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 agentmods add skills/254095728-bit/agent-skill-menu/skill-menunpx skills add 254095728-bit/agent-skill-menu --skill skill-menugit clone --depth 1 https://github.com/254095728-bit/agent-skill-menuWrote 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/254095728-bit/agent-skill-menu/skill-menu)<a href="https://agentmods.dev/skills/254095728-bit/agent-skill-menu/skill-menu"><img src="https://agentmods.dev/badge/skills/254095728-bit/agent-skill-menu/skill-menu.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.00806 |
| Opus 5 | $0.00053 | $0.00403 |
| Sonnet 5 | $0.00021 | $0.00161 |
| Haiku 4.5 | $0.00011 | $0.00081 |
Grade A, and why
skill-menu 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 6d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Skill Menu
Help the user discover relevant installed skills without executing them.
Workflow
- Infer the user's task, domain, objects, tools, file types, and desired outcome from the current conversation.
- Translate or expand those concepts into concise search terms when useful.
- Run the bundled CLI with JSON output:
node scripts/skill-menu.mjs search "<terms>" --json
- Present every relevant result in ranked order. Show only:
- Skill name
- One-sentence purpose
- Always copy the CLI result into the assistant response in the current Agent conversation. A tool call or terminal result alone is not a user-visible answer.
- Do not merely say that results were generated or that a menu was displayed. Include the actual complete result list in the response.
- Never show internal numeric scores.
- Never invoke, install, remove, move, repair, or modify a recommended skill.
- If no task is clear, run
list --jsonand show favorites followed by frequently viewed skills. - If no reliable match exists, say so. Only broaden the search when the user asks.
Commands
Run commands relative to this skill directory:
node scripts/skill-menu.mjs list [--json]
node scripts/skill-menu.mjs search "<terms>" [--json] [--broad]
node scripts/skill-menu.mjs show <skill-name> [--json]
node scripts/skill-menu.mjs favorite add|remove|list [skill-name] [--json]
node scripts/skill-menu.mjs tag add|remove <skill-name> <tag...> [--json]
node scripts/skill-menu.mjs tag rename <old-tag> <new-tag> [--json]
node scripts/skill-menu.mjs tag list [--json]
node scripts/skill-menu.mjs tag export [file]
node scripts/skill-menu.mjs tag import <file> [--replace]
node scripts/skill-menu.mjs root add|remove|list [path] [--json]
node scripts/skill-menu.mjs doctor [--json] [--report]
node scripts/skill-menu.mjs index rebuild [--json]
Use --root <path> to add one or more roots for a single command.
Presentation
- Respond in the user's language.
- Keep the default results compact and scrollable in the Agent interface.
- Render every returned result in the assistant message as a numbered list. Do not leave results only in tool output.
- Do not group results unless the user asks for grouping.
- Explain details, source paths, platforms, dependencies, tags, or health issues only when the user asks about a specific skill.
- Recommend ordered multi-skill workflows when the task clearly has multiple stages, but do not execute any step.
- Do not interrupt a skill the user already chose unless they ask for alternatives or the chosen skill cannot fit the task.
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.
- 6d ago First seen · 68 lines · 105 tokens per session scan A b6129fac542e
skill-menu is a skill published in the GitHub repository 254095728-bit/agent-skill-menu (2 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 806 once invoked, about $0.0005 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 2026-08-31.
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…