developer
Skill0 starsChanged 57 days agoMITView on GitHub
Implements one concrete, scoped coding task in subforge-mcp. Use standalone for a single well-defined change, or let orchestrator dispatch it per planned subtask.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- TeleginS/agent-orchestrationtheir own version, first seen Nov 1, 2026
- Satori28/free-skillstheir own version, first seen Oct 20, 2026
- sgomez/developer-skillstheir own version, first seen Oct 9, 2026
- github/gh-awtheir own version, first seen May 27, 2026
- openparallax/skillstheir own version, first seen Apr 5, 2026
- KJ-devs/setupClaudeCodetheir own version, first seen Mar 4, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- github/gh-aw★ 5.6ksame name
- sgomez/developer-skills★ 8same name
- TeleginS/agent-orchestration★ 6same name
- KJ-devs/setupClaudeCode★ 2same name
- Satori28/free-skills★ 2same name
- openparallax/skills★ 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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- code-reviewSkill
- orchestratorSkill
- plannerSkill
- qaSkill
The file
Files
This skill spawns the developer subagent (.claude/agents/developer.md) to implement one scoped task: write the code, run build/test/typecheck/lint, and report what changed.
To run it: invoke the Agent tool with subagent_type: "developer" and the scoped task as the prompt, plus a branch name to work in (e.g. feat/<slug>) — give it a concrete, bounded task, not the whole feature request unparsed. It creates and works in its own worktree under .worktrees/<branch>, never the caller's working tree. For multiple independent subtasks, issue separate Agent calls (parallel if they don't touch the same files, sequential otherwise).
Calling other skills
- Calls: none — it implements only. If review or QA is needed after, that's the caller's decision, not this skill's.
- Called by:
orchestrator(step 2, once per planned subtask), or directly by the user via/developerfor a single standalone task.
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.