[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CF0C2X7KM96T8ABKMJYC0N":3,"skill-same:01M7CF0C2X7KM96T8ABKMJYC0N":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7CF0C2X7KM96T8ABKMJYC0N","rr-plan",null,"Plan work before any edit. Given a spec (docs\u002Fsdlc\u002Fspecs\u002F\u003Cslug>.md), write the programme plan docs\u002Fsdlc\u002Fplans\u002F\u003Cslug>.md — files that change, order of work, risks, proof per requirement, rollback. Given one task, measure its weight with `state.py weight` (six axes, seven lines), take the mode it gives (light, guarded, full), shape the plan by that mode — inline, plan mode, or written — collect every question the plan depends on now, and register the task with `state.py start`, which arms the scope guard. Use on \"\u002Frr-plan\", \"plan this\", \"plan the implementation\", \"make the plan from the spec\", and whenever \u002Frr-build finds no task in flight.","vanssata\u002Fclaude-agentic-sdlc-module","vanssata","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1220804?v=4","01M7CEZV36E48TC48Q0V69PFE0","Ivan kakurov","01M7CEZV3SVZE2WWZYMDW13X2X",3,"MIT","https:\u002F\u002Fgithub.com\u002Fvanssata\u002Fclaude-agentic-sdlc-module\u002Fblob\u002Fmain\u002Fskills\u002Frr-plan\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rr-plan\ndescription: Plan work before any edit. Given a spec (docs\u002Fsdlc\u002Fspecs\u002F\u003Cslug>.md), write the programme plan docs\u002Fsdlc\u002Fplans\u002F\u003Cslug>.md — files that change, order of work, risks, proof per requirement, rollback. Given one task, measure its weight with `state.py weight` (six axes, seven lines), take the mode it gives (light, guarded, full), shape the plan by that mode — inline, plan mode, or written — collect every question the plan depends on now, and register the task with `state.py start`, which arms the scope guard. Use on \"\u002Frr-plan\", \"plan this\", \"plan the implementation\", \"make the plan from the spec\", and whenever \u002Frr-build finds no task in flight.\nargument-hint: \u003Ctask in one sentence> | \u003Cpath to docs\u002Fsdlc\u002Fspecs\u002F\u003Cslug>.md>\n---\n\n# \u002Frr-plan $ARGUMENTS\n\nPlan, never edit: this skill reads code and writes a plan, and the first edit\nbelongs to `\u002Frr-build`. Resolve the install root once:\n\n```bash\nfor AI_HOME in \"${CLAUDE_CONFIG_DIR:-$HOME\u002F.claude}\" \"${CODEX_HOME:-$HOME\u002F.codex}\"; do\n  [ -d \"$AI_HOME\u002Fskills\u002Frr-plan\" ] && break\ndone\nSTATE=\"python3 $AI_HOME\u002Fskills\u002Fai-task\u002Fstate.py\"\n```\n\nRead `docs\u002Fsdlc\u002Fconstitution.md` first and cite the principles a decision rests\non as `C\u003Cn>`; if it is absent, say so in one line and go on. `$STATE status`\nfirst: a task already in flight is finished or abandoned before another starts.\n\n## A spec → the programme plan\n\nWhen `$ARGUMENTS` is a spec (default: the newest `docs\u002Fsdlc\u002Fspecs\u002F*.md`):\n\n1. `docs\u002Fsdlc\u002Fconstitution.md` exists, else `\u002Frr-setup`. The template is\n   `docs\u002Fsdlc\u002Fplans\u002FTEMPLATE.md` when the project overrides it, else\n   `$AI_HOME\u002Fskills\u002Fproject-init\u002Ftemplates\u002Fplan.md`. If the spec's\n   **Flagged concerns** holds unresolved items, list them and have the human\n   resolve or explicitly accept each one before planning.\n2. If `superpowers:writing-plans` is available, use it for the step\n   granularity. Otherwise map each requirement to the files that must change\n   (`grep -n`; `Explore` when a file is not found in a few calls), order the\n   steps so each leaves the repository working, one step about one commit, and\n   name the command or test that proves it.\n3. Challenge it before writing: *what could this break* (callers, migrations,\n   config, other environments) and *which step is the riskiest — can it move\n   earlier or be split*. The answers go into **Risks**; mark the risky step.\n4. Copy the template to `docs\u002Fsdlc\u002Fplans\u002F\u003Cslug>.md`, fill **Files that change \u002F\n   Order of work \u002F Risks \u002F Proof \u002F Rollback**; Proof maps every requirement R\u003Cn>\n   to a test or command. One round of corrections; suggest the commit\n   `plan: \u003Ctitle>`. Each row of the plan is later one task, planned below —\n   unless the whole plan runs as one task through `\u002Frr-build-all` (the project's\n   `batch.default` in `weight.json`, or the developer's call): then every row\n   becomes one step of that task, so give each row its files and its *Consumes*\n   line (the rows it depends on) — that is what `\u002Frr-build-all` reads.\n\n## A task → weight, mode, plan, start\n\n**1. Classify** the request: feature, bugfix, refactoring, hotfix or\ninvestigation — say which and why. `using-riskrails.md` in the shared tree\n(`\"$AI_HOME\u002Friskrails\u002Fai-path\" using-riskrails.md`) and\n`workflows.md#\u003Ckind>` say what each kind requires. A refactoring and a feature\nare never one task.\n\n**2. Name the files** from the request, confirmed with `grep -n`. Recall what\nthe record holds about them — `$STATE recall --files \"\u003Ca>,\u003Cb>\"`: open risks,\nresidual findings and earlier decisions are evidence for the weight and the\nplan. Then weigh:\n\n```bash\n$STATE weight --files \"\u003Ca>,\u003Cb>\" --goal \"\u003Cone sentence>\" \\\n  --declare behaviour=\u003C0-2>:\"\u003Cevidence>\" --declare novelty=\u003C0-2>:\"\u003Cevidence>\"\n```\n\nSeven lines: six axes, W and the mode. Scope, reversibility, coverage and the\nhints are measured; behaviour, domain and novelty are yours to declare, each\nwith its evidence — a declaration without one is refused. Declare what the\nchange does to the project's decisions, not how long it feels. An unknown axis\nscores 1. A hint raises an axis; a declaration below a hint does not lower it.\nThe table is `.ai\u002Fpolicies\u002Fweight.json` (`weight.md` mirrors it).\n\n**3. The mode is the weight's**, not yours: raising it is free\n(`--mode \u003Cm> --by \"\u003Cname>\"` on `start`); lowering it is the human's, from their\nown terminal, or the command they picked in the dialog. Shape the plan by it:\n\n| Mode | Plan | Who sees it before the first edit |\n|---|---|---|\n| light | inline: files, the test, the rollback, in one to five lines | nobody — go |\n| guarded | plan mode: numbered steps, each with its files and tests | the human accepts plan mode |\n| full | written: steps, files, tests, what stays the same, risks, rollback; `architect` on STRONG when the design is open | the human reads and accepts it |\n\nIn every mode: a bugfix's first step is its failing test (C2); a change to\nlegacy behaviour without a test starts with a characterization test; the\nrollback is one line, usually `git revert`. A plan over eight steps is advised\nagainst, not refused — fewer, larger steps cost fewer handoffs.\n\n**4. Questions, now.** Everything the plan depends on is asked before `start`,\nso `\u002Frr-build` stops only on a real blocker. Ask in the conversation, or on the\nrecord with `$STATE ask --topic \u003Cslug> …` and `$STATE answer --topic \u003Cslug> …`\n(see `\u002Frr-spec`); a plan with an open **(blocking)** question is not accepted.\n\n**5. Start.** One call registers the task, its weight and mode, its files and\nsteps, and arms the scope guard:\n\n```bash\n$STATE start --goal \"\u003Cone sentence>\" --workflow \u003Ckind> --files \"\u003Ca>,\u003Cb>\" \\\n  --tests \"\u003Ct>\" [--declare …] [--plan-file \u002Fpath\u002Fsteps.json] [--mode \u003Cm> --by \"\u003Cname>\"]\n```\n\n`--plan-file` is a JSON list `[{\"id\": \"s1\", \"files\": [...], \"tests\": [...]}]`\nfor a guarded or full plan with steps; a light task is one scope and needs none.\nA step may add `\"after\": [\"s0\"]`, the steps it waits for — `\u002Frr-build-all` runs\nthe rest in parallel — and `--batch --by \"\u003Cname>\"` (or `--no-batch`) sets that\nloop for the task; the default is `batch.default` in `weight.json`.\n`--files` lists every file of every step — the guard refuses an edit outside\nthem. `--tests` names the task's own tests; a bugfix names its failing test. At\nguarded and full, run `start` only after the human accepted the plan.\n\nThen hand over: `\u002Frr-build` continues from the state, in this session or the\nnext.\n","# \u002Frr-plan $ARGUMENTS\n\nPlan, never edit: this skill reads code and writes a plan, and the first edit\nbelongs to `\u002Frr-build`. Resolve the install root once:\n\n```bash\nfor AI_HOME in \"${CLAUDE_CONFIG_DIR:-$HOME\u002F.claude}\" \"${CODEX_HOME:-$HOME\u002F.codex}\"; do\n  [ -d \"$AI_HOME\u002Fskills\u002Frr-plan\" ] && break\ndone\nSTATE=\"python3 $AI_HOME\u002Fskills\u002Fai-task\u002Fstate.py\"\n```\n\nRead `docs\u002Fsdlc\u002Fconstitution.md` first and cite the principles a decision rests\non as `C\u003Cn>`; if it is absent, say so in one line and go on. `$STATE status`\nfirst: a task already in flight is finished or abandoned before another starts.\n\n## A spec → the programme plan\n\nWhen `$ARGUMENTS` is a spec (default: the newest `docs\u002Fsdlc\u002Fspecs\u002F*.md`):\n\n1. `docs\u002Fsdlc\u002Fconstitution.md` exists, else `\u002Frr-setup`. The template is\n   `docs\u002Fsdlc\u002Fplans\u002FTEMPLATE.md` when the project overrides it, else\n   `$AI_HOME\u002Fskills\u002Fproject-init\u002Ftemplates\u002Fplan.md`. If the spec's\n   **Flagged concerns** holds unresolved items, list them and have the human\n   resolve or explicitly accept each one before planning.\n2. If `superpowers:writing-plans` is available, use it for the step\n   granularity. Otherwise map each requirement to the files that must change\n   (`grep -n`; `Explore` when a file is not found in a few calls), order the\n   steps so each leaves the repository working, one step about one commit, and\n   name the command or test that proves it.\n3. Challenge it before writing: *what could this break* (callers, migrations,\n   config, other environments) and *which step is the riskiest — can it move\n   earlier or be split*. The answers go into **Risks**; mark the risky step.\n4. Copy the template to `docs\u002Fsdlc\u002Fplans\u002F\u003Cslug>.md`, fill **Files that change \u002F\n   Order of work \u002F Risks \u002F Proof \u002F Rollback**; Proof maps every requirement R\u003Cn>\n   to a test or command. One round of corrections; suggest the commit\n   `plan: \u003Ctitle>`. Each row of the plan is later one task, planned below —\n   unless the whole plan runs as one task through `\u002Frr-build-all` (the project's\n   `batch.default` in `weight.json`, or the developer's call): then every row\n   becomes one step of that task, so give each row its files and its *Consumes*\n   line (the rows it depends on) — that is what `\u002Frr-build-all` reads.\n\n## A task → weight, mode, plan, start\n\n**1. Classify** the request: feature, bugfix, refactoring, hotfix or\ninvestigation — say which and why. `using-riskrails.md` in the shared tree\n(`\"$AI_HOME\u002Friskrails\u002Fai-path\" using-riskrails.md`) and\n`workflows.md#\u003Ckind>` say what each kind requires. A refactoring and a feature\nare never one task.\n\n**2. Name the files** from the request, confirmed with `grep -n`. Recall what\nthe record holds about them — `$STATE recall --files \"\u003Ca>,\u003Cb>\"`: open risks,\nresidual findings and earlier decisions are evidence for the weight and the\nplan. Then weigh:\n\n```bash\n$STATE weight --files \"\u003Ca>,\u003Cb>\" --goal \"\u003Cone sentence>\" \\\n  --declare behaviour=\u003C0-2>:\"\u003Cevidence>\" --declare novelty=\u003C0-2>:\"\u003Cevidence>\"\n```\n\nSeven lines: six axes, W and the mode. Scope, reversibility, coverage and the\nhints are measured; behaviour, domain and novelty are yours to declare, each\nwith its evidence — a declaration without one is refused. Declare what the\nchange does to the project's decisions, not how long it feels. An unknown axis\nscores 1. A hint raises an axis; a declaration below a hint does not lower it.\nThe table is `.ai\u002Fpolicies\u002Fweight.json` (`weight.md` mirrors it).\n\n**3. The mode is the weight's**, not yours: raising it is free\n(`--mode \u003Cm> --by \"\u003Cname>\"` on `start`); lowering it is the human's, from their\nown terminal, or the command they picked in the dialog. Shape the plan by it:\n\n| Mode | Plan | Who sees it before the first edit |\n|---|---|---|\n| light | inline: files, the test, the rollback, in one to five lines | nobody — go |\n| guarded | plan mode: numbered steps, each with its files and tests | the human accepts plan mode |\n| full | written: steps, files, tests, what stays the same, risks, rollback; `architect` on STRONG when the design is open | the human reads and accepts it |\n\nIn every mode: a bugfix's first step is its failing test (C2); a change to\nlegacy behaviour without a test starts with a characterization test; the\nrollback is one line, usually `git revert`. A plan over eight steps is advised\nagainst, not refused — fewer, larger steps cost fewer handoffs.\n\n**4. Questions, now.** Everything the plan depends on is asked before `start`,\nso `\u002Frr-build` stops only on a real blocker. Ask in the conversation, or on the\nrecord with `$STATE ask --topic \u003Cslug> …` and `$STATE answer --topic \u003Cslug> …`\n(see `\u002Frr-spec`); a plan with an open **(blocking)** question is not accepted.\n\n**5. Start.** One call registers the task, its weight and mode, its files and\nsteps, and arms the scope guard:\n\n```bash\n$STATE start --goal \"\u003Cone sentence>\" --workflow \u003Ckind> --files \"\u003Ca>,\u003Cb>\" \\\n  --tests \"\u003Ct>\" [--declare …] [--plan-file \u002Fpath\u002Fsteps.json] [--mode \u003Cm> --by \"\u003Cname>\"]\n```\n\n`--plan-file` is a JSON list `[{\"id\": \"s1\", \"files\": [...], \"tests\": [...]}]`\nfor a guarded or full plan with steps; a light task is one scope and needs none.\nA step may add `\"after\": [\"s0\"]`, the steps it waits for — `\u002Frr-build-all` runs\nthe rest in parallel — and `--batch --by \"\u003Cname>\"` (or `--no-batch`) sets that\nloop for the task; the default is `batch.default` in `weight.json`.\n`--files` lists every file of every step — the guard refuses an edit outside\nthem. `--tests` names the task's own tests; a bugfix names its failing test. At\nguarded and full, run `start` only after the human accepted the plan.\n\nThen hand over: `\u002Frr-build` continues from the state, in this session or the\nnext.\n",{"name":5,"description":7,"argument-hint":24},"\u003Ctask in one sentence> | \u003Cpath to docs\u002Fsdlc\u002Fspecs\u002F\u003Cslug>.md>","main","84a91bd082ae3a289fcbe8a0f1a52bdebe5f638a","skills\u002Frr-plan",0,"https:\u002F\u002Fgithub.com\u002Fvanssata\u002Fclaude-agentic-sdlc-module","https:\u002F\u002Fvanssata.github.io\u002Fclaude-agentic-sdlc-module\u002F","https:\u002F\u002Fgithub.com\u002Fvanssata","2026-11-14 21:12:58",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add vanssata\u002Fclaude-agentic-sdlc-module --skill rr-plan",{"tool":39,"command":40},"bunx","bunx skills add vanssata\u002Fclaude-agentic-sdlc-module --skill rr-plan",{"tool":42,"command":43},"pnpm","pnpm dlx skills add vanssata\u002Fclaude-agentic-sdlc-module --skill rr-plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvanssata\u002Fclaude-agentic-sdlc-module\u002Fblob\u002Fmain\u002Fskills\u002Frr-plan\u002FSKILL.md",true,[],[48,55,62,68,75,82],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7CF1FY7PYAK5378YCV5RV5S","sylius-fixtures","Load the Sylius fixture suite into the local database","https:\u002F\u002Fgithub.com\u002Fvanssata\u002Fclaude-agentic-sdlc-module\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsetup\u002Fnew-shop-like\u002Fdot-claude\u002Fskills\u002Fsylius-fixtures\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7CF1CTV8SNSJEGJ88HFM6JC","deploy-staging","Deploy the current branch to staging and smoke-test the checkout. Use on \"deploy to staging\".","https:\u002F\u002Fgithub.com\u002Fvanssata\u002Fclaude-agentic-sdlc-module\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsetup\u002Fnew-shop-like\u002Fdot-claude\u002Fskills\u002Fdeploy-staging\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"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":65,"categories":66,"keywords":67,"publishedAt":19},"01M7CF1ARVD7MZGDM7FJKE8CNR","rr-status","https:\u002F\u002Fgithub.com\u002Fvanssata\u002Fclaude-agentic-sdlc-module\u002Fblob\u002Fmain\u002Fskills\u002Frr-status\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7CF136MTETD8RF1NYJGYHK7","rr-spec","Turn a rough idea into one file, docs\u002Fsdlc\u002Fspecs\u002F\u003Cslug>.md — an `## Intent` section (problem, outcome, affected users and systems, constraints, decisions taken) from a short one-question-at-a-time brainstorm recorded through state.py, then requirements and design from the architect agent on the STRONG tier, checked against the project's constitution, instruction files, skills and ADRs, ending with explicitly flagged concerns (especially contradicting policies). Accepts an existing docs\u002Fsdlc\u002Fintent\u002F\u003Cslug>.md instead of the brainstorm. Use when starting a feature, \"write the spec\", \"let's define what we want\", \"design this\", before any plan or code.","https:\u002F\u002Fgithub.com\u002Fvanssata\u002Fclaude-agentic-sdlc-module\u002Fblob\u002Fmain\u002Fskills\u002Frr-spec\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7CF0WJVAB1ZCC0GF6NZ7H87","rr-ship","Close the task — state.py close measures the two facts (a green whole-suite verify on the tree as it is now; every changed file inside the task's files), applies the mode table and either archives the task or, in full mode, requests the human's approval and prints the exact approve command for their own terminal. Writes the commit message body and suggests the commit; never merges or deploys, and commits, pushes or approves only as the command the human picked in the dialog, verbatim, once. Use on \"\u002Frr-ship\", \"close the task\", \"ship it\", \"ready for approval\", after \u002Frr-build or \u002Frr-review.","https:\u002F\u002Fgithub.com\u002Fvanssata\u002Fclaude-agentic-sdlc-module\u002Fblob\u002Fmain\u002Fskills\u002Frr-ship\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"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":85,"categories":86,"keywords":87,"publishedAt":19},"01M7CF0SZAWZFAJBEK64M27KRF","rr-setup","https:\u002F\u002Fgithub.com\u002Fvanssata\u002Fclaude-agentic-sdlc-module\u002Fblob\u002Fmain\u002Fskills\u002Frr-setup\u002FSKILL.md",[],[]]