agent-delegation SKILL.md skillA

agent-delegation from qwenlm/qwen-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add qwenlm/qwen-code/agent-delegation@git:20260922.c650a3e

Pins git:20260922.c650a3e in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
qwenlm/qwen-code
Path
packages/core/src/skills/bundled/agent-delegation/SKILL.md
Versions recorded
1
Latest version
git:20260922.c650a3e, committed Sep 22, 2026
Size
3,393 bytes
Repository stars
29,081
License
Apache-2.0

Reference for briefing a subagent or a fork — what to put in the prompt, what not to delegate, and a worked example. Load before writing a delegation prompt; the Agent tool's own description carries the launch rules and the background-agent rules.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Delegation prompt reference

Everything below is about _writing_ the prompt. Whether to delegate at all, how
a background agent reports back, and the rules for running agents concurrently
stay in the Agent tool's description — this reference does not repeat them.

## Writing the prompt

Brief the agent like a smart colleague: make the delegated task, boundaries, and expected output explicit. Regular subagents have not seen this conversation; forks inherit all or the selected recent window.

- Explain what you're trying to accomplish and why.
- Describe what you've already learned or ruled out.
- Give enough context about the surrounding problem that the agent can make judgment calls rather than just following a narrow instruction.
- If you need a short response, say so explicitly.
- For lookups, provide the exact target. For investigations, provide the actual question rather than an over-prescribed sequence of steps.
- Provide clear, detailed prompts so the agent can work autonomously and return exactly the information you need.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add qwenlm/qwen-code/agent-delegation@sha256:e8c396feb979b0c3

The line at the top of this page pins the label git:20260922.c650a3e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ibo3h5notjcplfoe.svg)](https://markdownregistry.com/a/art_ibo3h5notjcplfoe)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 22, 2026.

versioncommittedcommitsizeaudit
git:20260922.c650a3e latest2026-09-22 c650a3e 3,393 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3393 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

qwenlm/qwen-code · 29,081 stars · license Apache-2.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ibo3h5notjcplfoe
GET https://markdownregistry.com/api/v1/resolve?ref=qwenlm/qwen-code/agent-delegation
GET https://markdownregistry.com/api/v1/blob/e8c396feb979b0c35b9aea8b22f68b5b6d0ca04873283b47f3b10a13e7f5fc89

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from qwenlm/qwen-code

agent-reproduce-align SKILL.md skill
qwenlm/qwen-code · .qwen/skills/agent-reproduce-align/SKILL.md · Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen…
git:20260602.bec97f4 · audit A · 29,081 stars
agent-reproduce-feature SKILL.md skill
qwenlm/qwen-code · .qwen/skills/agent-reproduce-feature/SKILL.md · Use when reproducing an existing Codex or Claude Code feature in Qwen Code or another agent CLI by choosing a reference…
git:20260602.bec97f4 · audit A · 29,081 stars
autofix SKILL.md skill
qwenlm/qwen-code · .qwen/skills/autofix/SKILL.md · Review and repair current local changes until they converge, or run Qwen Code Autofix issue and review workflows from…
git:20260910.67fe20a · audit A · 29,081 stars
bugfix SKILL.md skill
qwenlm/qwen-code · .qwen/skills/bugfix/SKILL.md · Fix a bug from a GitHub issue, following the reproduce-first
git:20260711.909f0fe · audit A · 29,081 stars
ci-flaky-patrol SKILL.md skill
qwenlm/qwen-code · .qwen/skills/ci-flaky-patrol/SKILL.md · Classify a bounded batch of stale PR CI failures and choose the safest response.
git:20261106.478c2f8 · audit A · 29,081 stars
codegraph SKILL.md skill
qwenlm/qwen-code · .qwen/skills/codegraph/SKILL.md · Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead…
git:20260513.fd53527 · audit A · 29,081 stars
create-issue SKILL.md skill
qwenlm/qwen-code · .qwen/skills/create-issue/SKILL.md · Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
git:20260611.4f1203b · audit A · 29,081 stars
deflake SKILL.md skill
qwenlm/qwen-code · .qwen/skills/deflake/SKILL.md · Stabilize a flaky test with a minimal, assertion-preserving fix — never by weakening or deleting the check.
git:20260719.0764276 · audit A · 29,081 stars
docs-audit-and-refresh SKILL.md skill
qwenlm/qwen-code · .qwen/skills/docs-audit-and-refresh/SKILL.md · Audit the repository's docs/ content against the current codebase,
git:20260609.30b52ec · audit A · 29,081 stars
docs-update-from-diff SKILL.md skill
qwenlm/qwen-code · .qwen/skills/docs-update-from-diff/SKILL.md · Review local code changes with git diff and update the official
git:20260609.30b52ec · audit A · 29,081 stars
e2e-testing SKILL.md skill
qwenlm/qwen-code · .qwen/skills/e2e-testing/SKILL.md · Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic…
git:20260611.4f1203b · audit A · 29,081 stars
feat-dev SKILL.md skill
qwenlm/qwen-code · .qwen/skills/feat-dev/SKILL.md · End-to-end workflow for implementing a non-trivial qwen-code
git:20260711.909f0fe · audit A · 29,081 stars

Every file in qwenlm/qwen-code

Other files named agent-delegation

agent-delegation SKILL.md skill
yeisonrestrepo/code-conductor · skills/agent-delegation/SKILL.md · Rules for when and how to spawn sub-agents: Explore for 3+ file reads, parallel agents for independent tasks, summaries…
git:20260922.8fd811c · audit A · 17 stars

Browse by kind, by grade A, or by owner.