feature-plan
Skill6 starsChanged 27 days agoMITView on GitHub
Turn an APPROVED specification into an implementation plan (docs/plans/PLAN-NNNN-slug.md) — tasks traced to requirements and acceptance criteria, the gates that must be green, rollback, and the orchestration loop. Also the procedure for executing an approved plan. Use after /approve spec, or when the owner asks how a feature will be built.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- kuyacarlo/skillstheir own version, first seen Oct 13, 2026
- lifemixture/ai-orchestration-repotheir own version, first seen Oct 11, 2026
- Simone-Tarantino/godot-superpowerstheir own version, first seen Oct 11, 2026
- hempq/symfony-claude-codetheir own version, first seen Oct 9, 2026
- levy-street/world-of-claudecrafttheir own version, first seen Oct 8, 2026
- refpath/chatgpt-teamtheir own version, first seen Sep 12, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- levy-street/world-of-claudecraft★ 2.3ksame name
- Simone-Tarantino/godot-superpowers★ 2same name
- dung204/hono-starter-template★ 1same name
- hempq/symfony-claude-code★ 1same name
- Koshux/agentic-sdlc-scaffold★ 0same name
- kuyacarlo/skills★ 0same name
- lifemixture/ai-orchestration-repo★ 0same name
- refpath/chatgpt-team★ 0same name
- telefrek/vallorcine★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adrSkill
- approveSkill
- intentSkill
- observatorySkill
- orchestrateSkill
- reflectSkill
- session-closeSkill
- specSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 0 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read the spec, its linked ADRs, docs/domain/*.md, REVIEW.md, and bash .claude/hooks/py.sh tools/context_graph.py query <SPEC stem>.
- Very specific: line 16
If the plan needs a decision that no accepted ADR covers (stack, data store, hosting, channel, model), write that ADR first with /adr — the …
- Very specific: line 18
Create docs/plans/PLAN-NNNN-<slug>.md from template.md, status: draft, spec: "[[SPEC-…]]".
- Very specific: line 32
Add a row to docs/plans/README.md.
- Very specific: line 49
If orchestration is enabled (orchestration/config.toml): after the task's code is ready, run bash .claude/hooks/py.sh orchestration/run.py …
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/feature-plan — plan an approved spec, then execute it
A. Writing the plan
Precondition: the spec is approved. If not, stop — tell the owner which /approve spec NNNN is
missing. (approve.py refuses a plan on an unapproved spec, and the CHAIN-PLAN gate fails.)
- Read the spec, its linked ADRs,
docs/domain/*.md,REVIEW.md, andbash .claude/hooks/py.sh tools/context_graph.py query <SPEC stem>. - If the plan needs a decision that no accepted ADR covers (stack, data store, hosting, channel,
model), write that ADR first with
/adr— the plan links to it and waits for its approval. - Create
docs/plans/PLAN-NNNN-<slug>.mdfrom template.md,status: draft,spec: "[[SPEC-…]]". Every task:- [ ] T<n> — <what> (REQ-…, AC-…) — verify: <command or check>. Small tasks (one commit each); a first version needs about 6–10. If thelintandunitgates are off, T1 switches them on (part B, step 1) with the first test and the code that makes it pass; every task writes its failing test/eval first (TDD) and commits only when it is green. Any install the plan needs is named in the task, so the person's yes is asked once, when that task starts. Slices the person can see. Each task is a vertical slice — a thin path through every layer the feature needs that works on its own, not "all the data first, every screen later" — and at least one of the first three tasks ends with something the person can open and see (a page, a screen, a printed result); its verify says where and what. A step thatgit revertcannot undo — sending a message or an e-mail, publishing, deleting or migrating real data, paying, opening an account — is a question to the person first, and its task says so. - List which gates must be green, which new gates or eval cases this plan adds (each with a drill), and the rollback path.
- Add a row to
docs/plans/README.md; runbash .claude/hooks/py.sh tools/context_graph.py check <file>. - Tell the owner in Georgian what will be built, in what order, and how they will see it working;
the decision is
/approve plan NNNN.
B. Executing an approved plan
- Set
status: in-progress(allowed). Work task by task, on a branch. In T1, if thelintandunitgates intools/gates/gates.tomlare both off, switch them on with the stack ADR's commands, pointed at the project's own code (not the engine'stools/):lintat once,unittogether with the first test (an empty test run proves nothing) — once that test passes, because the commit check runsunitand a red test cannot be committed. It is a protected file, so Claude Code asks the person — ask first, in one sentence saying why to say yes, and never ask them to edit it by hand. - For each task: write the test/eval and run it — see it fail — then the code →
bash .claude/hooks/py.sh tools/gates/gate.pygreen → tick the box → CHECKPOINT commit. Then go straight on to the next task in the same reply; stop only when the person is needed (a yes for an install, a protected file or a stepgit revertcannot undo; an account, a decision, or a result to look at) — never end a reply with "I'll start the next task" and wait. - If orchestration is enabled (
orchestration/config.toml): after the task's code is ready, runbash .claude/hooks/py.sh orchestration/run.py code-check --plan PLAN-NNNN --task T<n>(the owner is asked). Fix critical/high findings; at most 2 rounds — after that report open findings as UNVERIFIED. - Any change of approach → append a dated line under
## გადახრები(what and why). A change of scope → stop, reopen the plan (status only → draft) and ask the owner. - Done = every task ticked, every gate green, the
verifiersubagent returnsVERDICT: pass. Then setstatus: doneand updateplan.md/progress.md(or run/session-close), and show the result the waydocs/guides/<kind>.md§4 describes — publishing and the pilot are the person's yes. done→liveis the person's word alone: once they have seen it working and the pilot is over, they run/approve live NNNN(stage 6 — run and observe: guide §6, the spec's §6 measures; ADR-0013). Never setliveyourself; a change after that is a new/spec, never a reopened plan.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

