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 laguagu/agents-best-practices --skill skill-findergit clone --depth 1 https://github.com/laguagu/agents-best-practicesWrote 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/laguagu/agents-best-practices/skill-finder)<a href="https://agentmods.dev/skills/laguagu/agents-best-practices/skill-finder"><img src="https://agentmods.dev/badge/skills/laguagu/agents-best-practices/skill-finder/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/laguagu/agents-best-practices/skill-finder"><img src="https://agentmods.dev/badge/skills/laguagu/agents-best-practices/skill-finder.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 | $0.00114 | $0.01031 |
| Opus 5 | $0.00057 | $0.00515 |
| Sonnet 5 | $0.00023 | $0.00206 |
| Haiku 4.5 | $0.00011 | $0.00103 |
Grade A, and why
skill-finder 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Finder
Discover existing official skills before creating a new one.
Quick start
- Capture intent — domain (PDF, auth, PostgreSQL) + task (extract, validate, migrate)
- Search
references/official-skills.mdusing grep-style keyword lookup - Rank matches by publisher reputation and relevance
- Present 3-5 candidates with owner/name + one-line description + link
- Fallback to skills.sh /
npx skills find/ skill-creator if nothing fits
Workflow
Step 1: Understand intent
Extract two dimensions from the user's request:
- Domain — the subject area (e.g.,
PDF,auth,postgres,stripe,react) - Task — the action verb (e.g.,
extract,validate,migrate,test,deploy)
If the user is vague ("help me with auth stuff"), ask one clarifying question before searching. A narrower query returns better matches.
Step 2: Search the local list
Grep references/official-skills.md with the domain keyword first, then
refine with task keywords if too many hits.
grep -i "pdf" .agents/skills/skill-finder/references/official-skills.md
grep -i "auth\|oauth\|jwt" .agents/skills/skill-finder/references/official-skills.md
Expand queries for common synonyms:
database→ also matchpostgres,sql,mongo,mysqlauth→ also matchoauth,jwt,session,loginUI→ also matchfrontend,react,design,component
Step 3: Rank matches
When multiple candidates surface, prefer publishers in this order:
- Official publishers —
anthropics/,vercel-labs/,stripe/,supabase/,microsoft/,google-gemini/,cloudflare/,openai/ - Well-known teams —
huggingface/,sentry/,mongodb/,auth0/,figma/,notion/,datadog/ - Community — any remaining matches
Within a single publisher, prefer the skill whose name most directly matches the user's task verb.
Step 4: Present candidates
Format each recommendation as:
owner/skill-name — one-line description
https://officialskills.sh/owner/skills/skill-name
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.
- 11d ago First seen · 108 lines · 114 tokens per session scan A c8d12bae75c6
skill-finder is a skill published in the GitHub repository laguagu/agents-best-practices (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,031 once invoked, about $0.0006 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…