bringing-coworker
Skill5 starsChanged 55 days agoMITView on GitHub
Use from an in-progress dispatched worker when the user asks to pull in a colleague, or a rule requires a second-agent review.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-feedbackSkill
- asking-peer-agentsSkill
- boss-assistantSkill
- boss-saySkill
- choosing-graphSkill
- contacting-orchestratorsSkill
- create-great-harnessSkill
- dispatching-workSkill
- handoff-orchestratorSkill
- i-am-orchestratorSkill
- initSkill
- notifying-main-agentSkill
- peeking-workSkill
- reporting-to-userSkill
- resolving-appSkill
- shipping-taskSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Use your canonical instruction path from the dispatch contract:
≈ “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
Bring a coworker
A coworker is one interactive agent you bring into your own Herdr tab and worktree for a second opinion or file-disjoint support. You integrate its result, and coworker nesting stops at this one level.
1. Scope the second opinion
Give the coworker one outcome that can run beside your current task.
Default to review-only.
A writing task names a disjoint repo-relative --writable-path scope.
Complete when the task is independently useful and its write scope is disjoint.
2. Start beside you
Use your canonical instruction path from the dispatch contract:
uv run --script "$HOME/.straw-boss/bin/run-straw-boss-script.py" \
--origin-root "${CLAUDE_PLUGIN_ROOT:-$PWD}" --prefer-installed \
--script dispatch-coworker.py -- \
--parent-instruction-path <your-instruction-path> \
--slug <unique-slug> [--name <short-name>] \
--agent-kind claude|codex|agy --task "<user requirement and integrated context>" \
[--writable-path <repo-relative-path>]...The command authenticates your session, opens the coworker in this tab and worktree, injects its contract, and confirms delivery.
Omit --name for a <app>-coworker handle derived automatically.
Complete when it returns the coworker's pane and instruction path.
3. Work with the user
Point the user to the coworker pane. The coworker and user decide feedback and choose the specification, design, implementation, and the verification method inside the anchor you scoped for it; continue on your disjoint scope.
Complete when the coworker reports done or failed; parent and root coordinator receive that terminal event automatically.
4. Integrate and close
Integrate the reported result, then use dispatching-work wrap-up for the coworker instruction. The shared tab and your own instruction remain active.
Complete when the pane is closed and the coworker instruction is archived, before your own done or failed report.
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.