autonomous-feature
Skill3 starsChanged 49 days agoMITView on GitHub
Autonomously develop a repository feature from a high-level idea. Codex independently enhances the idea, proposes a detailed plan, and reviews the implementation while Claude reconciles requirements, implements, verifies, triages findings, and fixes valid issues. Use when the user delegates an end-to-end feature change.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- quaat/autonomous-developmentword for word, first seen Sep 24, 2026
Other versions1 project uses a version of this.
Word for word · 1
- quaat/autonomous-development★ 3100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository11 other files it gives its agents.
- adversarial-reviewSkill
- autonomous-currentSkill
- autonomous-mainSkill
- autonomous-statusSkill
- codex-reviewSkill
- enhance-ideaSkill
- fix-findingsSkill
- implementation-planSkill
- implement-planSkill
- review-existing-prSkill
- verify-featureSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 36
Use ultrathink for architecture, compatibility, and review triage.
- Distinctive: line 43
Never push, merge, publish, deploy, rotate credentials, or modify remote infrastructure.
- Very specific: line 44
Never use danger-full-access, --yolo, bypassPermissions, or equivalent unrestricted modes.
- Distinctive: line 45
Never apply an irreversible database migration or delete user data.
- Distinctive: line 46
Do not weaken authorization, validation, tests, or static checks to make the workflow pass.
- Distinctive: line 48
Use no more than the configured review-round budget.
- Distinctive: line 49
Treat every Codex finding as a proposal requiring evidence-based triage.
- Distinctive: line 50
Do not create commits unless the user explicitly requested them.
- Very specific: line 96
Do not declare success until evaluate succeeds:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Autonomous feature development
Implement this feature idea:
$ARGUMENTS
Use ultrathink for architecture, compatibility, and review triage. Operate as a state-machine
driver: ask the controller what to do next, execute that phase, repeat. Detailed per-phase guidance
lives in references/ and is loaded only when a phase needs it.
Non-negotiable boundaries
- Preserve unrelated user changes.
- Never push, merge, publish, deploy, rotate credentials, or modify remote infrastructure.
- Never use
danger-full-access,--yolo,bypassPermissions, or equivalent unrestricted modes. - Never apply an irreversible database migration or delete user data.
- Do not weaken authorization, validation, tests, or static checks to make the workflow pass.
- Codex planning and review executions must remain read-only.
- Use no more than the configured review-round budget.
- Treat every Codex finding as a proposal requiring evidence-based triage.
- Do not create commits unless the user explicitly requested them.
Driver loop
- Confirm this is a Git repository. Inspect
CLAUDE.md, repository instructions, architecture, status, and tests. UseEnterWorktreefor an isolated worktree whenever available — mandatory when the starting worktree has uncommitted changes. If the user explicitly asks for current-checkout mode, stay in the current branch instead of entering a worktree, and require a clean feature branch before proceeding. Initialize:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/controller.py" doctor python3 "${CLAUDE_PLUGIN_ROOT}/scripts/controller.py" init --feature "$ARGUMENTS" --mode auto --worktree-mode isolatedinitprints therun-state.jsonpath and run ID. With multiple concurrent runs, pass--run-id <run-id>to all subsequent commands. Ifdoctorreports a missing prerequisite, mark the run blocked and report it rather than bypassing it.For current-checkout mode, do not call
EnterWorktree. Instead, keep the current branch checked out and run:python3 "${CLAUDE_PLUGIN_ROOT}/scripts/controller.py" init --feature "$ARGUMENTS" --mode auto --worktree-mode currentThe controller refuses
main/masterunless the user also passes--allow-main, and it refuses a dirty tree in current-checkout mode.Repeatedly ask the controller for the next phase, then execute it:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/controller.py" next-action --jsonThe response gives
phase,required_action,completion_condition, andreferences. Read the referenced file underreferences/for that phase and follow it until the completion condition holds. Phase references:references/specification.md— produce the accepted spec.references/planning.md— produce the accepted plan and set the risk gate.references/implementation.md— implement the plan.references/verification.md— run and record checks.references/review.md— Codex review, triage, and adversarial review.
Do not declare success until
evaluatesucceeds:python3 "${CLAUDE_PLUGIN_ROOT}/scripts/controller.py" evaluate python3 "${CLAUDE_PLUGIN_ROOT}/scripts/controller.py" status python3 "${CLAUDE_PLUGIN_ROOT}/scripts/controller.py" usage-report
Final report
- the implemented behavior;
- principal files changed;
- verification commands and results;
- Codex review rounds and disposition of findings;
- adversarial review result when required;
- per-phase usage table from
usage-report; - remaining risks or explicit blocked reason;
- a suggested conventional commit message.
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.

