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.
npx skills add connorch/skills --skill claude-code-subagentgit clone --depth 1 https://github.com/connorch/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/connorch/skills/claude-code-subagent)<a href="https://agentmods.dev/skills/connorch/skills/claude-code-subagent"><img src="https://agentmods.dev/badge/skills/connorch/skills/claude-code-subagent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/connorch/skills/claude-code-subagent"><img src="https://agentmods.dev/badge/skills/connorch/skills/claude-code-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.01993 |
| Opus 5.5 | $0.00036 | $0.00797 |
| Sonnet 5.5 | $0.00018 | $0.00399 |
| Haiku 4.5 | $0.00009 | $0.00199 |
Grade A, and why
claude-code-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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Subagent
Use Claude Code as a separate agent for bounded work. It runs headless with claude -p on the user's Claude subscription and exits with a single JSON result. You remain responsible for scoping the task, reviewing what it changed, running or checking verification, and explaining the final result.
If CLAUDECODE is set in your environment, you are already Claude Code. Use native subagents instead of this skill.
Modes
| Mode | Use for | Permission mode |
|---|---|---|
| Implement | Code changes, refactors, fixes | auto |
| Read-only | Review, investigation, second opinion, planning | plan |
Always pass --permission-prompts none so anything that would need a human prompt is denied instead of stalling the run. Claude keeps working around denials, and they are listed in the result's permission_denials.
Never pass --dangerously-skip-permissions or --permission-mode bypassPermissions. Auto mode's classifier blocks exfiltration, destructive git operations, force pushes, and similar actions; that is the safety layer for an unattended run. Auto mode does not support Haiku models, so do not combine it with --model haiku.
Workflow
- Pin the current state with
git status --shortand note any user changes already present. - Define the scope: behavior to change, files or areas to avoid, constraints, and verification commands.
- Decide isolation. If you will keep editing the same checkout while Claude runs, give Claude its own worktree (
git worktree add <path> -b claude/<slug>) and install dependencies there before verification. Otherwise run in place and do not touch the files until Claude exits. - Create a temporary artifact directory and write a self-contained prompt to it.
- Launch
claude -pin the background. - Shortly after launch, check once that the process is alive and
run.logshows no error. - Wait for the
exit_codefile, then read the result JSON. - Inspect
git statusandgit diff, and run the cheapest reliable verification yourself when practical. - Report what Claude changed, what you verified, any permission denials, and any remaining risks or open questions.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago Changed · -1 lines c0a545cb163a
- 23d ago First seen · 168 lines · 90 tokens per session scan A f836880ee490
claude-code-subagent is a skill published in the GitHub repository connorch/skills (2 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 1,993 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…