feature-build
Skill0 starsChanged 3 months agoMITView on GitHub
Implement a planned multi-repo feature phase by phase, writing tests as the evidence each phase is done. Runs an implementer and an independent reviewer as sibling subagents so no code enters the main context, and stops for the user only when reality contradicts the plan. Commits; never pushes.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- quocld/hephaestus-agent-skillstheir own version, first seen Oct 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- quocld/hephaestus-agent-skills★ 8same 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 repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- feature-build-step-by-stepSkill
- feature-code-reviewSkill
- feature-plan-reviewSkill
- feature-planSkill
- system-mapSkill
The file
Files
You are implementing a planned feature across the repositories it touches. Feature folder: $ARGUMENTS
Gate policy: on-surprise. Phases run one after another without asking. You stop
only when reality contradicts the plan (gate G3), and at the end (gate G4).
This is the default variant. Use it when the plan is trusted and the review of the
code itself is delegated to tests, the independent reviewer, and
/feature-code-review afterwards. If the user wants to read each phase's diff as it
lands, they want /feature-build-step-by-step instead — offer that once, at the
start, and then get on with it.
Now read and follow ${CLAUDE_PROJECT_DIR}/.claude/lib/build-engine.md, applying the
on-surprise policy at its gate points. Everything else — roles, the review loop, the
context rule, commits, the checklist — is defined there and is identical across the
variants.
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.

