implementation, `dh-simplify` after validation, `dh-create-documentation` for new modules\u002FAPIs).\n3. If no marker files found → **non-software project** (skip `dh-domain-check`, `dh-simplify`, and `dh-create-documentation`).\n4. If uncertain (e.g., a `Makefile` with no other code), check for source code directories (`src\u002F`, `lib\u002F`, `app\u002F`) as secondary indicators.\n\nDelegation is IDENTICAL for both types: **every sub-task is executed by its\n`Delegated to agent`** (normally the selected implementation agent).\n\n> **Why this matters:** Non-software projects (docs repos, config repos, design assets) don't benefit from architecture\u002Fengineering agents or code-level simplification. Using the wrong agent type wastes context and produces irrelevant findings.\n\n## Workflow\n\n### Step 0: Resolve the delegated agent\n\nRead `## Agent Selection` in `plan.md` and confirm the sub-task's `Delegated to agent` names one of its agents. If the section or the field is absent, empty, or stale, STOP and ask the planner\u002Fuser to fix the plan — do not run the selection protocol as a substitute for the missing field. If the named agent is unavailable and no bundled capability covers the role, stop and report the gap.\n\n### Step 1: Select the active sub-task\n\nRead the plan with the `dh_plan_read` tool (`{ slug }`) and find exactly one sub-task using this phase-aware order. Fallback when the tool is unavailable: read `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Fplan.md` manually per the marker rules:\n\n1. Pick the FIRST phase marked `In Progress`; within it, pick its FIRST sub-task marked `In Progress` or `Pending`. If that sub-task is already `In Progress` (set by the orchestrator), skip marking and proceed directly to implementation.\n2. If no phase is `In Progress`, take the first sub-task of the first `Pending` phase and mark it `In Progress` via `dh_plan_update_status` (`target: \"subtask\"`, status `In Progress`) — the phase follows the lifecycle (it becomes `In Progress` when its first sub-task starts). Fallback: manual plan.md edit per the marker rules.\n3. If multiple phases are `In Progress`, or multiple sub-tasks within the active phase are `In Progress`, stop and ask which to continue.\n4. If no `In Progress` or `Pending` sub-tasks remain, report that the plan has no remaining work.\n\n### Step 2: Implement the sub-task\n\nFollow the sub-task's instructions, in-scope list, and implementation suggestions. **The sub-task's `Delegated to agent` is the single responsible executor**:\n\n- Delegate the FULL sub-task brief to that agent — for complex work (multi-file, architectural decisions, new modules), run the `dh-domain-check` skill first and include its findings in the delegation. When the project graph is indexed, use `dh-code-query` on the affected symbols (`definition`, `callers`, `importers`, `tests-reaching`) to include impact and test evidence in the brief.\n- Route implementation work through the `dh-coding` skill inside that agent's pass (test-first TDD; `CODE_RULES.md` at project root when present).\n- Route documentation sub-tasks through `dh-create-documentation` and test-only work through the project's testing guidance, still under the named agent.\n- **TDD**: the failing test is written first, then the minimal change to make it pass — performed inside the delegated agent's pass.\n- Do NOT implement sub-task work directly and do NOT seek another builder: the `Delegated to agent` is the only executor for this sub-task.\n\n**General rules:**\n- Stay within the sub-task's in-scope boundaries. Do not widen scope.\n- Never mark a phase `Completed` yourself while any sub-task in it is still open (phase coordination belongs to the orchestrator or the gated tool).\n\n### Step 3: Run validation\n\nUse the `dh-execute-cli` skill to run the smallest relevant validation for the changed code:\n\n- Run tests related to the changed files.\n- Run linters and static analysis.\n- Fix any failures before proceeding. If validation fails 3 consecutive times, stop and report the failure with full error output — do not proceed to review.\n\nWhen stopping on a hard blocker, recommend `dh-pause-plan` so the phase\u002Fsub-task, git state, decisions, and next steps are preserved in `handoff.md` before the session ends.\n\n### Step 3a: Simplify code (software projects only)\n\n**For software projects only** — after validation passes and before requesting review:\n\nRun the `dh-simplify` skill to review all changed code for reuse opportunities, quality issues, and efficiency improvements. This ensures code is clean before it reaches review.\n\n1. Invoke the `dh-simplify` skill with the full diff context from the sub-task implementation.\n2. Wait for all three simplify agents (code reuse, quality, efficiency) to report findings.\n3. Fix all P0\u002FP1 issues found by simplify. For P2\u002FP3 findings, use judgment — fix if meaningful, defer if low impact.\n4. If fixes were made, re-run validation via the `dh-execute-cli` skill to ensure nothing broke.\n5. **For non-software projects:** skip this entire step — the `dh-simplify` skill is code-focused and would produce irrelevant findings.\n\n### Step 3b: Generate documentation (software projects only)\n\n**For software projects only** — after `dh-simplify` and before requesting review:\n\nRun the `dh-create-documentation` skill to generate or update API references, module docs, architecture overviews, or any documentation relevant to the new or changed code.\n\n1. If the sub-task introduces new modules, APIs, public interfaces, or configuration schemas, invoke `dh-create-documentation` to produce the corresponding docs.\n2. If the sub-task modifies existing documented interfaces, update the related documentation rather than creating from scratch.\n3. If the sub-task has no public-facing changes (e.g., internal refactors, bug fixes), skip this step.\n4. **For non-software projects:** skip this entire step — documentation needs for config\u002Fdocs repos are handled differently.\n\n### Step 4: Request review\n\n(Orchestration note) When invoked from `dh-execute-plan` orchestrator, skip this step — the orchestrator runs the `dh-review` skill after this sub-task completes. When invoked standalone, ask the plan's selected review agent to review the changes against the active sub-task's acceptance criteria, scope boundaries, and done-when conditions. The reviewer writes findings to `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Ftasks\u002Freview.md`.\n\n### Step 5: Address review feedback\n\nRead the review and address findings:\n\n- For P0\u002FP1 (blocking\u002Fhigh): fix immediately, then proceed to Step 5a.\n- For P2\u002FP3: use judgment — fix if meaningful, defer if low impact.\n- After fixes, re-run the relevant validation with the `dh-execute-cli` skill.\n- Update `.\u002Fdocs\u002Fplans\u002F\u003Cplan-slug>\u002Ftasks\u002Freview.md` marking each finding as `Addressed` or `Not Addressed` with a brief rationale.\n- If re-validation fails 2 additional times after initial fixes, stop and report the failure with full error output — do not proceed; recommend `dh-pause-plan` to preserve state in `handoff.md` (resume with `dh-resume-plan`).\n\n### Step 5a: Confirm review resolution\n\n- If the reviewer approved (no outstanding P0\u002FP1 findings), proceed to Step 6.\n- If P0\u002FP1 findings remain unaddressed, fix them and request a re-review from the selected review agent (loop back to Step 4).\n- If P0\u002FP1 findings cannot be resolved in-session, recommend `dh-pause-plan` before stopping; do not mark the sub-task or phase `Completed`.\n- If only P2\u002FP3 findings remain and you have addressed or explicitly deferred them with rationale, proceed to Step 6.\n\n### Step 6: Update plan status\n\n1. (Orchestration note) When invoked from `dh-execute-plan` orchestrator, skip both status updates — the orchestrator marks Complete after its external review passes and handles sequencing. When invoked standalone, mark the current sub-task as `Completed` via `dh_plan_update_status` (`target: \"subtask\"`, status `Completed`); fallback: manual plan.md edit per the marker rules.\n2. **Phase coordination:** after the sub-task is `Completed`, check whether ALL sub-tasks of its phase are now `Completed`. If so, tell the orchestrator (`dh-execute-plan`) that the phase is ready to close; when running standalone, close it via `dh_plan_update_status` (`target: \"phase\"`, status `Completed`). Never mark a phase `Completed` yourself while any sub-task in it is still open.\n3. When standalone: if a next sub-task exists and is `Pending`, mark it as `In Progress`.\n4. When standalone: update `.\u002Fdocs\u002Fplans\u002Findex.md` with the latest status if this was the final sub-task.\n\n## Execution Delegation Guide\n\n**Per-sub-task executor policy:** every sub-task is implemented by its\n`Delegated to agent`. Implementation sub-tasks normally name the plan's\nselected implementation agent; documentation, test-only, and similar\nsub-tasks name the matching selected role. There is no builder split beyond\nthat explicit field.\n\n| Work | Delegate to | Post-steps |\n|---|---|---|\n| Software (complex, architectural) | sub-task's `Delegated to agent` | `dh-domain-check` first, then `dh-simplify` + `dh-create-documentation` |\n| Software (other) | sub-task's `Delegated to agent` | `dh-simplify` after validation |\n| Non-software | sub-task's `Delegated to agent` | none (skip `dh-simplify`\u002F`dh-domain-check`\u002F`dh-create-documentation`) |\n\nValidation always runs through the `dh-execute-cli` skill; review through the\nplan's selected review agent.\n\n## Loop Integration (bundled)\n\nThis copy is bundled in the plugin; the harness runtime contract (full loop\n1–5) lives in repo-root AGENTS.md and in `dh-execute-plan`'s Loop Integration\nsection. Executing a sub-task sits inside loop step 2:\n\n- 2.1 delegate code implementation through the `dh-coding` skill (software\n  work); run `dh-domain-check` before complex implementation.\n- 2.2 run `dh-simplify` after validation (software projects only).\n- 2.3 `dh-review` + `dh-code-review` verify the sub-task before it is marked `Completed`.\n- 2.4 **Hard blockers halt automation.** Repeated validation failures (3\n  consecutive strikes), unresolved P0\u002FP1 review findings, or missing\n  preconditions that cannot be worked around → STOP: report the blocker and\n  ask the user for guidance. Never silently continue, never skip the blocked\n  step, and never mark sub-tasks `Completed` around a blocker. A blocked\n  sub-task also blocks its phase — do not mark the phase `Completed` around a\n  blocker. Before stopping for a hard blocker or ending the session, run\n  `dh-pause-plan` to preserve the phase\u002Fsub-task, git state, decisions,\n  blockers, and next steps in `handoff.md`; resume later with `dh-resume-plan`.\n\n## References\n\n- Fast variant: `dh-execute-plan-task-fast` executes one sub-task from `plan_fast.md` with dual-plan status writes, per-task skipped-check rows, and no per-task gates.\n- [`..\u002Fdh-planning\u002Freferences\u002Fagent-selection.md`](..\u002Fdh-planning\u002Freferences\u002Fagent-selection.md): capability→agent resolution (discovery, ranking, fallback, re-validation).\n- `dh-execute-cli` skill: runs commands, tests, linters, and builds with logged, compact output.\n- `dh-domain-check` skill: validates architecture against DDD bounded contexts and SOLID principles before complex implementation (software projects only).\n- `dh-simplify` skill: reviews changed code for reuse, quality, and efficiency after validation (software projects only).\n- `dh-create-documentation` skill: generates docs for new modules, APIs, and interfaces after simplify (software projects only).\n\n## Doc search\n\n**Documentation management:** delegate create \u002F update \u002F delete \u002F retrieve of generated documents (excluding docs\u002Fplans) to the best available documentation agent (bundled documentation capability as fallback) — the main and only documentation owner (see dh-create-documentation).\n\nSearch generated documentation quickly: `notesmd-cli search-content \"\u003Cterm>\" --vault \"\u003Cproject-name>\"` or `obsidian search query=\"\u003Cterm>\"` (fallback: `rg --glob '*.md' \"\u003Cterm>\" docs\u002F`).\n",{"name":5,"license":15,"metadata":24,"description":27,"allowed-tools":28,"compatibility":29},{"audience":25,"workflow":26},"developers","development","Execute a single sub-task from plan.md: select the active one (In Progress phase first), resolve its `Delegated to agent`, implement (TDD), validate via dh-execute-cli, update status; project-type aware. Use for the next sub-task or continuing work — not orchestration.\n","read, write, edit, bash","opencode, copilot, antigravity","main","f7ddc0c3b3190e379bda1059d53f861bd4e1f30d","skills\u002Fdh-execute-plan-task",1,"https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness","https:\u002F\u002Fgithub.com\u002Fandrescevp","2026-11-10 07:43:44",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add andrescevp\u002Fdevelopment-harness --skill dh-execute-plan-task",{"tool":43,"command":44},"bunx","bunx skills add andrescevp\u002Fdevelopment-harness --skill dh-execute-plan-task",{"tool":46,"command":47},"pnpm","pnpm dlx skills add andrescevp\u002Fdevelopment-harness --skill dh-execute-plan-task","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-execute-plan-task\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7DK6HMNFES75RNB4G6TE55T","dh-simplify","Review changed code for reuse, quality, and efficiency (three parallel reviews), then fix findings directly. Use after making changes or when asked to clean up, refactor, simplify, or improve this code.","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-simplify\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7DK6BFEQ9PVZTHKV0DR66BR","dh-setup","Audit system software, configure user MCPs\u002Fplugins, scaffold project QA (hooks + per-stack tools), bootstrap docs\u002Farchitecture with the selected architecture agent, and write harness directives into AGENTS.md. Use to check requirements or setup the environment.","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-setup\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7DK62N6CDZ2TH890AX2Z7P9","dh-semver","Apply strict Semantic Versioning — analyze commits since the last tag to determine the bump type (major\u002Fminor\u002Fpatch from conventional commit prefixes), generate an automated changelog grouped by breaking changes, features, fixes, and chores, and create a git tag locally without pushing until confirmed, handling both conventional commits and manual version decisions. Use when preparing a release, invoked by dh-execute-plan after plan completion and dh-final-review for release readiness, or when the user asks \"what version is next?\", \"bump version\", \"generate changelog\", \"tag release\", or \"what changed since last release?\".","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-semver\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7DK5SM44RAH10HM59JC6ZPZ","dh-review","Verify a plan sub-task against acceptance criteria, scope, done-when; review diff, validation, regression risk; structured verdict to tasks\u002Freview.md. Plan Alignment Mode (fast execution) is a separate mode: no sub-task selection, no diff review, no code review — it compares plan.md with plan_fast.md and writes tasks\u002Freview-fast.md (pre-execution) or tasks\u002Freview-fast-final.md (plan-end). Use after implementation, to review\u002Fverify the sub-task, or to check fast-plan alignment.","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-review\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7DK5KKZ05K0FR0ARFHA58KG","dh-resume-plan","Resume a paused phased plan from docs\u002Fplans\u002F\u003Cslug>\u002Fhandoff.md: validate the contract, detect drift, rehydrate context, mark the handoff resumed, and continue via dh-execute-plan resume mode. Use when the user says \"resume the plan\", \"continue where we stopped\", \"pick up the plan\", or \"resume after a pause\".","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-resume-plan\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7DK5E10T47JWQAJSAXJHHGD","dh-preflight","Run tests, linters, static analysis as a release gate: auto-detect tooling, check dirty state, pass\u002Ffail verdict with actionable failures (no auto-fixes). Use to run preflight, pre-release check, or validate before release.","https:\u002F\u002Fgithub.com\u002Fandrescevp\u002Fdevelopment-harness\u002Fblob\u002Fmain\u002Fskills\u002Fdh-preflight\u002FSKILL.md",[],[]]