delegate skill
Decide whether to hand work to a subagent or child thread, and write the brief - what context to pass, what to leave out, and what to ask back. Use before launching any subagent, reviewer, or bb child thread.
- GitHub stars
- 5
- Files
- 1
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the delegate skill do?
delegate is an agent skill. Decide whether to hand work to a subagent or child thread, and write the brief - what context to pass, what to leave out, and what to ask back. Use before launching any subagent, reviewer, or bb child thread.
How to install the delegate skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the delegate skill in Plugin
/plugin marketplace add NickolasBenakis/agent-playbook /plugin install agent-playbook@agent-playbook
Install the delegate skill in Claude Code
~/.claude/skills/delegate/SKILL.md
$ npx degit NickolasBenakis/agent-playbook/skills/delegate ~/.claude/skills/delegateInstall the delegate skill in Claude Code (project)
.claude/skills/delegate/SKILL.md
$ npx degit NickolasBenakis/agent-playbook/skills/delegate .claude/skills/delegateInstall the delegate skill in Codex
~/.agents/skills/delegate/SKILL.md
$ npx degit NickolasBenakis/agent-playbook/skills/delegate ~/.agents/skills/delegateInstall the delegate skill in Gemini CLI
~/.gemini/skills/delegate/SKILL.md
$ npx degit NickolasBenakis/agent-playbook/skills/delegate ~/.gemini/skills/delegateInstall the delegate skill in Claude.ai
npx degit NickolasBenakis/agent-playbook/skills/delegate delegate && zip -r delegate.zip delegate # claude.ai → Customize → Skills → + → Create skill → Upload a skill → delegate.zip
SKILL.md
View on GitHubDelegate
A helper knows only what you put in the brief, and you get back only its summary. Both handoffs lose detail. Delegate when that loss buys something: time, a clean context, or an unbiased opinion.
Pick the vehicle
| Need | Use | Why |
|---|---|---|
| Find something across many files | an Explore/read-only subagent | you keep its conclusion, not the file dumps |
| A second opinion on a diff | playbook-reviewer with the criteria and a diff file |
it can't be anchored on your reasoning |
| Several independent reads or reviews | parallel subagents in one message | cheap; they finish together |
| Read-only work over 3+ separate areas, too much to read yourself | one subagent per area, launched together | you keep conclusions, not dumps |
| Independent builds that each run 10+ minutes of agent time | a child thread or worktree subagent per build | only then does parallel time beat start-up cost |
| A small build (most fixes take this model 1–2 min), or one that shares files with yours | do it yourself | the handoff costs more than the work |
Two builds that touch the same files are one task: give them to one agent.
The brief
Write it as if for a capable colleague who just walked in:
- Goal and finish line, as checks ("
npm testpasses,GET /x?page=2returns the second page"). - Pointers, not payloads: file paths with line ranges, the commands to run, the branch to start from. Don't paste file contents or the chat.
- What's settled: decisions already made, approaches ruled out and why, so it doesn't redo them.
- What to reuse: existing helpers, tables, patterns and test setup, by path. Children that weren't told reinvented existing code.
- Constraints: scope limits, and the playbook rules that bite here (Decisions, secrets, no push to the default branch).
- What to return: at most ~15 lines: the result, the evidence (command and its outcome), Decisions, open questions. Diffs as a branch or file path, not inline.
Never put secret values in a brief; name the variable.
For a verifier or reviewer, pass the task and the artifact only, not your hypothesis or your reasons: a helper handed a conclusion tends to confirm it.
When it comes back
A summary can be confidently wrong. Re-run the finish-line check yourself before you report the work as done, and read the diff of anything you will put your name on.
Files in this skill
1delegate skill questions
How do I install the delegate skill in Claude Code?
Run npx degit NickolasBenakis/agent-playbook/skills/delegate ~/.claude/skills/delegate. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the delegate skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.