Skip to main content
skill CX Codex

subagent-delegation · chrisbanes — Claude Code skill: what it does, how to install

The subagent-delegation skill for Claude Code manages subagent task distribution and reassignment. It runs when the user invokes the playbook or explicitly requests delegation.

Apache-2.0 123 installs ★ 1,164 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add chrisbanes/skills --skill subagent-delegation -a claude-code
Open on GitHub

What subagent-delegation does

This skill orchestrates task handoffs by matching assignment requirements to subagent capabilities. It keeps architectural decisions, integration, and final acceptance under the lead agent's control while parallelizing worker tasks. Each assigned agent receives a standalone brief defining their scope and task dependencies.

Use this when delegating work requires defined boundaries or independent auditing. The skill does not automate assignments without a direct command. Successful delegation requires providing clear acceptance criteria and verification expectations for the delegated agent.

What it helps with

  • Distribute tasks among multiple agents
  • Match agent capabilities to specific task requirements
  • Perform independent audits of delegated work
  • Isolate execution of independent code segments

Example prompts for the agent

  • Use subagent-delegation to prepare a task brief
  • Delegate module refactoring using subagent-delegation rules

How to install subagent-delegation

1Skills CLI (Vercel)

npx skills add chrisbanes/skills --skill subagent-delegation -a claude-code

2Manually: put the files in place

~/.claude/skills/subagent-delegation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/subagent-delegation/

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 the command npx skills add chrisbanes/skills --skill subagent-delegation -a claude-code in your terminal.

What does subagent-delegation do?

It provides a framework for handing off tasks, setting up agent briefs, and verifying completed work.

What is required to run subagent-delegation?

It requires specific task definitions and the lead agent to verify completion evidence before accepting the work.

Source text

SKILL.md · Apache-2.0
---
name: subagent-delegation
description: Use when the user invokes the subagent delegation playbook, or the user's instructions direct its use when delegating work or deciding whether to delegate.
---

# Subagent delegation

## Core principle

Match each bounded assignment to the capability and judgment it needs, while
keeping architecture, integration, authorization, and final acceptance with
the lead. Installed agent definitions are authoritative for pinned settings.

## Procedure

1. Apply this playbook when the user invokes it or the user's instructions
   direct its use for delegation; either covers delegation and reassignment
   throughout the current task. Without either, a generic request to implement
   work or use subagents does not apply it. Keep required constraints in agent
   briefs so they apply without child agents loading this skill. Loading the
   skill does not authorize implementation.
2. Prefer solo work for small or tightly coupled tasks; use delegation or
   worktrees when independent work or isolation justifies them. Leave task-graph
   execution, worktree lifecycle, integration sequencing, and implementation
   gates to the calling workflow, such as `implement-with-subagents`.
3. Choose the capability before the runtime role name: specific discovery,
   predetermined mechanical checking, implementation with self-review and
   repair ownership, or independent read-only analysis. For analysis, state
   the mode: review against requirements, or investigation of a concrete
   unresolved question. Establish concrete evidence before an investigation.
4. Load only the active runtime's reference:
   - [Codex](references/codex.md): exposed roles, installed TOML pins, model
     and effort routing, and fresh-context calls.
   - [Claude Code](references/claude-code.md): agent definitions, model and
     effort routing, invocation overrides, and owner/reviewer lifecycle.
   - Other runtimes: inspect their exposed capabilities and installed policy;
     preserve configured choices rather than translating either provider's
     model identifiers or effort values. Resolve missing required settings
     before dispatch.
5. Reassess capability and judgment for every new assignment, including
   reassignment, independently of the parent task's size or model. Keep the
   lead's model unchanged. File count, component count, or a sensitive area
   alone does not raise a tier; when judgment matters, prefer a stronger model
   at lower effort over a weaker model at higher effort. Preserve pinned
   settings and access restrictions. If required capability or settings
   are unavailable, report and resolve the mismatch before dispatch. Name the
   assignment category in the brief and justify departures from the default
   row. For investigations, name the unresolved question; for reviews,
   identify the correctness checks; for synthesis, identify the evidence or
   deliverable demands. At opus or fable (Claude Code), Sol (Codex), or an equivalent
   tier with high effort or above, make that question or those checks
   concrete; touching a risky area alone does not qualify. If work stalls,
   diagnose missing inputs, tool failures, or routine test repairs before
   considering a higher tier.
6. Give each agent a self-contained brief that fills every field of the
   [handoff brief](references/subagent-selection.md#handoff-brief). Tell
   workers they share the codebase, must preserve others' edits, and must
   accommodate concurrent changes. Further delegation
   requires the lead's explicit authority. Keep remote mutations with the
   root task holding the user's authorization, with one mutation owner.
7. Launch independent assignments in parallel. Queue work behind another agent
   only for a stated dependency, such as shared files, a contract, or ordering;
   name that dependency. Separate worktrees alone do not remove dependencies.
8. Choose independent audits proportionally to risk unless the calling
   workflow requires one. Use a fresh read-only
   reviewer without the implementation conversation. Supply original
   requirements, the plan when available, and exact review scope; require a
   `ship`, `fix-first`, or `rethink` verdict with evidence. Keep repairs with
   the original worker and context where possible; the lead may take ownership
   or explicitly reassign them.
9. Inspect delegated diffs and verification evidence before accepting the work.
   Repeat checks when evidence is incomplete or affected code changes, without
   duplicating adequate validation. Return failures to the owner for repair
   and reassess affected evidence.

## Finish gate

Finish when the lead has inspected the assigned result and its evidence,
resolved failures or reported the specific blocker, and made the acceptance
decision under the calling workflow. For advice-only requests, finish with the
assignment choices and their reasons; do not spawn agents or start execution.

© chrisbanes · Apache-2.0 · chrisbanes/skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

subagent-delegation by other authors comes first.

subagent-delegation sammcj subagent-delegation guides Claude Code in scoping sub-tasks, assigning file ownership, and choosing between clean named sub-agents or session forks. CX Codex +1 ★ 173repo stars subagent-driven-development Hermes Agent (adapted from obra/superpowers) subagent-driven-development runs an implementation plan task by task. Each task goes to a fresh subagent via delegate_task, then gets a spec review and a code quality review. CX Codex +1 106installs delegation-core athola delegation-core delegates tasks to eight external CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer). Keeps design and architecture local, sends execution out. CX Codex +1 1installs delegation Paweł Huryn delegation — a Claude Code skill for briefing subagents and assessing their reports. It applies before handing off a build, review, or research task. CX Codex +1 ★ 741repo stars competition-kerberos-delegation zhaoxuya520 competition-kerberos-delegation — a skill for Claude Code that automates Kerberos delegation analysis in CTF scenarios. It runs after context setup via $ctf-sandbox-orchestrator to verify exploitation paths. CX Codex +1 109installs delegation-audit Son Nguyen delegation-audit is a Claude Code skill that reviews which models handled each subagent type and how those assignments performed. It flags weak results, repeated failures, and possible model mismatches. CX Codex +1 ★ 1,198repo stars ak-task saltbo ak-task is a skill for creating, assigning and tracking Agent Kanban tasks through Realmroot Toolbox. It helps hand off work to an agent and monitor progress. CX Codex +1 146installs

From the same set21

The whole set →
to-plan to-plan turns one GitHub issue or an in-chat task into an implementation plan with acceptance criteria. Useful when the work has to be handed to someone else. CX Codex +1 884installs run-github-project run-github-project runs a repository's GitHub Project workflow: triages Todo, claims work in Ready to implement, and carries it through to Done. CX Codex +1 829installs implement-with-subagents implement-with-subagents orchestrates plan tasks across solo or worker subagents with task-scoped commits, integration checks, and mandatory independent review. CX Codex +1 807installs grounded-writing grounded-writing — a skill for drafting and reviewing developer docs, reports, and replies without invented facts, promotional filler, or irrelevant implementation mechanics. CX Codex +1 660installs android-benchmark-comparison android-benchmark-comparison enforces a reproducible procedure for comparing physical Android benchmark configurations. Helps resolve reversed rankings and pick measured defaults safely. CX Codex +1 559installs release-kotlin-library release-kotlin-library is a Claude Code skill that prepares, validates, and publishes Kotlin library releases. It checks changelogs and Metalava API snapshots before publication. CX Codex +1 559installs deliver-spec deliver-spec takes an approved GitHub issue or local specification and delivers it through a validated pull request. Useful when delegating implementation with mandatory independent review. CX Codex +1 359installs changelog A skill for Claude Code checks changelog entries against Git history and evidence from issues and PRs. It runs when preparing or reviewing release notes. CX Codex +1 159installs

Project sponsors

Companies that keep this analytics open