Agent skill

Subagent Delegation

by Porabuild in Porabuild/Poracode

Delegate independent, bounded work to the best available Poracode agents and consolidate verified results.

Apache-2.0Auto-check passedAgent Workflows

Install Subagent Delegation

skills CLI
$ npx skills add Porabuild/Poracode --skill subagent-delegation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Porabuild/Poracode subagent-delegation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Porabuild/Poracode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/plugins/subagent-delegation/skills/subagent-delegation .claude/skills/subagent-delegation && rm -rf skills-src

Use ~/.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/

Facts

Skill name
subagent-delegation
GitHub stars
115
Token cost
~789 tokens
SKILL.md length
402 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
Apache-2.0

At a glance

Delegate independent, bounded work to the best available Poracode agents and consolidate verified results.

  • Works in 6 steps: Classify the work with one to five… → Omit provider, model, reasoning, and… → Split the work into concrete subtasks… → …
  • Parallel research
  • SKILL.md covers Decide whether to delegate, Workflow, Safety and retries and Output
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Subagent Delegation is an agent skill from Porabuild/Poracode. Delegate independent, bounded work to the best available Poracode agents and consolidate verified results. Use for parallel research, independent reviews, specialist work, or non-overlapping implementation; do not delegate trivial, sequential, tightly coupled, or context-heavy work.

Its SKILL.md is about 790 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: One window for all your AI coding agents. Run Claude, Codex, OpenCode, Gemini, Antigravity, Cursor, and Copilot side-by-side. Terminal and chat, any layout. The licence is Apache-2.0.

When your agent uses it

  • Parallel research
  • Independent reviews
  • Specialist work
  • Non-overlapping implementation

Example prompts

  • “/subagent-delegation”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Classify the work with one to five concise task tags. Use list_agents when selection matters; call get_agent only when you need a…
  2. Omit provider, model, reasoning, and Fast unless the user chose them or the task requires a deliberate override. Let Crossagents apply…
  3. Split the work into concrete subtasks with clear deliverables and non-overlapping edit scope. Every prompt must be self-contained and…
  4. For one short task, call spawn_agent in the foreground. Set background=true only when the coordinator has useful independent work to do…
  5. At the next real synchronization point, wait once for every required background result. Do not repeatedly poll. Cancel or continue without…
  6. Inspect returned evidence and changes, resolve disagreements or shared-worktree conflicts, and verify the combined result against the…

What it can do on your machine

Read from SKILL.md and the folder at commit e56fcc8. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Subagent Delegation loads about 789 tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 402 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~789

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 Porabuild/Poracode at commit e56fcc8, republished under its Apache-2.0 licence (© Porabuild). 402 words, ~789 tokens.

Download SKILL.mdSave it as .claude/skills/subagent-delegation/SKILL.md (or your agent's skills folder).
name
subagent-delegation
description
Delegate independent, bounded work to the best available Poracode agents and consolidate verified results. Use for parallel research, independent reviews, specialist work, or non-overlapping implementation; do not delegate trivial, sequential, tightly coupled, or context-heavy work.

Crossagents

Use Poracode's crossagents MCP when independent, bounded work can run in parallel or a specialist or independent second opinion will materially improve the result. The coordinator remains responsible for understanding the problem, protecting shared state, and validating the final answer.

Decide whether to delegate

Delegate when at least one of these is true:

  • two or more subtasks can run independently;
  • a distinct provider or specialist perspective is valuable;
  • an independent review reduces correctness or security risk;
  • a bounded search, test, or implementation lane can return a concrete artifact.

Do not delegate a trivial task, a sequence whose next step depends on the previous result, overlapping edits, or work that would require copying most of the conversation. Do not delegate merely to avoid understanding the task.

Workflow

  1. Classify the work with one to five concise task tags. Use list_agents when selection matters; call get_agent only when you need a provider's detailed models, reasoning choices, Fast support, or permission information.
  2. Omit provider, model, reasoning, and Fast unless the user chose them or the task requires a deliberate override. Let Crossagents apply learned and configured routing.
  3. Split the work into concrete subtasks with clear deliverables and non-overlapping edit scope. Every prompt must be self-contained and include relevant context, constraints, authority, expected output, and verification.
  4. For one short task, call spawn_agent in the foreground. Set background=true only when the coordinator has useful independent work to do before synchronization. Submit independent tasks together through one tasks call for actual parallelism.
  5. At the next real synchronization point, wait once for every required background result. Do not repeatedly poll. Cancel or continue without a stalled optional run.
  6. Inspect returned evidence and changes, resolve disagreements or shared-worktree conflicts, and verify the combined result against the original request.
Show full SKILL.md (106 more words)Show less

Safety and retries

  • Child agents have powerful permissions. Their prompt must not authorize actions beyond the user's request.
  • Use startup-only fallback retries by default. any-failure can repeat writes or external side effects and requires explicit justification and authority.
  • Do not allow multiple agents to edit the same files concurrently. Assign exact ownership or make review lanes read-only.
  • Treat a confident child response as a claim, not proof. Check the relevant files, commands, tests, sources, or runtime state yourself.

Output

Lead with the consolidated result. Mention delegated lanes only when it helps explain evidence, disagreement, limitations, or provider diversity. State what was verified and what remains uncertain.

© Porabuild, 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

Just SKILL.md in resources/plugins/subagent-delegation/skills/subagent-delegation of Porabuild/Poracode.

Open the folder on GitHubat commit e56fcc8

Compare with similar skills

Subagent Delegation 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.

Subagent Delegation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Subagent Delegation this skillPorabuild/Poracode115—~789Automated safety check: PassApache-2.0
Claude Code Agent Developmentanthropics/claude-plugins-official38k7 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25840 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    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.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 37 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • 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

    258 GitHub starsUsed in 40 repos~1.5k tokens
    Agent WorkflowsAuto-check passed
  • 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.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed
  • 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.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from Porabuild/Poracode

All 21 skills in this repo
  • Interactive Testing

    Porabuild/Poracode

    Run repeatable integration and smoke testing against the real Poracode Electron app through Chrome DevTools Protocol.

    115 GitHub stars~4.5k tokensUpdated today
    Auto-check: notes
  • Release Notes

    Porabuild/Poracode

    Write consistent, hand-written-looking changelog entries for a Poracode release.

    115 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Skill Creator Poracode

    Porabuild/Poracode

    Create a new reusable agent skill managed by Poracode. An agent skill from Porabuild/Poracode.

    115 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • App Controls

    Porabuild/Poracode

    Inspect and drive Poracode itself — the Terminal panel, other threads, projects, workspaces, git, pull requests, and schedules — through the poracode MCP.

    115 GitHub stars~745 tokensUpdated today
    Auto-check passed
  • Chrome Control

    Porabuild/Poracode

    Use the user's real Chrome tabs and signed-in sessions for visible browser workflows.

    115 GitHub stars~691 tokensUpdated today
    Auto-check passed
  • Computer Use

    Porabuild/Poracode

    Inspect and operate native Windows, macOS, or Linux applications through Poracode's desktop-control tools.

    115 GitHub stars~718 tokensUpdated today
    Auto-check passed

Categories

Questions about Subagent Delegation

What does Subagent Delegation do?

Delegate independent, bounded work to the best available Poracode agents and consolidate verified results. Subagent Delegation is an agent skill from Porabuild/Poracode. Delegate independent, bounded work to the best available Poracode agents and consolidate verified results.

When should I use Subagent Delegation?

Subagent Delegation fits situations like: parallel research; independent reviews; specialist work; non-overlapping implementation.

How do I install Subagent Delegation in Claude Code?

Run `npx skills add Porabuild/Poracode --skill subagent-delegation -a claude-code`. Or copy the skill folder (resources/plugins/subagent-delegation/skills/subagent-delegation in Porabuild/Poracode) into .claude/skills/subagent-delegation in your project. Claude Code loads it when a task matches its description.

How do I install Subagent Delegation in Codex?

Run `npx skills add Porabuild/Poracode --skill subagent-delegation -a codex`. Or copy the skill folder (resources/plugins/subagent-delegation/skills/subagent-delegation in Porabuild/Poracode) into .agents/skills/subagent-delegation in your project. Codex loads it when a task matches its description.

Can I use Subagent Delegation 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 Porabuild/Poracode --skill subagent-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/subagent-delegation, .gemini/skills/subagent-delegation, .github/skills/subagent-delegation and .opencode/skills/subagent-delegation in your project.

What does Subagent Delegation need to run?

SKILL.md names no scripts, command-line tools or credentials: Subagent Delegation is instructions for the agent only.

Does Subagent Delegation 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 Subagent Delegation 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 Subagent Delegation use?

Subagent Delegation 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 Subagent Delegation use?

About 789 tokens (SKILL.md is roughly 3.2k 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 Subagent Delegation?

Skills that share tags, products or a category with Subagent Delegation: Claude Code Agent Development (anthropics/claude-plugins-official, 38k 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 Subagent Delegation?

Porabuild (a GitHub organization) maintains it in Porabuild/Poracode, which has 115 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 9, 2026.

Source: Porabuild/Poracode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.