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 LiuYihey/Auto-agent-skills --skill search-skillgit clone --depth 1 https://github.com/LiuYihey/Auto-agent-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/liuyihey/auto-agent-skills/search-skill)<a href="https://agentmods.dev/skills/liuyihey/auto-agent-skills/search-skill"><img src="https://agentmods.dev/badge/skills/liuyihey/auto-agent-skills/search-skill/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/liuyihey/auto-agent-skills/search-skill"><img src="https://agentmods.dev/badge/skills/liuyihey/auto-agent-skills/search-skill.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 | $0.00015 | $0.00498 |
| Opus 5 | $0.00008 | $0.00249 |
| Sonnet 5 | $0.00003 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
search-skill 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 11d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instruction: Searching for Skills
When you encounter a task, follow this workflow to find and use the best skills:
1. Analyze User Request
- Carefully read the user's instructions and requirements.
- Identify the core steps needed to accomplish the task.
- Determine which of these steps might benefit from existing, mature skills (e.g., standard setups, specific framework configurations, complex workflows).
2. Formulate Search Keywords
- Based on the analysis, extract 1 to 3 targeted keywords representing the core needs (e.g., "deploy", "react", "testing").
- The keywords should be broad enough to find relevant skills but specific enough to be useful. MUST BE IN ENGLISH.
3. Search for Skills
- Use the
searchPublicSkillscommand/function (or equivalent) to search for each keyword. - IMPORTANT: As an agent, you should execute the search by running
npx skills find <keyword>in the terminal.
4. Evaluate Search Results
- Observe the output from the terminal.
- Analyze the returned skills based on:
- Relevance/Match: Does the skill description match your specific need?
- Downloads/Popularity: Is it a widely used and trusted skill?
- Select the most appropriate skill(s) to install.
5. Install and Plan Usage
- First, construct a new , add 'gitclone.com' after 'https://' and before the original repository URL. Here is a simple example:
- Original:
https://github.com/user/repo - New:
https://gitclone.com/github.com/user/repo
- Original:
- Second, try to install the chosen skill(s) using
git clone <New repository-url>to our personal skills library (~/.autoskills/personal-skills/). - Third, create a symlink for this skill in the global skills library (~/.agents/skills/).
6. Read Skill Documentation
- Explicitly state in your plan in which subsequent step you will refer to or use this installed skill.
- You can adapt the skill's instructions to the specific constraints of the current task if needed.
7. Execution
- Proceed with the task execution, referring to the installed skill(s) at the designated stages.
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.
- 11d ago First seen · 43 lines · 15 tokens per session scan A ed717e18460f
search-skill is a skill published in the GitHub repository LiuYihey/Auto-agent-skills (9 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 498 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 2026-08-31.
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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…