autoplan — Claude Code skill: plans and installation
The autoplan Claude Code skill drafts implementation plans without asking follow-up questions. It inspects the repository and maps risks to concrete plan steps.
MIT 287 installs ★ 6 updated 2026-11-10
npx skills add prathamdby/skills --skill autoplan -a claude-codeWhat autoplan does
autoplan runs in Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. It analyzes a request and its repository, then returns a plan in the conversation or at a path named by the caller. It does not edit product code.
The skill checks contracts and related files, and uses ADRs, tests, and repository notes as evidence. The plan depth follows the task: small changes get a compact response, while migrations and risky work get assumptions, a file map, ordered phases, and outcome checks. Each identified risk belongs to a plan step.
When a request lacks a grounded target or asks for implementation rather than planning, autoplan returns BLOCKED with the missing detail and a workable example. Its cold scan is bounded to at most three anchors per module, across up to 30 manifest modules.
What it helps with
- draft an implementation plan without follow-up questions
- split a large change into reviewable phases
- locate relevant contracts, tests, and ADRs
- assign risks to specific plan steps
- decide whether a change needs a short or detailed plan
Example prompts for the agent
- Plan a schema migration in this repository without asking me questions.
- Break the new API work into phases and attach risks to each one.
- Draft a contract-change plan and include checks for its expected outcomes.
How to install autoplan
1Skills CLI (Vercel)
npx skills add prathamdby/skills --skill autoplan -a claude-code2Manually: put the files in place
~/.claude/skills/autoplan/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/autoplan/
1Skills CLI (Vercel)
npx skills add prathamdby/skills --skill autoplan -a codex2Manually: put the files in place
.agents/skills/autoplan/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add prathamdby/skills --skill autoplan -a cursor2Manually: put the files in place
.cursor/skills/autoplan/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install prathamdby/skills skills/engineering/autoplan2Manually: put the files in place
.github/skills/autoplan/SKILL.md1Skills CLI (Vercel)
npx skills add prathamdby/skills --skill autoplan -a gemini-cli2Platform CLI
gemini skills install https://github.com/prathamdby/skills --path skills/engineering/autoplanManually: put the files in place
.devin/skills/autoplan/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add prathamdby/skills --skill autoplan -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about autoplan
How do I install autoplan in Claude Code?
Run npx skills add prathamdby/skills --skill autoplan -a claude-code. The skill file is at ~/.claude/skills/autoplan/SKILL.md.
What does autoplan do?
It examines a request and its repository, then produces an implementation plan with phases, risks, and outcome checks. It does not change product code.
Will autoplan implement a requested feature?
No. It is for planning, not product edits. For a build request, it returns BLOCKED, names the missing planning target, and gives a workable example.
Source text
SKILL.md · MIT
--- name: autoplan description: > When the user wants an implementation plan written without stopping for questions. --- # Autoplan Analysis only. Deliver one plan in thread, or at the caller's named path. ## Options and triage Default: current repo, standard depth, thread output. Quick/sketch uses Shape and Risks with always-on lenses. Thorough/risky/migration uses deep, winning over quick; a named area scopes evidence. Resolve conflicting scope narrowly and record both readings under Assumptions; never ask. Before evidence, `BLOCKED` if no groundable verb/object/area, a non-repo intent has no plannable target, or building rather than planning was requested. Name the missing piece and one workable example; emit no lenses/map/milestones on refusal. A build request does not authorize product edits by this skill. Trivial means one module, no contract/data/signature change, and one-sentence behavior. Return `DIRECT` plus that sentence and three lines: shape, files, first step; no lenses. Otherwise record `intent | scope | depth | terminal`. Done when triage has a terminal or a grounded target. ## 1. Evidence Check whether the requested contract already exists; harden an existing match, not rebuild it. Locate sibling recon's installed `SKILL.md` to resolve its anchor and shared/legacy memory rules. Read a repository-verified snapshot whose head resolves; do not invoke a refresh merely to read it. Without usable memory, cold-scan at most three anchors for each of at most 30 manifest modules. Missing recon is not an evidence dependency: use that bounded scan instead. Scan ADR trees (`docs/adr/`, `adr/`, `doc/adr/`, `docs/decisions/`) silently when absent. Note TODOs, recent reverts, and duplication. Dirty content is an Assumptions overlay, not proof of existing contracts. Every later claim cites a path/test/ADR, a scoped no-match result, or an explicit missing-evidence Assumption; cite inherited patterns. Done when material claims have provenance. ## 2. Lenses Apply all always-on probes in `REFERENCE.md`: contracts/API, failure/rollback, longevity/debt. For a leaf, playbook, or matcher, also apply `references/router-contracts.md`. Score every probe for each activated lens, turning a hit into a cited risk owned by a plan step; close each lens pass with cite, risk → step, or no evidence. Deep activates all. Otherwise load only triggered lenses: - Schema/backfill, stored artifacts, toolchain: `references/data.md`. - External consumers/stored payloads: `references/compatibility.md`. - Auth/secrets/PII/untrusted input: `references/security.md`. - Hot paths/cost-bearing calls: `references/cost.md`. - Services/deployment/paging: `references/operations.md`. State one skip line per inactive lens. Done when every active probe is scored and each risk has an owner. ## 3. Plan Specify decisions, changed contracts, constraints, and deviations from cited patterns, not implementation bodies or restatements. Standard/deep includes: Assumptions; Shape (bold sentence + pattern); Layer map (NEW/CHANGED roles); phase sequence; file-plus-symbol grounding (prose: file + contract step); worst-first Risks (probability × impact, or stated judgment); Milestones; non-goals. Sketch includes only Shape and Risks. Small work is one PR. Larger work lists every milestone in build order, and each milestone is one reviewable vertical PR. Approval covers that whole list, in that order. The first milestone is the thinnest end-to-end contract/check slice. Later milestones stay in the same approval. Do not ask which milestone to build. Name landed symbols, expected success and relevant failure outcomes, and assertions or observed manual results proving them. Exit zero alone is not proof. End the plan on its last section. End a DIRECT reply on its three lines. End a BLOCKED reply on the missing piece and the workable example. Add no next step, handoff, review route, or ship route in any section. A route the caller already has stays with the caller. Name a skill or file when the work changes it. Done with `PLANNED` when behavior is grounded or assumed, risks are owned, and every milestone has outcome-linked checks. Terminals: `PLANNED`, `DIRECT`, `BLOCKED`.
© prathamdby · MIT · prathamdby/skills