New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Subagent Delegation

by tola-rs in tola-rs/tola-ssg

Run work through subagents instead of the main thread. An agent skill from tola-rs/tola-ssg.

MITAuto-check passedAgent Workflows

Install Subagent Delegation

skills CLI
$ npx skills add tola-rs/tola-ssg --skill subagent-delegation -a claude-code

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

GitHub CLI
$ gh skill install tola-rs/tola-ssg 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/tola-rs/tola-ssg.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/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
178
Token cost
~924 tokens
SKILL.md length
476 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Run work through subagents instead of the main thread. An agent skill from tola-rs/tola-ssg.

  • Planning multi-step work
  • SKILL.md covers Stays in main thread, Goes out, Route models for the task and Limit = cooldown, not verdict, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Surveying a codebase

What it does

Subagent Delegation is an agent skill from tola-rs/tola-ssg. Run work through subagents instead of the main thread. Use when planning multi-step work, searching or surveying a codebase, implementing against a fixed brief, running review passes, researching outside the repo, or checking subagent model routing.

Its SKILL.md is about 920 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: SSG for typst-based websites - keep your focus on the content. The licence is MIT.

When your agent uses it

  • Planning multi-step work
  • Surveying a codebase
  • Implementing against a fixed brief
  • Running review passes

Example prompts

  • “/subagent-delegation”

What it can do on your machine

Read from SKILL.md and the folder at commit fbb0506. 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 924 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 476 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~924

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 tola-rs/tola-ssg at commit fbb0506, republished under its MIT licence (© tola-rs). 476 words, ~924 tokens.

Download SKILL.mdSave it as .claude/skills/subagent-delegation/SKILL.md (or your agent's skills folder).
name
subagent-delegation
description
Run work through subagents instead of the main thread. Use when planning multi-step work, searching or surveying a codebase, implementing against a fixed brief, running review passes, researching outside the repo, or checking subagent model routing.

Subagent Delegation

Delegation: default for work that can proceed independently. Buys parallel wall-clock and lean main context.

Stays in main thread

Planning, decomposition, decisions, trade-offs, user conversation, result integration, final verification. Main model = reasoning budget; mechanical reading, searching, transcribing spend it for nothing.

Goes out

  • Reconnaissance/surveys (scout), implementation against complete brief (task; sonic mechanical), review passes (reviewer), web research.
  • Independent slices batched together, one owner per file/area.
  • Stay inline: one-line edit, reasoning existing only in this conversation, anything needing user — brief would cost more than work.

Route models for the task

Select a model appropriate to the task through client routing. Spawn resolves model in order: client per-agent override → agent definition's own model → session's own model. An agent no override covers inherits the session model; configured fallback chains may change the resolved model.

  • The only excluded subagent model is the model the user calls 6 astra; no provider, family, or tier is required or otherwise excluded.
  • Know which routing rule decides a spawn's model before making it; after start or a fallback, inspect the actual model (resolvedModel or the client's agent view). Stop and reroute for this model restriction only when the actual model is 6 astra.

Limit = cooldown, not verdict

Spawn dying on rate limit, overload, or provider outage is transient — not evidence delegation is unavailable, not reason to absorb work into main thread.

  • Assume recovery first, including after main model itself hit a limit: session running again usually means account limits cleared, subagents included. Re-attempt delegation before inline work; let a new failure — not the old — decide otherwise.
  • Recover the slice, don't replace: message failed agent to retry (write agent://<id> — still holds brief and context), or spawn slice again. Fresh run → fresh retry budget; configured fallback chains may already have moved it to another provider.
  • NEVER hard-cancel a limit-stopped spawn: proc://<id>/kill aborts it and releases the session — terminal state; slice rebuildable only by fresh agent reading history://<id>, losing whatever original held. Leave idle/parked, wake with write agent://<id> once account works — still holds brief and context, resumes in place. Account switch is exactly this case ⇒ waking is recovery, not redo.
  • Inline execution replaces one slice for one moment, never the mode: "subagents unavailable" does not carry into rest of session. Client applies same rule to fallback models — fallback returns to primary when cooldown expires.
  • Non-transient failure (bad brief, failing acceptance) → re-brief, not blindly retry.
Show full SKILL.md (81 more words)Show less

Brief carries everything

Subagent starts blank: no conversation, no plan, none of parent's context — only workspace, context files, spawn itself. Spawn states goal, interface it must respect, files it owns, what not to touch, acceptance criterion, shape of answer. Subagent that has to guess guesses wrong at full price.

Read through pointer

Delivery holds preview; agent://<id> holds full output. Work from pointer, pull only lines that matter. Follow-up: message live agent (write agent://<id>) — already holds context — instead of briefing fresh one.

© tola-rs, 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 .agents/skills/subagent-delegation of tola-rs/tola-ssg.

Open the folder on GitHubat commit fbb0506

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 skilltola-rs/tola-ssg178—~924Automated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k7 repos~2.8kAutomated safety check: PassApache-2.0
Create Agentvectorize-io/hindsight48k—~1.1kAutomated safety check: PassMIT
Swarm Parallel Dispatchlangchain-ai/langchain-skills1.3k—~3kAutomated safety check: PassMIT
Fable Foremanolsenbrands/fable-foreman143—~5.2kAutomated safety check: PassMIT
Subagent CreatorgreatSumini/cc-system438—~958Automated safety check: PassMIT

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

  • Create Agent

    vectorize-io/hindsight

    Create a new Hindsight-powered subagent with long-term memory.

    48k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Swarm Parallel Dispatch

    langchain-ai/langchain-skills

    Official

    Fans a list of independent items out to subagents in parallel, merges the results back into a table and supports retrying only the rows that failed.

    1.3k GitHub stars~3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Fable Foreman

    olsenbrands/fable-foreman

    Turns the lead model into a foreman that plans, routes and verifies while cheaper Claude, Codex or Grok workers do the typing, using a per-machine routing card.

    143 GitHub stars~5.2k tokensUpdated 16 days ago
    Agent WorkflowsAuto-check passed

  • Subagent Creator

    greatSumini/cc-system

    Create specialized Claude Code sub-agents with custom system prompts and tool configurations.

    438 GitHub stars~958 tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed

  • Claudish Usage

    MadAppGang/claudish

    CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models).

    1k GitHub stars~9k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

More from tola-rs/tola-ssg

All 10 skills in this repo

  • Trim

    tola-rs/tola-ssg

    Shrink code, tests, comments, and docs to what carries meaning — delete dead paths, redundant states, and refactor-dragging tests outright, then hold the survivors to the four bars.

    178 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Tola

    tola-rs/tola-ssg

    Build and maintain Tola websites and documentation. An agent skill from tola-rs/tola-ssg.

    178 GitHub stars~6k tokensUpdated yesterday
    Auto-check passed

  • Concurrency And Failure

    tola-rs/tola-ssg

    Design and review work that runs concurrently, waits, retries, or owns resources.

    178 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Friendly Report

    tola-rs/tola-ssg

    Report progress to the human. An agent skill from tola-rs/tola-ssg.

    178 GitHub stars~634 tokensUpdated yesterday
    Auto-check passed

  • Refactoring

    tola-rs/tola-ssg

    Restructure code while keeping observable behavior identical, and prove it with difference testing.

    178 GitHub stars~659 tokensUpdated yesterday
    Auto-check passed

  • Scope Discipline

    tola-rs/tola-ssg

    Keep a change inside its requested scope. An agent skill from tola-rs/tola-ssg.

    178 GitHub stars~478 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Subagent Delegation

What does Subagent Delegation do?

Run work through subagents instead of the main thread. An agent skill from tola-rs/tola-ssg. Subagent Delegation is an agent skill from tola-rs/tola-ssg. Run work through subagents instead of the main thread.

When should I use Subagent Delegation?

Subagent Delegation fits situations like: planning multi-step work; surveying a codebase; implementing against a fixed brief; running review passes.

How do I install Subagent Delegation in Claude Code?

Run `npx skills add tola-rs/tola-ssg --skill subagent-delegation -a claude-code`. Or copy the skill folder (.agents/skills/subagent-delegation in tola-rs/tola-ssg) 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 tola-rs/tola-ssg --skill subagent-delegation -a codex`. Or copy the skill folder (.agents/skills/subagent-delegation in tola-rs/tola-ssg) 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 tola-rs/tola-ssg --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 MIT 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 924 tokens (SKILL.md is roughly 3.7k 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), Create Agent (vectorize-io/hindsight, 48k stars), Swarm Parallel Dispatch (langchain-ai/langchain-skills, 1.3k stars) and Fable Foreman (olsenbrands/fable-foreman, 143 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Subagent Delegation?

tola-rs (a GitHub organization) maintains it in tola-rs/tola-ssg, which has 178 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 9, 2026.

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