loop-tick
Skill7 starsChanged 14 days agoApache-2.0View on GitHub
Run one tick of a loop from docs/loops/<name>.yaml. Use when a schedule, the night tick or the human asks to advance a loop.
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
- new-role-typeSkill
- postgres-patternsSkill
- python-patternsSkill
- python-testingSkill
- releaseSkill
- resume-stageSkill
- running-specagent-pipelinesSkill
- run-stageSkill
- specSkill
- wiki-ingestSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Never change a loop file, its limits or its state file.
- Distinctive: line 18
If a run exists, update its HANDOFF.md with the handoff skill.
≈ “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
Tick a loop
Argument: $0 = loop name (the file docs/loops/$0.yaml).
uv run harness loop tick --name $0prints one JSON object. Act on itsactionand on nothing else:wait: the loop's last run is still active. Handle that run like any other (poll, resume, escalations, approvals). Start nothing.launch: a run was created from the loop's goal with the loop's pipeline. Launch its first stage with the run-stage skill and continue as docs/roles/MANAGER.md describes.prompt: read the printedfileand do exactly what it says in this turn.external: the loop runs in CI; there is nothing to do here.exit: the episode ended for the printedrule(success, failure, max_iterations, max_minutes, max_usd, no_progress, disabled, not_ready). Report the rule and the detail to the human in one line. For every rule except success, tell the human that the schedule should stop until someone looks.
- Never change a loop file, its limits or its state file. A human edits
docs/loops/in a pull request. - If a run exists, update its HANDOFF.md with the handoff skill.
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.