cat:spawn-subagent

A way to start another coding agent with the relevant task information in a separate working copy of the project. An isolated worktree is a separate set of project files for making changes safely.

In plain words
What is it for?
Use it to delegate a task to a subagent while keeping its changes separate.
Why use it?
It lets another agent work without interfering with the main working copy and tracks its token use.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/cowwoc/cat/spawn-subagent
Any agent
npx skills add cowwoc/cat --skill spawn-subagent
Clone the repo
git clone --depth 1 https://github.com/cowwoc/cat

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.08456
Opus 5 $0.00010 $0.04228
Sonnet 5 $0.00004 $0.01691
Haiku 4.5 $0.00002 $0.00846

Measured 2d ago against content hash dcf8c4f29746, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cat:spawn-subagent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/spawn-subagent/SKILL.md · 1,035 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 1,035 lines · 19 tokens per session scan A dcf8c4f29746

Subscribe to this mod's changes

cat:spawn-subagent is a skill published in the GitHub repository cowwoc/cat (101 stars, last pushed 1mo ago), with no licence file. It adds 19 tokens to every session and 8,456 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

gsd-eval-review

Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.

open-gsd/gsd-core · 26 tokens

gsd-orchestrator

Build software products autonomously via GSD headless mode. Handles the full lifecycle: write a spec, launch a build, poll for completion, handle blockers, track costs, and verify the result. Use when asked to "build something", "create a project", "run gsd", "check build status", or any task that requires autonomous…

open-gsd/gsd-pi · 80 tokens

create-mcp-server

Build, iterate, and evaluate Model Context Protocol (MCP) servers that expose external services as tools an LLM can call. Covers schema/tool design, error handling, pagination, MCP Inspector testing, and an eval set. Use when asked to "build an MCP server", "create an MCP tool", "wrap this API as MCP", "expose X to…

open-gsd/gsd-pi · 90 tokens

create-skill

Expert guidance for creating, writing, building, and refining GSD skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

open-gsd/gsd-pi · 45 tokens

observability

Add agent-first observability — structured logs, health endpoints, failure-state persistence, explicit failure modes — so the next agent can diagnose problems unattended. Use when asked to "add logging", "add observability", "add metrics", "make this observable", or when building/refactoring a subsystem that runs…

open-gsd/gsd-pi · 76 tokens

create-gsd-extension

Create, debug, and iterate on GSD extensions (TypeScript modules adding tools, commands, event hooks, custom UI, and providers). Use when asked to build an extension, add a tool the LLM can call, register a slash command, hook into GSD events, create custom TUI components, or modify GSD behavior. Triggers on…

open-gsd/gsd-pi · 101 tokens