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 tylerjhayden/agent-toolkit --skill publish-to-toolkitgit clone --depth 1 https://github.com/tylerjhayden/agent-toolkitWrote 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/tylerjhayden/agent-toolkit/publish-to-toolkit)<a href="https://agentmods.dev/skills/tylerjhayden/agent-toolkit/publish-to-toolkit"><img src="https://agentmods.dev/badge/skills/tylerjhayden/agent-toolkit/publish-to-toolkit/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/tylerjhayden/agent-toolkit/publish-to-toolkit"><img src="https://agentmods.dev/badge/skills/tylerjhayden/agent-toolkit/publish-to-toolkit.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 | $0.00037 | $0.01408 |
| Opus 5 | $0.00018 | $0.00704 |
| Sonnet 5 | $0.00007 | $0.00282 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
publish-to-toolkit 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 12d 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.
This is a copy
89% identical to publish-skill — 36 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
publish-to-toolkit
Sanitize and publish your skills and tools to the public agent-toolkit GitHub repo.
Overview
Automates the process of taking a private skill or tool, stripping internal references (paths, names, cross-references), generating user-facing docs, and pushing to the your-username/agent-toolkit public repo. Tracks versions and file hashes to detect changes.
When to Use
- "Publish bear to the marketplace"
- "Push this skill public"
- "What skills are published?"
- "Diff bear against the published version"
README vs SKILL.md — Two-Audience Doctrine
These files serve different readers and should be authored differently:
| SKILL.md | README.md | |
|---|---|---|
| Audience | The AI agent | Humans installing the skill |
| Tone | Dense, operational | Explanatory, setup-focused |
| Must include | When to invoke, commands, data locations | Installation, shell alias setup, why it works the way it does |
| Should include | Common mistakes (for the agent) | First-time config steps, common mistakes, full command ref |
| Should NOT include | Verbose rationale, setup prose | Internal implementation details |
SKILL.md is optimized for context. Every line burns tokens. Keep it tight: trigger phrases, command reference, data locations.
README.md must be useful before the AI is involved. A human follows it to install the skill — they can't ask the AI for help yet. It must answer: What is this? Why does it work this way? How do I get it running?
Skills with CLI tools nearly always need three things in the README that generate_readme cannot produce:
- Shell alias setup — how the tool gets on PATH for terminal use
- "Why" explanations — rationale for non-obvious design choices (e.g., "Why Playwright?", "Why URL scheme?")
- First-time credential/config steps — concrete instructions for acquiring API keys, session cookies, etc.
When a README needs this level of detail, set preserve_readme: true in the manifest. The publish flow will preserve the handcrafted README instead of regenerating it from SKILL.md.
What ships with it
3 files 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.
- 12d ago First seen · 117 lines · 37 tokens per session scan A c0aef59fe5c8
publish-to-toolkit is a skill published in the GitHub repository tylerjhayden/agent-toolkit (2 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 1,408 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to publish-skill, differing in 36 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…