subagent-delegation · sammcj — Claude Code skill: what it does, how to install
subagent-delegation guides Claude Code in scoping sub-tasks, assigning file ownership, and choosing between clean named sub-agents or session forks.
Apache-2.0 ★ 173 updated 2026-10-24
npx skills add sammcj/agentic-coding --skill subagent-delegation -a claude-codeWhat subagent-delegation does
The skill provides rules for delegating work via the Agent tool. It requires setting strict file ownership per worker, preventing concurrent sub-agents from overwriting shared code. Instructions must tell sub-agents they are one of several workers and request only key findings in return.
It establishes named sub-agents as the default choice because they operate in an isolated context window. Forking clones the entire conversation history, system prompt, and tools. Forking code reviews or premise checks will fail because the fork inherits the main session's bias.
For basic tasks that skip heavy reasoning, the instructions allow switching to the sonnet model. When a forked agent needs to touch project files speculatively, the skill enforces isolation: "worktree" so edits stay in an isolated git worktree.
What it helps with
- Enforce file boundaries across concurrent agents
- Select between isolated named agents and session forks
- Keep speculative code edits inside a separate git worktree
- Formulate concise briefs with explicit success criteria
Example prompts for the agent
- Delegate backend and frontend refactoring across two sub-agents with strict file boundaries
- Spawn a session fork with worktree isolation to test an alternative architecture
- Run background research using a named sub-agent with its own fresh context
How to install subagent-delegation
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill subagent-delegation -a claude-code2Manually: put the files in place
~/.claude/skills/subagent-delegation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/subagent-delegation/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill subagent-delegation -a codex2Manually: put the files in place
.agents/skills/subagent-delegation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill subagent-delegation -a cursor2Manually: put the files in place
.cursor/skills/subagent-delegation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sammcj/agentic-coding Skills/subagent-delegation/SKILL.md2Manually: put the files in place
.github/skills/subagent-delegation/SKILL.md1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill subagent-delegation -a gemini-cli2Platform CLI
gemini skills install https://github.com/sammcj/agentic-coding --path Skills/subagent-delegationManually: put the files in place
.devin/skills/subagent-delegation/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about subagent-delegation
How to install subagent-delegation in Claude Code?
Run npx skills add sammcj/agentic-coding --skill subagent-delegation -a claude-code or save the skill file to ~/.claude/skills/subagent-delegation/SKILL.md.
What does subagent-delegation do?
It outlines how to brief helper agents, prevent file conflicts, pick suitable models, and decide when session forking is appropriate.
When is a session fork the wrong choice?
Never fork code review or premise verification. The forked agent brings along the session's prior assumptions, losing the objective adversarial perspective needed for audits.
Source text
SKILL.md · Apache-2.0
--- name: subagent-delegation description: How to scope, brief and choose sub-agents when delegating work with the Agent tool - named vs forked agents, file ownership boundaries, model selection, and when a fork is the wrong choice. Use when delegating to one or more sub-agents, deciding between a named agent and a fork, or splitting parallel work across agents. --- # Sub-agent delegation Delegation is authorised standingly (see CLAUDE.md). This skill covers how to do it well. ## Briefing a sub-agent - Instruct them to return only key information - Define clear boundaries per agent. Specify which files each agent owns - Include "you are one of several agents" in instructions - Set explicit success criteria. Combine small updates to prevent over-splitting - Sub-agents can compete and erase each other's changes - ensure no overlap - If the task is simple and does not require careful consideration, reasoning or creativity (for example summarising simple web searches) you may use the sonnet model ## Named vs forked **Named** (standard) sub-agents have their own context window - good for parallel research, inspection, or separate features. Default to a named sub-agent. A **fork** inherits the main session's full conversation history, system prompt, tools, and model. Output isolation is preserved (only the final result returns) but input isolation is lost. Fork only when the accumulated nuance of the main conversation is genuinely useful to the subtask AND the task doesn't benefit from a fresh perspective. - Never fork code review, premise-checking, or any task that needs an adversarial reading - the fork inherits its own bias along with its context - Fork suits: parallel design variations that must respect prior decisions, MCP queries whose answer depends on session context, multi-step tangents you'd otherwise need to recap - Pass `isolation: "worktree"` when a fork will edit files speculatively, so its changes land in a separate git worktree instead of the working tree
© sammcj · Apache-2.0 · sammcj/agentic-coding
Similar skills
All skills for Agent setup: memory, context, orchestration →subagent-delegation by other authors comes first.