resume-stage
Skill7 starsChanged 16 days agoApache-2.0View on GitHub
Resume a unit under its session id. Use when harness poll prints resume, rework or recheck, or an escalation is answered.
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
- 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, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Update HANDOFF.md with the handoff skill and report to the human in one line.
- Very specific: line 15
When the answer says continued as a copy <id>, Claude Code started a copy under a new session id.
≈ “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
Resume a stage
uv run harness escalations --run $0 --stage $1lists the stage's escalations and their status.uv run harness resume --run $0 --stage $1resumes the unit under its newest known session id (the manifest's, or the copy an earlier resume recorded); add--shard Nfor one shard of a sharded stage. Add--escalation $2to deliver that answer verbatim; add--message "<text>"only for an instruction the human dictated, verbatim. If it printsconfig_changed, stop and tell the human. 2a. For areworkorrecheckaction:uv run harness resume --run $0 --stage $1 --rework, without--message: the harness delivers the findings fromrework.md, or the instruction to check again after it rebuilt the stage's inputs and Material. A plain resume of such a unit is refused within_rework;round_movingmeans runuv run harness poll --run $0first;max_runsmeans the loop is over: tell the human.- The CLI chooses
claude respawn <job-id>when there is nothing to deliver and the old row is still listed asstoppedorfailed,claude --resume <session-id> --bg "<message>"otherwise, andclaude -p --resume <session-id> …for amode: printunit (run to completion; the output is processed like a first run); you do not choose. Pass themessagethatharness pollprinted for the unit (the failing gate checks, or the failed print run's error) unless the human dictated another. - Update HANDOFF.md with the
handoffskill and report to the human in one line.
When the answer says continued as a copy <id>, Claude Code started a copy under a new session id; the CLI already recorded it in state.json and poll follows it. The CLI refuses a resume above max_attempts; then you ask the human instead of retrying.
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.

