Harness Agent Team Designer
revfactory/harness
Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.
Reference for writing briefs to a subagent or a fork: what context to include, what never to delegate, and how a custom subagent's definition limits the prompt.
Install Agent Delegation Prompts
$ npx skills add QwenLM/qwen-code --skill agent-delegation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install QwenLM/qwen-code agent-delegation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/QwenLM/qwen-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/src/skills/bundled/agent-delegation .claude/skills/agent-delegation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-delegation" agent skill from https://github.com/QwenLM/qwen-code/tree/main/packages/core/src/skills/bundled/agent-delegation into .claude/skills/agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-delegation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/QwenLM/qwen-code/tree/main/packages/core/src/skills/bundled/agent-delegationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add QwenLM/qwen-code --skill agent-delegation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install QwenLM/qwen-code agent-delegation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QwenLM/qwen-code.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/core/src/skills/bundled/agent-delegation .agents/skills/agent-delegation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-delegation" agent skill from https://github.com/QwenLM/qwen-code/tree/main/packages/core/src/skills/bundled/agent-delegation into .agents/skills/agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-delegation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QwenLM/qwen-code --skill agent-delegation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install QwenLM/qwen-code agent-delegation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QwenLM/qwen-code.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/core/src/skills/bundled/agent-delegation .cursor/skills/agent-delegation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-delegation" agent skill from https://github.com/QwenLM/qwen-code/tree/main/packages/core/src/skills/bundled/agent-delegation into .cursor/skills/agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-delegation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/QwenLM/qwen-code.git --path packages/core/src/skills/bundled/agent-delegation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add QwenLM/qwen-code --skill agent-delegation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install QwenLM/qwen-code agent-delegation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QwenLM/qwen-code.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/core/src/skills/bundled/agent-delegation .gemini/skills/agent-delegation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-delegation" agent skill from https://github.com/QwenLM/qwen-code/tree/main/packages/core/src/skills/bundled/agent-delegation into .gemini/skills/agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-delegation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install QwenLM/qwen-code agent-delegationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add QwenLM/qwen-code --skill agent-delegation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/QwenLM/qwen-code.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/core/src/skills/bundled/agent-delegation .github/skills/agent-delegation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-delegation" agent skill from https://github.com/QwenLM/qwen-code/tree/main/packages/core/src/skills/bundled/agent-delegation into .github/skills/agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-delegation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QwenLM/qwen-code --skill agent-delegation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install QwenLM/qwen-code agent-delegation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/QwenLM/qwen-code.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/core/src/skills/bundled/agent-delegation .opencode/skills/agent-delegation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-delegation" agent skill from https://github.com/QwenLM/qwen-code/tree/main/packages/core/src/skills/bundled/agent-delegation into .opencode/skills/agent-delegation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-delegation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-delegation- GitHub stars
- 28k
- Token cost
- ~847 tokens
- SKILL.md length
- 481 words
- Files
- 2
- Skills in repo
- 41
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Reference for writing briefs to a subagent or a fork: what context to include, what never to delegate, and how a custom subagent's definition limits the prompt.
- Writing a prompt for a subagent that has not seen the conversation
- SKILL.md covers Writing the prompt, Writing a fork prompt and Worked example
- Runs TypeScript scripts from its folder
- Briefing a fork with limited history
What it does
The skill covers prompt writing only. Whether to delegate, how background agents report back and the rules for concurrent agents stay in the Agent tool's own description. The advice is to brief the agent like a capable colleague: explain the goal and why, say what is already known or ruled out, give enough surrounding context for judgment calls, state when a short answer is wanted, give exact targets for lookups and real questions for investigations, and say whether code should be written or only research done. Terse command-style prompts produce shallow work.
Two rules stand out. Never delegate understanding, so a prompt like fix the bug based on your findings gets replaced with file paths, constraints and scope. And a custom subagent's own definition outranks the prompt, so a prompt cannot widen its scope or tools. Fork prompts act as directives when full history is inherited and need older context added when history is limited. A worked example appears further into the skill.
When your agent uses it
- Writing a prompt for a subagent that has not seen the conversation
- Briefing a fork with limited history
- Deciding what context and boundaries a delegated task needs
- Fixing delegation prompts that produce shallow results
Example prompts
- “Write a delegation prompt for a subagent that should find every caller of the legacy auth helper, research only.”
- “Rewrite the prompt that says to fix the bug based on the findings into one that proves I understood the task.”
- “Draft a fork prompt that covers the parser module and leaves the lexer to another agent.”
- “My subagent ignored the repository search I asked for, so check its definition against my prompt.”
Requirements
- An agent runtime with subagent or fork support
What it can do on your machine
Read from SKILL.md and the folder at commit d9c6f8c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (TypeScript), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agent Delegation Prompts loads about 847 tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 481 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from QwenLM/qwen-code at commit d9c6f8c, republished under its Apache-2.0 licence (© QwenLM). 481 words, ~847 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-delegation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- agent-delegation
- description
- 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.
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.
- Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent.
Terse command-style prompts produce shallow, generic work.
Never delegate understanding. Do not write prompts like "based on your findings, fix the bug" or "based on the research, implement it." Those phrases push synthesis onto the agent instead of doing it yourself. Write prompts that prove you understood the task: include relevant file paths, constraints, what specifically needs to be learned or changed, and what is out of scope.
A custom subagent's own definition outranks your prompt. When subagent_type names a subagent someone defined, that definition already fixes its scope, its tools and its output contract; your prompt adds task context, not a new contract. Asking one confined to a single file to search the repository does not widen it — the dispatch simply cannot succeed. If the contract is too narrow for what you need, the definition is what has to change, not the prompt.
Show full SKILL.md (150 more words)Show less
Writing a fork prompt
With the default full history, the prompt is a directive — what to do, not what the situation is. When fork_turns limits history, include any older context the fork still needs. Be specific about scope: what's in, what's out, what another agent is handling.
Worked example
<example_agent_descriptions> "test-runner": use this agent after you are done writing code to run tests </example_agent_descriptions>
<example>
user: "Please write a function that checks if a number is prime"
assistant: I'm going to use the Write tool to write the following code:
<code>
function isPrime(n) {
if (n <= 1) return false
for (let i = 2; i * i <= n; i++) {
if (n % i === 0) return false
}
return true
}
</code>
<commentary>
Since a significant piece of code was written and the task was completed, now use the test-runner agent to run the tests
</commentary>
assistant: Uses the agent tool to launch the test-runner agent
</example>© QwenLM, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in packages/core/src/skills/bundled/agent-delegation of QwenLM/qwen-code.
- SKILL.md
- SKILL.test.ts
Open the folder on GitHubat commit d9c6f8c
Compare with similar skills
Agent Delegation Prompts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Delegation Prompts this skillQwenLM/qwen-code | 28k | — | ~847 | Automated safety check: Pass | Apache-2.0 | |
| Harness Agent Team Designerrevfactory/harness | 9.1k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~11k | Automated safety check: Pass | CC-BY-4.0 | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| ClawTeam Multi-Agent Swarmwin4r/ClawTeam-OpenClaw | 1.5k | 1 repos | ~2.9k | Automated safety check: Pass | MIT |
Similar skills
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
ClawTeam Multi-Agent Swarm
win4r/ClawTeam-OpenClaw
Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.
Harness Evolution Feedback Loop
revfactory/harness
Collects feedback on how an agent harness performed, generalizes it, and updates the harness agents, skills and orchestrator along with a change-history table.
More from QwenLM/qwen-code
All 41 skills in this repoAgent Feature Reproduction
QwenLM/qwen-code
Reproduces a feature from Codex or Claude Code in Qwen Code by running the reference agent under capture, reading the traces, then implementing matching behavior.
Qwen Code E2E Testing
QwenLM/qwen-code
Guides end-to-end testing of the Qwen Code CLI in headless mode with real model calls, MCP test servers and inspection of raw API traffic.
Repo Hygiene Scan and Fix
QwenLM/qwen-code
Scheduled CI skill that scans a repository for small, certain docs, test and code hygiene issues and fixes them on one branch with a commit per finding.
Qwen Code Desktop Brand Builder
QwenLM/qwen-code
Builds a rebranded Qwen Code desktop package from the Tauri shell using only a brand id and a logo, with sensible derived defaults.
Qwen Code Memory Leak Debugger
QwenLM/qwen-code
Walks through capturing and comparing V8 heap snapshots to find memory leaks in the Qwen Code Node.js CLI, using tmux and the chrome-devtools CLI.
tmux Real User Testing
QwenLM/qwen-code
Drives Qwen Code in a real tmux session the way a user would and saves a readable step-by-step transcript of each screen for maintainers to review.
Related
Categories
Questions about Agent Delegation Prompts
What does Agent Delegation Prompts do?
Reference for writing briefs to a subagent or a fork: what context to include, what never to delegate, and how a custom subagent's definition limits the prompt. The skill covers prompt writing only. Whether to delegate, how background agents report back and the rules for concurrent agents stay in the Agent tool's own description.
When should I use Agent Delegation Prompts?
Agent Delegation Prompts fits situations like: writing a prompt for a subagent that has not seen the conversation; briefing a fork with limited history; deciding what context and boundaries a delegated task needs; fixing delegation prompts that produce shallow results.
How do I install Agent Delegation Prompts in Claude Code?
Run `npx skills add QwenLM/qwen-code --skill agent-delegation -a claude-code`. Or copy the skill folder (packages/core/src/skills/bundled/agent-delegation in QwenLM/qwen-code) into .claude/skills/agent-delegation in your project. Claude Code loads it when a task matches its description.
How do I install Agent Delegation Prompts in Codex?
Run `npx skills add QwenLM/qwen-code --skill agent-delegation -a codex`. Or copy the skill folder (packages/core/src/skills/bundled/agent-delegation in QwenLM/qwen-code) into .agents/skills/agent-delegation in your project. Codex loads it when a task matches its description.
Can I use Agent Delegation Prompts in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add QwenLM/qwen-code --skill agent-delegation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-delegation, .gemini/skills/agent-delegation, .github/skills/agent-delegation and .opencode/skills/agent-delegation in your project.
What does Agent Delegation Prompts need to run?
Going by SKILL.md and its folder, Agent Delegation Prompts needs TypeScript for the scripts in its folder. Our summary lists: An agent runtime with subagent or fork support.
Does Agent Delegation Prompts access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Agent Delegation Prompts safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Agent Delegation Prompts use?
Agent Delegation Prompts is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Delegation Prompts use?
About 847 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Agent Delegation Prompts?
Skills that share tags, products or a category with Agent Delegation Prompts: Harness Agent Team Designer (revfactory/harness, 9.1k stars), Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), Task Observer (rebelytics/one-skill-to-rule-them-all, 3.2k stars) and O2 Review Loop (openobserve/openobserve, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Delegation Prompts?
QwenLM (a GitHub organization) maintains it in QwenLM/qwen-code, which has 28,410 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 11, 2026.
Source: QwenLM/qwen-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.