run-stage
Skill7 starsChanged 16 days agoApache-2.0View on GitHub
Launch one stage of a run as a role session with its stored assignment. Use when the manager starts the next stage or an ad-hoc one.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- mcmespinaa/folder-structure-protocoltheir own version, first seen Jun 12, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- mcmespinaa/folder-structure-protocol★ 6same 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 repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- docs/llms.txtllms.txt
- adrSkill
- agent-evalSkill
- agent-security-hardeningSkill
- agent-self-evaluationSkill
- checkpointSkill
- commit-styleSkill
- conventional-commit-reviewSkill
- councilSkill
- cpp-coding-standardsSkill
- cpp-testingSkill
- doc-gardeningSkill
- docs-governanceSkill
- escalateSkill
- eval-harnessSkill
- handoffSkill
- intakeSkill
- loop-tickSkill
- new-role-typeSkill
- postgres-patternsSkill
- python-patternsSkill
- python-testingSkill
- releaseSkill
- resume-stageSkill
- running-specagent-pipelinesSkill
- specSkill
- wiki-ingestSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Very specific: line 13
Read what the stage builds on: the brief.
- Distinctive: line 15
Leave nothing out because the type's instruction covers it.
- Distinctive: line 17
Read the draft as the session will: with only this text, the brief and its instruction, would a capable agent do the job as well as it can …
- Very specific: line 24
Update HANDOFF.md with the handoff skill.
- Very specific: line 27
Never paste prompt.md into the conversation, never start a session with claude yourself (only harness launch does.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Run a stage
Arguments: $0 = run id, $1 = stage id.
uv run harness status --run $0 --stage $1printsready, orno_assignmentfor a stage that has none yet. If it printsblocked-by:<stage>orlocked, stop and tell the human.- Write the assignment, unless the stage has one. A role session is a subagent in everything but the way it is started: it knows its type's instruction and the brief, and nothing of what you know about this run. Write for it exactly what you would write into the prompt of a subagent you were about to send to do this job, and then give that text to the role session instead.
- Read what the stage builds on: the brief; the outputs of the stages it depends on (
stages/<dep>/output/, andresult.jsonwith itsopen_questions); the human's decisions and answered escalations. - Copy
templates/stage-assignment.mdto<runs root>/$0/assignments/drafts/$1.mdand fill it. Goal: who uses the output next and what they must be able to do with it without asking. Known: what is settled or ruled out. Deliver: every deliverable and how exact it has to be, down to the level of detail at which the next session decides nothing itself. Prove: what is shown by running it or by opening the source (the trial, the probes, the commands, the inputs at the edges, the check before finishing). Hard parts: where a quick answer would look right and be wrong in this run. Done when: what makes the stage finished. - Leave nothing out because the type's instruction covers it. The instruction says how the type works in any run; the assignment says what this run needs, as exactly as you know it.
- Do not cut the material: the harness chooses it by script at launch (the stage's inputs, the brief's material, every place the stage's texts cite as
path:linewith the piece that holds it, the short files they name, what matches the brief) and gives it in the session's cached system prompt. Write every place you know aspath:linewhere the assignment needs it. Use the optionalMaterialonly for a piece that no text of the stage points to.uv run harness material --run $0 --stage $1shows the choice without a model, for when the human asks. - Read the draft as the session will: with only this text, the brief and its instruction, would a capable agent do the job as well as it can be done? Whatever the answer rests on that you know and did not write, write.
- For a reviewing type (verifier, critic, validator, test-verifier, comparator, judge) the assignment names nothing its row in
docs/roles/need-to-know.yamlhides: not who made the work, not what another reviewer found, not the budget, not a model. uv run harness assign --run $0 --stage $1stores the draft.thin_assignmentnames what is missing: write it and store again. The shards of aparallel: per_taskstage share one assignment.
- Read what the stage builds on: the brief; the outputs of the stages it depends on (
uv run harness material --run $0 --stage $1shows what the session will have.does_not_fitmust be empty: split the stage or narrow the assignment,launchrefuses it otherwise. For every file undernot_text(an image, a PDF) the assignment says what the session has to look for in it.uv run harness launch --run $0 --stage $1prints one JSON line withsession_idandjob_id(bg mode; the session id is the one Claude Code assigned to the background session, read back fromclaude agents) orcheckpointed/print_failedwith the exit code and stderr (print mode; the gate runs at the next poll); for aparallel: per_taskstage it splits the planner'stasks.jsonand prints one entry per shard inlaunched[](--shard Nrelaunches a single shard). If it printsno_assignment, go back to step 2. If it printsconfig_changed, stop and tell the human (just refreezeafter their review). If it printsalready_launched, the unit exists: use the resume-stage skill and never launch it again. If it printsin_rework, the unit answers a loop: use the resume-stage skill with--rework. Run exactly this command: it is listed insandbox.excludedCommands, so the session it starts is not created inside the sandbox.claude agents --json --all --cwd ${CLAUDE_PROJECT_DIR}must show a row whosesessionIdequals each printedsession_id(bg mode; a finished print unit has no row). If a row is missing, runuv run harness poll --run $0and follow its actions; never launch the unit again.- Start
uv run harness watch --run $0as a background command (Bash withrun_in_background). It stays in the terminal's task list while the role sessions work, prints every status change, and ends when the run needs you: a gate passed, a question was filed, a unit stopped. Its output is the list of actions, the same oneharness pollprints. Do not poll in a loop yourself. The status line shows every running role session in the meantime. - Update
HANDOFF.mdwith thehandoffskill. - Reply to the human in two lines: what was launched, and that you will come back when the watcher ends.
Never paste prompt.md into the conversation, never start a session with claude yourself (only harness launch does; claude agents is read-only), never launch a stage whose dependencies have not passed their gate, and never launch a stage on the brief alone.
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.

