factory
Skill8 starsChanged yesterdayMITView on GitHub
Orchestrate a goal end to end (refactor, feature, cleanup batch) - split it into small PRs, delegate each to an opencode worker, get an independent review, merge on green, then run chaos on the result. Use when the user gives a goal with /factory <goal>.
- Reads credentials
19 other projects use a version of this.
Adopted by
Most recently taken up by
- shaqmughal/seekstonetheir own version, first seen Nov 15, 2026
- janrenz/factorytheir own version, first seen Nov 15, 2026
- NickolasBenakis/agent-playbooktheir own version, first seen Nov 15, 2026
- lutzseverino/repo-canontheir own version, first seen Nov 8, 2026
- momoathome/software-factorytheir own version, first seen Nov 8, 2026
- WordPress/desktop-modetheir own version, first seen Nov 2, 2026
Used with
Projects with it also use status and implement.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 3 projects that use this
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- PrimeIntellect-ai/prime-agent★ 23ksame name
- BuilderIO/skills★ 4.7ksame name
- WordPress/desktop-mode★ 280same name
- akashgit/remote-factory★ 74same name
- boston-harness-group/remote-factory★ 74same name
- shaqmughal/seekstone★ 35same name
- AirsupHQ/factory-skill★ 16same name
- NickolasBenakis/agent-playbook★ 5same name
- xavierforge/skills★ 4same name
- jaydubya818/MissionControl★ 2same name
9 more not listed
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 repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- Break ChangeSkill
- cavecrewSkill
- caveman-commitSkill
- caveman-compressSkill
- caveman-helpSkill
- caveman-reviewSkill
- cavemanSkill
- caveman-statsSkill
- Chaos MonkeySkill
- Probe FeatureSkill
- Ship ChangeSkill
- Verify Obsidian ChatSkill
- Verify PRSkill
- WorktreeSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
2
Distinctive
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
- Distinctive: line 17
Map: Read the code the goal touches.
- Very specific: line 33
Check the worker: Read the full diff yourself while the review runs.
- Very specific: line 40
Merge: Only after the user says "merge" (AGENTS.md rule 7).
- Very specific: line 45
Chaos: After the PRs merge, load @chaos-monkey and run a capped explore on the changed area with --llm opencode (explorer and miner on the …
- Distinctive: line 57
Prefer deleting code over adding layers.
“Common” is measured: kept by at least 6 in 10 of the 18 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
Factory
The goal is the argument. You are the orchestrator: you decide, write specs,
review diffs, and merge. Workers do the self-contained steps. Never spawn Claude
subagents for this; use scripts/delegate.sh (opencode, flat-rate model). It
sandboxes each run: edits only in its worktree (or only the verdict file for a
review), a shell allowlist, no web, no .env reads.
Loop
- Map. Read the code the goal touches. For a refactor, list the behaviors that must not change and find the test that pins each one. A behavior with no test gets a test first (its own PR, or step 1 of the first PR).
- Split. Cut the goal into PRs that are small enough for the review-gate
budget and independent where possible. Write the plan as a section in
NEXT.md(at the repo root, in.gitignore): one line per PR, with its witness. - Delegate. For each PR, in parallel (e2e lanes can run side by side):
npm run worktree:new -- <name> npm run delegate -- ship <name> <spec.md> "<pr title>" "<review focus>"ship= work, then the script (never the worker) pushes and opens the PR from the worker'slogs/delegate/pr-body.md, then the independent review. The shared worker rules inspec-rules.mdgo in front of every spec; the spec adds the exact files, the behavior, the witness test, and "Do not touch". A vague spec gives a vague diff. (workalone still exists.) - Check the worker. Read the full diff yourself while the review runs. Fix
small gaps yourself (then run a new
review); re-delegate large ones. - Review.
reviewposts the verdict to the PR and re-runs the Review gate. On a PASS it also setsno-behavior-change(when the verdict saysBehavior change: none) andlarge-pr(over 25src/files or 1000 added lines). The reviewer cites green CI instead of re-runningfast. Fix real notes before the merge and say which notes you did not fix and why. - Merge. Only after the user says "merge" (AGENTS.md rule 7); then merge each
PR when it is green (
gh pr merge <n> --squash). After each merge, runnpm run delegate -- update <next-pr> <name>for the next PR: it mergesmain, takesmain's feature map and fixes its refs, pushes, waits for CI, posts a re-check, and re-runs the gate. It stops on a source conflict. - Chaos. After the PRs merge, load
@chaos-monkeyand run a capped explore on the changed area with--llm opencode(explorer and miner on the subscription; only plugin replies cost money). Check every finding in code or by--replaybefore it becomes work. Real findings go toNEXT.md. - Clean up. Copy any
logs/chaos/runs from the PR worktrees to the main checkout, then remove the merged worktrees.
Rules
AGENTS.mdnon-negotiables apply to every PR: witness, counts, clips or an explicit waiver, independent verdict, merge only on "merge".- A refactor PR must not change behavior. If a test must change, stop and say why.
- Prefer deleting code over adding layers. Measure: lines removed, files touched.
- Report to the user per PR: what changed, the witness, counts, the verdict.
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.

