Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Delegate one complex task to a single subagent, review its work in two stages before merging back.
Install Delegate Task
$ npx skills add danielvm-git/bigpowers --skill delegate-task -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install danielvm-git/bigpowers delegate-task --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/danielvm-git/bigpowers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/delegate-task .claude/skills/delegate-task && 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 "delegate-task" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/delegate-task into .claude/skills/delegate-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "delegate-task", 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/danielvm-git/bigpowers/tree/main/skills/delegate-taskType 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 danielvm-git/bigpowers --skill delegate-task -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install danielvm-git/bigpowers delegate-task --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/delegate-task .agents/skills/delegate-task && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "delegate-task" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/delegate-task into .agents/skills/delegate-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "delegate-task", 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 danielvm-git/bigpowers --skill delegate-task -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install danielvm-git/bigpowers delegate-task --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/delegate-task .cursor/skills/delegate-task && 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 "delegate-task" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/delegate-task into .cursor/skills/delegate-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "delegate-task", 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/danielvm-git/bigpowers.git --path skills/delegate-task--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 danielvm-git/bigpowers --skill delegate-task -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install danielvm-git/bigpowers delegate-task --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/delegate-task .gemini/skills/delegate-task && 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 "delegate-task" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/delegate-task into .gemini/skills/delegate-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "delegate-task", 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 danielvm-git/bigpowers delegate-taskInstalls 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 danielvm-git/bigpowers --skill delegate-task -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/delegate-task .github/skills/delegate-task && 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 "delegate-task" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/delegate-task into .github/skills/delegate-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "delegate-task", 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 danielvm-git/bigpowers --skill delegate-task -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install danielvm-git/bigpowers delegate-task --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/danielvm-git/bigpowers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/delegate-task .opencode/skills/delegate-task && 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 "delegate-task" agent skill from https://github.com/danielvm-git/bigpowers/tree/main/skills/delegate-task into .opencode/skills/delegate-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "delegate-task", 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
delegate-task- GitHub stars
- 256
- Token cost
- ~961 tokens
- SKILL.md length
- 412 words
- Files
- 1
- Skills in repo
- 39
- Repo updated
- First seen
- Licence
- MIT
At a glance
Delegate one complex task to a single subagent, review its work in two stages before merging back.
- Works in 5 steps: Define the task → Spawn the subagent (iterative retrieval,… → Stage 1 review — output inspection → …
- A task is complex and requires careful review before the result is accepted
- SKILL.md covers Subagent depth tiers (e45s30) and Process
- Calls git
What it does
Delegate Task is an agent skill from danielvm-git/bigpowers. Delegate one complex task to a single subagent, review its work in two stages before merging back. Sequential — one agent at a time, with oversight. Use when a task is complex and requires careful review before the result is accepted. Distinct from dispatch-agents (no parallelism here; reviewer sees full diff before proceeding).
Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents. The repository describes itself as: Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers. The licence is MIT.
When your agent uses it
- A task is complex and requires careful review before the result is accepted
- Tasks that involve Subagents
Example prompts
- “/delegate-task”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 812d57a. 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
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Delegate Task loads about 961 tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 412 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 danielvm-git/bigpowers at commit 812d57a, republished under its MIT licence (© danielvm-git). 412 words, ~961 tokens.
Download SKILL.mdSave it as
.claude/skills/delegate-task/SKILL.md (or your agent's skills folder).- name
- delegate-task
- description
- Delegate one complex task to a single subagent, review its work in two stages before merging back. Sequential — one agent at a time, with oversight. Use when a task is complex and requires careful review before the result is accepted. Distinct from dispatch-agents (no parallelism here; reviewer sees full diff before proceeding).
- model
- sonnet
- effort
- standard
story: e45s30
Delegate Task
HARD GATE — HARD GATE — Delegated work must have clear success criteria and verification commands. The delegate must be able to verify completion independently.
Delegate a single complex task to a subagent with a two-stage review gate before accepting the result. Use when oversight of a single task matters more than speed.
Distinct from dispatch-agents: This skill runs one subagent sequentially with a mandatory review. dispatch-agents runs multiple subagents in parallel without inter-task review gates.
Subagent depth tiers (e45s30)
Select brief depth from task risk: and skill effort: before spawning:
| Tier | When | Brief includes |
|---|---|---|
full_maturity | P0 stories, multi-file refactors, security work | Full template + CONVENTIONS excerpts + threat model if present |
standard | Default implementation tasks | Goal, scope, out-of-bounds, constraints, verify, prior decisions |
minimal_decisive | Light probes, read-only audits | Goal, verify, explicit file list (≤15 lines total) |
State depth: <tier> in the Agent tool description field.
Process
1. Define the task
Before spawning the agent, read specs/state.yaml if it exists. Then write a minimal self-contained brief using this template (brief size directly controls token cost and hallucination risk — do not pad):
Goal: [one sentence — specific, measurable outcome]
In scope: [explicit file or module list]
Out of bounds: [what NOT to do]
Constraints: [relevant CONVENTIONS.md rules, existing patterns, test requirements]
Verify: [runnable command]
Prior decisions: [relevant entries from specs/state.yaml — omit section if none apply]Do not include full file contents, full conversation history, or decisions unrelated to this task.
2. Spawn the subagent (iterative retrieval, max 3 cycles)
Use the Agent tool with a fresh context per spawn. Pass prior decisions only via specs/state.yaml.
Cycle: dispatch → evaluate output vs goal → refine brief → re-spawn if needed (max 3 cycles).
Include in each brief:
- All context the agent needs (it starts cold — no shared state)
- Reference to CONVENTIONS.md constraints
- The verify command it must run before reporting done
Show full SKILL.md (150 more words)Show less
3. Stage 1 review — output inspection
When the subagent returns, review its report before looking at the diff:
- Did it run the verify command? Did it pass?
- Does it explain what it changed and why?
- Are there any concerns raised by the agent?
If the report raises red flags, ask the subagent for clarification or re-run with adjusted instructions.
4. Stage 2 review — diff inspection
Inspect the actual diff:
git diff main...HEADCheck:
- Changes are scoped to what was asked — nothing extra
- No
any, no@ts-ignore, no disabled lint rules - Tests added for new behavior
- CONVENTIONS.md compliance (naming, structure, no gh issue creation)
- Boy Scout Rule: touched areas are cleaner than before
5. Decision
- Accept: merge the result into the main working branch
- Revise: send back to the subagent with specific feedback
- Reject: discard and re-approach differently
After accepting, append to specs/state.yaml under ## Active Decisions:
**[task short name]**: [what approach the agent chose and why — one sentence]Report the decision and rationale to the user.
© danielvm-git, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/delegate-task of danielvm-git/bigpowers.
Open the folder on GitHubat commit 812d57a
Compare with similar skills
Delegate Task 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 |
|---|---|---|---|---|---|---|
| Delegate Task this skilldanielvm-git/bigpowers | 256 | — | ~961 | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 repos | ~1.5k | Automated safety check: Pass | None | |
| 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 | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
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.
More from danielvm-git/bigpowers
All 39 skills in this repoExtract Design
danielvm-git/bigpowers
Extract a Google DESIGN.md file from an HTML prototype (claude.ai/design or any styled page) using Puppeteer, producing machine-readable tokens and AI-generated prose.
Align Grid
danielvm-git/bigpowers
Build editorial/magazine/report webpages on a GENUINE Müller-Brockmann modular grid (International Typographic Style) — not a decorative one.
Assess Impact
danielvm-git/bigpowers
Analyze the blast radius of a proposed change before any code is written.
Audit Code
danielvm-git/bigpowers
Self-review checklist for the coding agent to run before dispatching a reviewer.
Audit Plan
danielvm-git/bigpowers
Evaluate an incoming project plan against bigpowers principles and conventions, surface gaps, and produce a READY/NOT READY verdict before engagement begins.
Compose Workflow
danielvm-git/bigpowers
Chain multiple bigpowers skills into a custom workflow recipe saved in specs/.
Related
Categories
Questions about Delegate Task
What does Delegate Task do?
Delegate one complex task to a single subagent, review its work in two stages before merging back. Delegate Task is an agent skill from danielvm-git/bigpowers. Delegate one complex task to a single subagent, review its work in two stages before merging back.
When should I use Delegate Task?
Delegate Task fits situations like: A task is complex and requires careful review before the result is accepted; tasks that involve Subagents.
How do I install Delegate Task in Claude Code?
Run `npx skills add danielvm-git/bigpowers --skill delegate-task -a claude-code`. Or copy the skill folder (skills/delegate-task in danielvm-git/bigpowers) into .claude/skills/delegate-task in your project. Claude Code loads it when a task matches its description.
How do I install Delegate Task in Codex?
Run `npx skills add danielvm-git/bigpowers --skill delegate-task -a codex`. Or copy the skill folder (skills/delegate-task in danielvm-git/bigpowers) into .agents/skills/delegate-task in your project. Codex loads it when a task matches its description.
Can I use Delegate Task 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 danielvm-git/bigpowers --skill delegate-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/delegate-task, .gemini/skills/delegate-task, .github/skills/delegate-task and .opencode/skills/delegate-task in your project.
What does Delegate Task need to run?
Going by SKILL.md and its folder, Delegate Task needs the command-line tools its instructions call (git).
Does Delegate Task access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Delegate Task 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 Delegate Task use?
Delegate Task is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Delegate Task use?
About 961 tokens (SKILL.md is roughly 3.8k 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 Delegate Task?
Skills that share tags, products or a category with Delegate Task: Claude Code Agent Development (anthropics/claude-plugins-official, 37k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Delegate Task?
danielvm-git (a GitHub user) maintains it in danielvm-git/bigpowers, which has 256 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on September 21, 2026.
Source: danielvm-git/bigpowers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.