worker
Skill3 starsChanged 4 days agoUnlicenseView on GitHub
Choose the workers this session delegates to. Usage /worker [claude-light | claude | hybrid-light [fast|ultrafast] | hybrid [fast|ultrafast] | codex-light [fast|ultrafast] | codex [fast|ultrafast] | codex-max [fast|ultrafast] | none], default hybrid.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- AJschoons/robowrighttheir own version, first seen Nov 8, 2026
- lza6/claw-code-tingfengtheir own version, first seen Nov 1, 2026
- Rhovian/nilestheir own version, first seen Nov 1, 2026
- cill-i-am/skillstheir own version, first seen Oct 20, 2026
- itoflow/skillstheir own version, first seen Oct 17, 2026
- VJDiPaola/skill-forgetheir own version, first seen Oct 11, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- Yeachan-Heo/oh-my-codex★ 34ksame name
- HazAT/pi-config★ 451same name
- lza6/claw-code-tingfeng★ 5same name
- Rhovian/niles★ 4same name
- AJschoons/robowright★ 1same name
- cill-i-am/skills★ 1same name
- itoflow/skills★ 1same name
- ahmedmango/claude-colony★ 0same name
- ngothanhthien/claude-skills★ 0same name
- stotihv/skills★ 0same name
1 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
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 10 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 36
If a worker fails, report it.
- Very specific: line 44
Run codex with the scripts in .claude/skills/worker/scripts/, using the repo .venv Python.
- Very specific: line 47
Write each task to <WORK>/prompt.txt.
- Very specific: line 50
Add --workroot <DIR> when codex must work outside the repo root, such as in a worktree.
- Distinctive: line 51
Never give one work dir to two waiters, and never stop a waiter's background task: that also kills the codex runs it started.
“Common” is measured: kept by at least 6 in 10 of the 10 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
Worker routing
Until the session ends, delegate work by the column this invocation selects. The latest /worker wins, and a routing table the user gives in the session replaces this one until the next /worker.
/workeror/worker hybrid: thehybridcolumn./worker claude-light: theclaude-lightcolumn./worker claude: theclaudecolumn./worker hybrid-light: thehybrid-lightcolumn./worker codex-light: thecodex-lightcolumn./worker codex: thecodexcolumn./worker codex-max: thecodex-maxcolumn./worker none: start no workers, Claude or GPT, and do all the work yourself. Workers already running finish; take their results.
fast or ultrafast after hybrid-light, hybrid, codex-light, codex or codex-max puts that column's GPT workers on service tier priority or ultrafast. Otherwise, and in both claude columns, GPT workers run at standard speed.
| Work | claude-light | claude | hybrid-light | hybrid | codex-light | codex | codex-max |
| Hard: a bug of unknown cause, a design or architecture decision, a change across several modules, a change that is hard to undo (security, auth, payments, data migration) | opus xhigh | opus max | opus xhigh | opus max | astra max | astra max | astra max |
| Writing or changing code, tests or documents | opus high | opus xhigh | sol max | astra max | sol max | astra max | astra max |
| Deep review of an important change | opus high | opus xhigh | opus high | opus xhigh | sol max | astra max | astra max |
| Web search; research in external documents or open source | opus medium | opus high | sol max | sol max | sol max | sol max | astra max |
| General: the scope is set and judgment stays inside it. Reproduction, simple diagnosis, routine review and checks | opus medium | opus high | sol max | sol max | sol max | sol max | astra max |
| Simple: nothing to interpret. Finding, reading, listing; running tests and reporting the result; a spelled-out edit in one or two files; mechanical repetition | opus medium | opus medium | sol max | sol max | sol max | sol max | astra max |
| Computer Use, one such worker at a time | sol max | sol max | sol max | sol max | sol max | sol max | astra max |
opus is a Claude subagent; astra (gpt-6-astra) and sol (gpt-6.1-sol) run through codex. Computer Use is the exception in every column: it always runs through codex.
Whenever you can, split work across workers and run them in parallel; parallelize only tasks that can run side by side without trouble.
If a worker fails, report it; do not quietly hand its work to a different worker or do it yourself. Trying the same worker again is fine.
Claude workers
Spawn with the Agent tool: subagent_type: worker-effort-<effort>, model: opus.
GPT workers
Run codex with the scripts in .claude/skills/worker/scripts/, using the repo .venv Python.
new_workdir.py [COUNT]prints COUNT new work dirs.- Write each task to
<WORK>/prompt.txt. For a JSON result, add<WORK>/schema.json. - Hand the work dirs to one waiter in the background (
run_in_background: true):wait_codex.py --model <astra|sol> --effort <effort> [--service-tier <tier>] <WORK>...Add--workroot <DIR>when codex must work outside the repo root, such as in a worktree. Add--cap N(runs at once, default 64),--launch-gap S(seconds between starts) or--retries N(fresh restarts of a run that failed for good) when the user asks for them. Never give one work dir to two waiters, and never stop a waiter's background task: that also kills the codex runs it started. To act on each run as it ends, give each its own waiter. - Act on the summary:
OK <file>: codex's final message.FAILED <WORK> <kind>: report it; do not rerun blindly.STALLED <WORK> <minutes>: report it; never kill codex for being slow. The same command waits another round.RUNNING/QUEUED: the same command continues the batch. After a usage limit, rerun it once the reset time shown has passed.
- To answer a worker's question or give it follow-up instructions, write them to
<WORK>/reply.txtand run the waiter on that work dir again. The run continues in the same codex session.
The waiter makes schema.json strict (additionalProperties: false, every property required). Avoid what it cannot fix: a non-object root, allOf/not/if/then/else/dependentRequired/dependentSchemas, and maps (use arrays of key/value objects).
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.

