start
Skill4 starsChanged 14 days agoMITView on GitHub
Run red-green on one ticket or spec of this project, from worktree to fast-forward.
137 other projects use a version of this.
Adopted by
Most recently taken up by
- tatashbar/Economic-Modeling-Studiotheir own version, first seen Nov 16, 2026
- flavien-ia/hypervibe-harnesstheir own version, first seen Nov 15, 2026
- srinator22/agent-kerneltheir own version, first seen Nov 15, 2026
- librosdeia/builder-method-claude-plugintheir own version, first seen Nov 15, 2026
- willink-oss/willink-claude-kittheir own version, first seen Nov 15, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
Used with
Projects with it also use setup-engine, team-audio and 10 more.
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.
CoralGameSkillsetup-engine
Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.
Also in 13 projects that use this
CoralGameSkillteam-audio
Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.
Also in 13 projects that use this
lilangMaxSkillcreate-stories
Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
Also in 11 projects that use this
lilangMaxSkillstory-done
End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.
Also in 11 projects that use this
- +5 more from CoralGame
- +3 more from lilangMax
Other versions137 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 137
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- anthropics/knowledge-work-plugins★ 36ksame name
- openai/plugins★ 7.8ksame name
- SterlingChin/marvin-template★ 1ksame name
- educlopez/ui-craft★ 441same name
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- dsifry/metaswarm★ 432same name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- ansvisor/ansvisor★ 241same name
- alexeykrol/claude-code-starter★ 194same name
127 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.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 1 is distinctive, and 6 are very specific to this project.
0
Common
Most of the 124 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 31
Ask the user to pick and name them, proposing a tier per pick: fast a static check that reads the source without building it (lint, format …
- Very specific: line 34
Put the picks in profile.blocks.gates.gates as {name, command, tier}, for this run only: nothing is written to the project unless the user …
- Very specific: line 36
No candidate, or none picked: stop here and offer /red-green:setup.
- Very specific: line 106
Read the result (result.md) and every commit on wf/<name>.
- Very specific: line 107
Delete from the worktree each path in stray_proofs: an uncommitted proof left by the run.
- Distinctive: line 111
Run the acceptance gates on the worktree, from scratch, with a Bash timeout of 10 minutes:
- Very specific: line 129
After the fast-forward or the user's decision, and only then: remove the worktree (git worktree remove <repo>), delete every directory …
“Common” is measured: kept by at least 6 in 10 of the 124 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
Start a red-green run
You are the main thread: you prepare the run, launch it, accept it and report. The user names only the ticket.
<tools> is ${CLAUDE_PLUGIN_ROOT}, the core's checkout.
1. Inputs
target: the ticket or spec path the user named. No path given: ask for it.<name>: a short slug of the ticket's file name.<branch>: the branch the user is on;base: its HEAD.run: a fresh scratchpad directory.profile: the contents of the project's profile file.claude/red-green/profile.json, else{}(args-and-profile.md).
With a profile file, check it: node <tools>/.claude/workflows/red-green/template/render.mjs --check
.claude/red-green/profile.json. Exit 1: stop here and give the user the check's stderr and the file's path; the
worktree and the run wait for a profile that passes.
With no declared gates (profile.blocks.gates.gates absent or empty), find them here; a run refuses to start without:
- Find candidates: the repo's agent instructions, then CI config, then the task runner; the first source that names gates wins. A gate: a command CI or those instructions require before a commit; runs with no human, network or secrets; pass/fail by exit code; writes nothing to the tree.
- Ask the user to pick and name them, proposing a tier per pick:
fasta static check that reads the source without building it (lint, format check, typecheck);rounda build, a test suite, or a gate you are unsure of;acceptanceone too heavy to run each iteration. A run needs at least onefastorroundgate. - Put the picks in
profile.blocks.gates.gatesas{name, command, tier}, for this run only: nothing is written to the project unless the user asks. - No candidate, or none picked: stop here and offer
/red-green:setup.
Done when the check exits 0 (or there is no profile file), profile declares a fast or round gate, and every arg in
args-and-profile.md's required rows has a value or a step below that gives it.
2. Worktree
git worktree add ../wt-<name> -b wf/<name> <branch>. repo is its absolute path, branch is wf/<name>. Copy or
symlink into it any gitignored file the project's gates need.
Done when repo has wf/<name> checked out at base and every gitignored file the gates read is in it.
3. Baseline
Measure the fast and round gates with the runner on the worktree, with a Bash timeout of 10 minutes:
node <tools>/.claude/workflows/red-green/skills/run_gates.mjs --gates '<gates as JSON>' --dir <run> --repo <repo> --tier round --no-cache
<gates as JSON> is profile.blocks.gates.gates, its commands' placeholders filled from the args
(args-and-profile.md). Exit 3: run it again. Exit 2 or a not_run row: stop
here and give the user the reason. Each printed row's status and line become args.baseline[<gate name>]. Write
<run>/gates.json as {<gate name>: {seconds, line}} and give the user a line per gate: name, status, seconds, line.
acceptance gates are not measured at base.
Done when baseline and gates.json have an entry per fast and round gate, each with its seconds in the report.
4. Run
Pick the launch before calling. Only the session's working directory counts for a scriptPath launch, not repo or an
added directory:
<tools>inside the session's working directory:Workflow({scriptPath: '<tools>/.claude/workflows/red-green.js', args}), which reads the scripts from disk.- Any other case, a
<tools>added with/add-dirincluded:Workflow({name: 'red-green:red-green-workflow', args}), and tell the user the run uses the scripts as they were at session start.
args is {target, repo, branch, tools: '<tools>', run, base, baseline, profile} in both.
A refused launch is not retried unchanged.
<wf dir> is the transcript directory the Workflow launch result prints; it holds the run's journal.jsonl.
The run goes on in the background and never waits for the user. Watch its journal with the Monitor tool, timeout_ms
1800000:
tail -n +1 -F <wf dir>/journal.jsonl | jq -cn --unbuffered 'foreach (inputs | select(.key)) as $r ({};
if $r.type == "started" then .[$r.key] = $r.label else . end; .[$r.key] as $l
| if $r.type == "started" and $l == "implement" then ({done: true}, halt)
elif $r.type == "result" and ($l | IN("research", "plan", "replan")) then
(($r.result | objects | .questions) // []) as $q | ($q[] | {stage: $l, requirement, question, reading, cases}), {stage: $l, questions: ($q | length)}
else empty end)'Give the user each question as it lands: stage, requirement, question, and the plan's reading and cases. Tell them a
reply settles it and that, unanswered, the run keeps the reading. Implement starts after plan and any replan, so the
watch command exits there, after a {done: true} line, and the watch ends with it, even when that line is lost. A run
that fails before implement ends the watch with its result: stop the monitor then (TaskStop). Re-arm it on an earlier
expiry.
A reply, or any detail the user adds meanwhile, goes to the run's mailbox
(mailbox.md), and the run keeps going. A reply to a question is an entry to: all
whose text names the requirement.
Done when the run's result is in.
5. Accept
- Save the spans:
node <tools>/.claude/workflows/red-green/trace.mjs <wf dir> > <run>/trace.jsonl,<wf dir>as in § 4 (tracing.md). - Read the result (
result.md) and every commit onwf/<name>. - Delete from the worktree each
pathinstray_proofs: an uncommitted proof left by the run. Itsstray proofentry infailuresthen no longer counts against the fast-forward; every other entry does. Thengit status --porcelainin the worktree: acceptance measures the commit that lands, so anything left skips step 4 and stops the fast-forward; show it to the user at step 6. Run the acceptance gates on the worktree, from scratch, with a Bash timeout of 10 minutes:
node <tools>/.claude/workflows/red-green/skills/run_gates.mjs --gates '<gates as JSON>' --dir <run> --repo <repo> --tier acceptance --no-cache --baseline '<baseline as JSON>'Exit 3: run it again. Blocking: a row with status
redornot_run, or exit 2. Aknown_redrow is reported and not blocking.- Fast-forward
<branch>towf/<name>when all of these hold and the user did not ask to hold:failuresholds nothing but thestray proofentries of step 3;verdictsholds noDIEDorSILENT;leftover_findingsholds no blocking finding:severity: majororstatus: unmet. A leftover minor orunverifiedrow goes in the report and does not stop it;- step 3 left the worktree clean and step 4 found nothing blocking.
- Otherwise both branches stay. A red
acceptancegate may first be run on base: in a temporary worktree atbase, given the gitignored files the gates read, with--gatesholding that gate,--tier acceptanceand--dir <run>/base, then removed. Red there too is an old breakage, and you report it as one. Show the user the findings and wait for the choice:- accept: fast-forward as in step 5;
- fix: make the fixes on
wf/<name>in the worktree, then repeat from the status check of step 3; - new run: it takes a
<name>of its own, sincewf/<name>stays.
- After the fast-forward or the user's decision, and only then: remove the worktree (
git worktree remove <repo>), delete every directory underrun(keeping its top-level files,trace.jsonlandgates.jsonamong them), thengit worktree prune.
Done when trace.jsonl and gates.json are in run, the branch is fast-forwarded or the user has decided with the
reason in the report, run holds no directory, and the worktree is removed.
6. Report
To the user: status, the commits, the acceptance rows, the strays deleted, leftover_findings, advisory, verify_launch (checks only a person can make), the open
questions per stage, and the tokens per block from trace.mjs --table.
Done when the report names each of them, none where one is empty.
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.

