[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DTH7JFWZMG64SSXGGNDEC":3,"skill-same:01M79DTH7JFWZMG64SSXGGNDEC":57},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M79DTH7JFWZMG64SSXGGNDEC","harness-plan-brief",null,"Generate a Plan Brief HTML for non-engineer vibecoders before implementation starts. Searches harness-mem (project-only) for relevant past decisions, patterns, and Plans archive entries, then renders a single-file HTML artifact summarizing understanding, options, risks, acceptance criteria, and confidence. Use when the user requests a planning preview, a non-engineer-friendly summary before approval, or says: plan brief, planning preview. Do NOT load for: actual implementation, code review, release work.","foden303\u002Fharness","foden303","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F77870743?v=4","01M79DK06BJVG7HTKT05FM221X","Foden Ngo","01M79DK071J1HMYV20FJSMG71X",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fharness-plan-brief\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: harness-plan-brief\ndescription: \"Generate a Plan Brief HTML for non-engineer vibecoders before implementation starts. Searches harness-mem (project-only) for relevant past decisions, patterns, and Plans archive entries, then renders a single-file HTML artifact summarizing understanding, options, risks, acceptance criteria, and confidence. Use when the user requests a planning preview, a non-engineer-friendly summary before approval, or says: plan brief, planning preview. Do NOT load for: actual implementation, code review, release work.\"\ndescription-en: \"Generate a Plan Brief HTML for non-engineer vibecoders before implementation starts. Searches harness-mem (project-only) for relevant past decisions, patterns, and Plans archive entries, then renders a single-file HTML artifact summarizing understanding, options, risks, acceptance criteria, and confidence. Use when the user requests a planning preview, a non-engineer-friendly summary before approval, or says: plan brief, planning preview. Do NOT load for: actual implementation, code review, release work.\"\nallowed-tools: [\"Read\", \"Write\", \"Edit\", \"Bash\"]\nargument-hint: \"[task-description]\"\nuser-invocable: true\n---\n\n# harness-plan-brief\n\nA skill that presents the plan Claude is about to start, on **a single HTML page**, for non-engineer requesters and producer roles.\nUse it at the requester's cognitive-load peak (1): understanding the plan.\n\n## Quick Reference\n\n- \"**create a Plan Brief**\" → this skill\n- \"**give me a rough overview before implementation**\" → this skill\n- \"**show the plan for a non-engineer**\" → this skill\n\n## Responsibility boundaries\n\n| Scope | This skill's responsibility |\n|-------|-----------------------------|\n| Search | **Current project only** (always specify `project: \u003Ccurrent>`, `strict_project: true`) |\n| Cross-project | **Do not do it** (opened up as opt-in via the `--cross-project-group \u003Cname>` flag from Phase 65.3 onward) |\n| Writes | Do not do it (memory writes after Plan Brief approval are the responsibility of `plan-brief-record-decision.sh`) |\n| plan_readiness computation | Delegated to `scripts\u002Fplan-brief-compile.sh`. The compat field name `confidence` is kept, but its meaning is limited to DoD clarity + dependency resolution rate |\n\n## Input\n\nPass the user's request in the `[task-description]` argument.\nWhen there is no argument, take it interactively.\n\n## Output\n\n| Output | Path | Format |\n|--------|------|--------|\n| Plan Brief HTML | `.claude\u002Fstate\u002Fviews\u002Fplan-brief-\u003Ctimestamp>.html` | Standalone HTML (no server, no JS framework) |\n| Plan Brief context JSON | `.claude\u002Fstate\u002Fviews\u002Fplan-brief-\u003Ctimestamp>.context.json` | `plan-brief-context.v1` schema |\n\n## Schema: `plan-brief-context.v1`\n\n```json\n{\n  \"schema\": \"plan-brief-context.v1\",\n  \"user_request\": \"string (the user's original request)\",\n  \"my_understanding\": \"string (Claude's understanding in 1-3 paragraphs)\",\n  \"options\": [\n    { \"name\": \"string\", \"summary\": \"string\", \"pros\": [\"string\"], \"cons\": [\"string\"] }\n  ],\n  \"risks\": [\n    { \"kind\": \"string\", \"severity\": \"info|warn|critical\", \"description\": \"string\", \"mitigation\": \"string\" }\n  ],\n  \"acceptance_criteria\": [\n    { \"id\": \"string\", \"description\": \"string\", \"verifiable_by\": \"string\" }\n  ],\n  \"tdd_required\": \"yes|no|skip:\u003Creason>\",\n  \"confidence\": 0,\n  \"confidence_evidence\": [\"string (plan_readiness evidence: DoD clarity + dependency resolution only)\"],\n  \"related_decisions\": [\n    { \"id\": \"string\", \"title\": \"string\", \"relevance\": \"string\" }\n  ],\n  \"similar_past_plans\": [\n    { \"archive_path\": \"string\", \"phase\": \"string\", \"outcome\": \"cc:done|cc:WIP|cc:TODO|skipped\", \"relevance\": \"string\" }\n  ],\n  \"project\": \"string\",\n  \"generated_at\": \"ISO8601\"\n}\n```\n\nFor the full schema, see [`schemas\u002Fplan-brief-context.v1.schema.json`](${CLAUDE_SKILL_DIR}\u002Fschemas\u002Fplan-brief-context.v1.schema.json).\n\n## Execution Flow\n\nWhen the skill starts, Claude operates in the following steps.\n\n### Step 1: Resolve the project name\n\n```bash\nPROJECT_NAME=\"$(basename \"$(git rev-parse --show-toplevel)\")\"\n```\n\nIf `PROJECT_NAME` is empty (outside git), use `current` as the default.\n\n### Step 2: Search harness-mem **project-only** (default)\n\nWhen the arguments do **not** include the `--cross-project-group \u003Cname>` flag (default behavior):\n\nCall `mcp__harness__harness_mem_search` **always** with the following parameters:\n\n```\nproject: \u003CPROJECT_NAME>\nstrict_project: true\nquery: \u003Cuser request>\nexpand_links: true\nlimit: 5\n```\n\n> **Important**: the `project` parameter is **required**. Do not pass an empty string or `null`.\n> Specify `strict_project: true` and **never** perform a cross-project search.\n> You may narrow with a `tags` filter for `decision` \u002F `pattern` if needed, but keep `project` fixed.\n\nRetrieve up to 5 similar items from past decisions (D1-D41) \u002F patterns (P1-P33) \u002F the 28 Plans archive entries.\n\n### Step 2 (alt): cross-project search (Phase 65.3.5 opt-in)\n\nOnly when the arguments **do** include the `--cross-project-group \u003Cname>` flag:\n\nFollowing D43 Option α (MCP N-call), perform the cross-project search in the following steps.\n\n```bash\n# (a) resolve group → member projects (yaml SSOT)\nMEMBERS_JSON=\"$(bash scripts\u002Fload-cross-project-groups.sh --group \"\u003Cname>\" 2>\u002Fdev\u002Fnull)\" || {\n  echo \"ERROR: cross-project group not found: \u003Cname>\" >&2\n  exit 1\n}\n# MEMBERS_JSON is a JSON array in the form [\"proj1\",\"proj2\",...]\n```\n\nIf `MEMBERS_JSON` is `[]` (empty array), emit a warning and fall back to the default single-project search.\n\nWhen `MEMBERS_JSON` is non-empty, **issue one MCP search per member project**:\n\n```\nfor each project in MEMBERS_JSON:\n  mcp__harness__harness_mem_search(\n    project: \u003Cmember>,\n    strict_project: true,\n    query: \u003Cuser request>,\n    expand_links: true,\n    limit: 5\n  )\n```\n\n**Merge, dedupe (by id), and sort by relevance_score descending on the client side**, then narrow to at most 5 items.\nNote that the total number of calls grows (5 calls for a 5-project group), so latency increases.\n\n> **Why N calls**: the memory search tool schema exposes neither `projects: [array]` nor `strict_project: false`,\n> so client-side N-call is the only option for cross-project search.\n\nAlways pass cross-project results through the Layer 2\u002F3 (Phase 65.3.2-65.3.4) redaction:\n- Use `bash scripts\u002Frender-html.sh ... --with-redaction` when rendering the HTML\n- This ensures proper nouns do not leak, via the 3-stage dictionary + NER + final scan\n\n### Step 3: Assemble the context JSON\n\nUse `scripts\u002Fplan-brief-compile.sh` to build JSON conforming to the\n`plan-brief-context.v1` schema from the mem search results.\n\nFrom Phase 105.3 onward, the Plan Brief `confidence` is a backward-compatible field name, and\nits displayed meaning is treated as `plan_readiness`. Fix the computation axes to just the following two.\n\n- DoD clarity: how many machine-verifiable numbers \u002F conditions the request \u002F DoD contains\n- Dependency resolution rate: the fraction of similar Plans whose dependencies can be treated as complete\n\nDisplay the success rate of similar past cases and the count of related Decisions \u002F Patterns as context-only evidence;\ndo not add them to the readiness score on a separate axis. This avoids being misread as \"the AI's comprehension\" or \"probability of success.\"\n\nAlways generate at least one `options` \u002F `risks` \u002F `acceptance_criteria` entry.\nEven when the mem search is empty, fill in at minimum the following.\n\n- `options`: at least one recommended option. Add alternatives if needed, with pros \u002F cons\n- `risks`: at least one risk specific to this plan, such as readiness misread, scope creep, or unobserved data\n- `acceptance_criteria`: at least one condition that can be machine-verified or visually confirmed after execution\n\nExample:\n\n```bash\njq -n \\\n  --arg req \"$USER_REQUEST\" \\\n  --arg proj \"$PROJECT_NAME\" \\\n  --arg ts \"$(date -u +%Y-%m-%dT%H:%M:%SZ)\" \\\n  '{\n    schema: \"plan-brief-context.v1\",\n    user_request: $req,\n    my_understanding: \"(not started yet)\",\n    options: [{name:\"Option A: proceed with minimal validation\", summary:\"confirm DoD and dependencies before implementing\", pros:[\"small impact\"], cons:[\"large redesigns need to be split into separate tasks\"]}],\n    risks: [{kind:\"readiness-misread\", severity:\"warn\", description:\"risk of misreading plan_readiness as the AI's comprehension\", mitigation:\"state clearly in evidence that it is only a metric of DoD clarity + dependency resolution rate\"}],\n    acceptance_criteria: [{id:\"AC-1\", description:\"the Plan Brief context contains non-empty options \u002F risks \u002F acceptance_criteria\", verifiable_by:\"tests\u002Ftest-plan-brief-compile.sh\"}],\n    confidence: 0,\n    confidence_evidence: [\"plan_readiness DoD clarity: 0\u002F60\", \"plan_readiness dependency resolution rate: 0\u002F40\"],\n    tdd_required: \"no\",\n    related_decisions: [],\n    similar_past_plans: [],\n    project: $proj,\n    generated_at: $ts\n  }' > \"$CONTEXT_JSON\"\n```\n\n### Step 4: Generate the HTML\n\nCall `scripts\u002Frender-html.sh` (Phase 65.1.1) with `templates\u002Fhtml\u002Fplan-brief.html.template`:\n\nThe HTML displays the TDD decision in one line.\nThe format is one of `tdd_required: yes`, `tdd_required: no`, or `tdd_required: skip:\u003Creason>`.\n\n```bash\nbash scripts\u002Frender-html.sh \\\n  --template plan-brief \\\n  --data \"$CONTEXT_JSON\" \\\n  --out \"$HTML_OUT\"\n```\n\n### Step 5: Auto-open in the browser\n\nOS-specific dispatch via `scripts\u002Fplan-brief-open.sh`:\n\n```bash\nbash scripts\u002Fplan-brief-open.sh \"$HTML_OUT\"\n```\n\nWhen the `BROWSER=true` env is set (CI environment), open is **skipped** and only the path is printed via `printf`.\n\n### Step 6: Wait for user approval\n\nConfirm \"is it OK to proceed to implementation with this understanding.\"\nMemory writes after approval are the responsibility of a separate skill (Phase 65.1.4's `plan-brief-record-decision.sh`).\n\n## Failure behavior\n\n| Failure | Behavior |\n|---------|----------|\n| `mcp__harness__harness_mem_search` unreachable | Show a warning and continue with `related_decisions` \u002F `similar_past_plans` as empty arrays |\n| `git rev-parse --show-toplevel` failed | Continue with `PROJECT_NAME=current` |\n| `render-html.sh` failed | Print the error to stderr and exit 1 |\n| `plan-brief-open.sh` failed | Just print the HTML path to stdout and exit 0 (browser open is best-effort) |\n\n## Related\n\n- `scripts\u002Frender-html.sh` (Phase 65.1.1) — HTML template engine\n- `scripts\u002Fplan-brief-compile.sh` (Phase 65.1.3) — context compilation\n- `scripts\u002Fplan-brief-record-decision.sh` (Phase 65.1.4) — approval memory write\n- `harness-accept` skill (Phase 65.2.1) — acceptance-decision skill (paired structure)\n- `harness-progress` skill (Phase 65.4.1) — progress-management skill (paired structure)\n","# harness-plan-brief\n\nA skill that presents the plan Claude is about to start, on **a single HTML page**, for non-engineer requesters and producer roles.\nUse it at the requester's cognitive-load peak (1): understanding the plan.\n\n## Quick Reference\n\n- \"**create a Plan Brief**\" → this skill\n- \"**give me a rough overview before implementation**\" → this skill\n- \"**show the plan for a non-engineer**\" → this skill\n\n## Responsibility boundaries\n\n| Scope | This skill's responsibility |\n|-------|-----------------------------|\n| Search | **Current project only** (always specify `project: \u003Ccurrent>`, `strict_project: true`) |\n| Cross-project | **Do not do it** (opened up as opt-in via the `--cross-project-group \u003Cname>` flag from Phase 65.3 onward) |\n| Writes | Do not do it (memory writes after Plan Brief approval are the responsibility of `plan-brief-record-decision.sh`) |\n| plan_readiness computation | Delegated to `scripts\u002Fplan-brief-compile.sh`. The compat field name `confidence` is kept, but its meaning is limited to DoD clarity + dependency resolution rate |\n\n## Input\n\nPass the user's request in the `[task-description]` argument.\nWhen there is no argument, take it interactively.\n\n## Output\n\n| Output | Path | Format |\n|--------|------|--------|\n| Plan Brief HTML | `.claude\u002Fstate\u002Fviews\u002Fplan-brief-\u003Ctimestamp>.html` | Standalone HTML (no server, no JS framework) |\n| Plan Brief context JSON | `.claude\u002Fstate\u002Fviews\u002Fplan-brief-\u003Ctimestamp>.context.json` | `plan-brief-context.v1` schema |\n\n## Schema: `plan-brief-context.v1`\n\n```json\n{\n  \"schema\": \"plan-brief-context.v1\",\n  \"user_request\": \"string (the user's original request)\",\n  \"my_understanding\": \"string (Claude's understanding in 1-3 paragraphs)\",\n  \"options\": [\n    { \"name\": \"string\", \"summary\": \"string\", \"pros\": [\"string\"], \"cons\": [\"string\"] }\n  ],\n  \"risks\": [\n    { \"kind\": \"string\", \"severity\": \"info|warn|critical\", \"description\": \"string\", \"mitigation\": \"string\" }\n  ],\n  \"acceptance_criteria\": [\n    { \"id\": \"string\", \"description\": \"string\", \"verifiable_by\": \"string\" }\n  ],\n  \"tdd_required\": \"yes|no|skip:\u003Creason>\",\n  \"confidence\": 0,\n  \"confidence_evidence\": [\"string (plan_readiness evidence: DoD clarity + dependency resolution only)\"],\n  \"related_decisions\": [\n    { \"id\": \"string\", \"title\": \"string\", \"relevance\": \"string\" }\n  ],\n  \"similar_past_plans\": [\n    { \"archive_path\": \"string\", \"phase\": \"string\", \"outcome\": \"cc:done|cc:WIP|cc:TODO|skipped\", \"relevance\": \"string\" }\n  ],\n  \"project\": \"string\",\n  \"generated_at\": \"ISO8601\"\n}\n```\n\nFor the full schema, see [`schemas\u002Fplan-brief-context.v1.schema.json`](${CLAUDE_SKILL_DIR}\u002Fschemas\u002Fplan-brief-context.v1.schema.json).\n\n## Execution Flow\n\nWhen the skill starts, Claude operates in the following steps.\n\n### Step 1: Resolve the project name\n\n```bash\nPROJECT_NAME=\"$(basename \"$(git rev-parse --show-toplevel)\")\"\n```\n\nIf `PROJECT_NAME` is empty (outside git), use `current` as the default.\n\n### Step 2: Search harness-mem **project-only** (default)\n\nWhen the arguments do **not** include the `--cross-project-group \u003Cname>` flag (default behavior):\n\nCall `mcp__harness__harness_mem_search` **always** with the following parameters:\n\n```\nproject: \u003CPROJECT_NAME>\nstrict_project: true\nquery: \u003Cuser request>\nexpand_links: true\nlimit: 5\n```\n\n> **Important**: the `project` parameter is **required**. Do not pass an empty string or `null`.\n> Specify `strict_project: true` and **never** perform a cross-project search.\n> You may narrow with a `tags` filter for `decision` \u002F `pattern` if needed, but keep `project` fixed.\n\nRetrieve up to 5 similar items from past decisions (D1-D41) \u002F patterns (P1-P33) \u002F the 28 Plans archive entries.\n\n### Step 2 (alt): cross-project search (Phase 65.3.5 opt-in)\n\nOnly when the arguments **do** include the `--cross-project-group \u003Cname>` flag:\n\nFollowing D43 Option α (MCP N-call), perform the cross-project search in the following steps.\n\n```bash\n# (a) resolve group → member projects (yaml SSOT)\nMEMBERS_JSON=\"$(bash scripts\u002Fload-cross-project-groups.sh --group \"\u003Cname>\" 2>\u002Fdev\u002Fnull)\" || {\n  echo \"ERROR: cross-project group not found: \u003Cname>\" >&2\n  exit 1\n}\n# MEMBERS_JSON is a JSON array in the form [\"proj1\",\"proj2\",...]\n```\n\nIf `MEMBERS_JSON` is `[]` (empty array), emit a warning and fall back to the default single-project search.\n\nWhen `MEMBERS_JSON` is non-empty, **issue one MCP search per member project**:\n\n```\nfor each project in MEMBERS_JSON:\n  mcp__harness__harness_mem_search(\n    project: \u003Cmember>,\n    strict_project: true,\n    query: \u003Cuser request>,\n    expand_links: true,\n    limit: 5\n  )\n```\n\n**Merge, dedupe (by id), and sort by relevance_score descending on the client side**, then narrow to at most 5 items.\nNote that the total number of calls grows (5 calls for a 5-project group), so latency increases.\n\n> **Why N calls**: the memory search tool schema exposes neither `projects: [array]` nor `strict_project: false`,\n> so client-side N-call is the only option for cross-project search.\n\nAlways pass cross-project results through the Layer 2\u002F3 (Phase 65.3.2-65.3.4) redaction:\n- Use `bash scripts\u002Frender-html.sh ... --with-redaction` when rendering the HTML\n- This ensures proper nouns do not leak, via the 3-stage dictionary + NER + final scan\n\n### Step 3: Assemble the context JSON\n\nUse `scripts\u002Fplan-brief-compile.sh` to build JSON conforming to the\n`plan-brief-context.v1` schema from the mem search results.\n\nFrom Phase 105.3 onward, the Plan Brief `confidence` is a backward-compatible field name, and\nits displayed meaning is treated as `plan_readiness`. Fix the computation axes to just the following two.\n\n- DoD clarity: how many machine-verifiable numbers \u002F conditions the request \u002F DoD contains\n- Dependency resolution rate: the fraction of similar Plans whose dependencies can be treated as complete\n\nDisplay the success rate of similar past cases and the count of related Decisions \u002F Patterns as context-only evidence;\ndo not add them to the readiness score on a separate axis. This avoids being misread as \"the AI's comprehension\" or \"probability of success.\"\n\nAlways generate at least one `options` \u002F `risks` \u002F `acceptance_criteria` entry.\nEven when the mem search is empty, fill in at minimum the following.\n\n- `options`: at least one recommended option. Add alternatives if needed, with pros \u002F cons\n- `risks`: at least one risk specific to this plan, such as readiness misread, scope creep, or unobserved data\n- `acceptance_criteria`: at least one condition that can be machine-verified or visually confirmed after execution\n\nExample:\n\n```bash\njq -n \\\n  --arg req \"$USER_REQUEST\" \\\n  --arg proj \"$PROJECT_NAME\" \\\n  --arg ts \"$(date -u +%Y-%m-%dT%H:%M:%SZ)\" \\\n  '{\n    schema: \"plan-brief-context.v1\",\n    user_request: $req,\n    my_understanding: \"(not started yet)\",\n    options: [{name:\"Option A: proceed with minimal validation\", summary:\"confirm DoD and dependencies before implementing\", pros:[\"small impact\"], cons:[\"large redesigns need to be split into separate tasks\"]}],\n    risks: [{kind:\"readiness-misread\", severity:\"warn\", description:\"risk of misreading plan_readiness as the AI's comprehension\", mitigation:\"state clearly in evidence that it is only a metric of DoD clarity + dependency resolution rate\"}],\n    acceptance_criteria: [{id:\"AC-1\", description:\"the Plan Brief context contains non-empty options \u002F risks \u002F acceptance_criteria\", verifiable_by:\"tests\u002Ftest-plan-brief-compile.sh\"}],\n    confidence: 0,\n    confidence_evidence: [\"plan_readiness DoD clarity: 0\u002F60\", \"plan_readiness dependency resolution rate: 0\u002F40\"],\n    tdd_required: \"no\",\n    related_decisions: [],\n    similar_past_plans: [],\n    project: $proj,\n    generated_at: $ts\n  }' > \"$CONTEXT_JSON\"\n```\n\n### Step 4: Generate the HTML\n\nCall `scripts\u002Frender-html.sh` (Phase 65.1.1) with `templates\u002Fhtml\u002Fplan-brief.html.template`:\n\nThe HTML displays the TDD decision in one line.\nThe format is one of `tdd_required: yes`, `tdd_required: no`, or `tdd_required: skip:\u003Creason>`.\n\n```bash\nbash scripts\u002Frender-html.sh \\\n  --template plan-brief \\\n  --data \"$CONTEXT_JSON\" \\\n  --out \"$HTML_OUT\"\n```\n\n### Step 5: Auto-open in the browser\n\nOS-specific dispatch via `scripts\u002Fplan-brief-open.sh`:\n\n```bash\nbash scripts\u002Fplan-brief-open.sh \"$HTML_OUT\"\n```\n\nWhen the `BROWSER=true` env is set (CI environment), open is **skipped** and only the path is printed via `printf`.\n\n### Step 6: Wait for user approval\n\nConfirm \"is it OK to proceed to implementation with this understanding.\"\nMemory writes after approval are the responsibility of a separate skill (Phase 65.1.4's `plan-brief-record-decision.sh`).\n\n## Failure behavior\n\n| Failure | Behavior |\n|---------|----------|\n| `mcp__harness__harness_mem_search` unreachable | Show a warning and continue with `related_decisions` \u002F `similar_past_plans` as empty arrays |\n| `git rev-parse --show-toplevel` failed | Continue with `PROJECT_NAME=current` |\n| `render-html.sh` failed | Print the error to stderr and exit 1 |\n| `plan-brief-open.sh` failed | Just print the HTML path to stdout and exit 0 (browser open is best-effort) |\n\n## Related\n\n- `scripts\u002Frender-html.sh` (Phase 65.1.1) — HTML template engine\n- `scripts\u002Fplan-brief-compile.sh` (Phase 65.1.3) — context compilation\n- `scripts\u002Fplan-brief-record-decision.sh` (Phase 65.1.4) — approval memory write\n- `harness-accept` skill (Phase 65.2.1) — acceptance-decision skill (paired structure)\n- `harness-progress` skill (Phase 65.4.1) — progress-management skill (paired structure)\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":29,"description-en":7,"user-invocable":30},[25,26,27,28],"Read","Write","Edit","Bash","[task-description]",true,"main","3517f6fc9c5159f32d585682386ed45e35c30ddf","skills\u002Fharness-plan-brief","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness","https:\u002F\u002Fgithub.com\u002Ffoden303","Software Engineer","2026-11-06 10:59:21",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":30},[40,43,46],{"tool":41,"command":42},"npx","npx skills add foden303\u002Fharness --skill harness-plan-brief",{"tool":44,"command":45},"bunx","bunx skills add foden303\u002Fharness --skill harness-plan-brief",{"tool":47,"command":48},"pnpm","pnpm dlx skills add foden303\u002Fharness --skill harness-plan-brief","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fharness-plan-brief\u002FSKILL.md",[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"schemas\u002Fplan-brief-context.v1.schema.json","REFERENCE","参考文档",4433,"https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fharness-plan-brief\u002Fschemas\u002Fplan-brief-context.v1.schema.json",[58,64,70,77,84,91],{"skillNo":59,"name":60,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M79DWR27RWW11HNKY0MRECPP","escape-skill","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-escape\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M79DWPSR8ZK3V4DQK5EWVJ3K","zz-review-empty","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fzz-review-empty\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M79DWFV6PYV0QEZ3SC32VMCM","memory","Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, harness-mem, past decisions, or record this. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fmemory\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79DWB6MB7EQK2JT4A84NHJD","maintenance","File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: \u002Fmaintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new feature development.","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fmaintenance\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M79DW33AEPBCXFAMX8YH56PG","harness-work","HAR: Execute Plans.md tasks from single task to full parallel team run. Trigger: implement, execute, do everything, breezing, team run, parallel. Do NOT load for: planning, review, release, setup.","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fharness-work\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M79DVWV7PZC0E2GYC103QBYZ","harness-sync","HAR: Sync Plans.md with implementation. Drift detect, marker update, retrospective. Trigger: sync-status, where am I, check progress. --snapshot for snapshots. Do NOT load for: planning, implementation, review, release.","https:\u002F\u002Fgithub.com\u002Ffoden303\u002Fharness\u002Fblob\u002Fmain\u002Fskills\u002Fharness-sync\u002FSKILL.md",[],[]]