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 ngocsangyem/MeowKit --skill docs-findergit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/docs-finder)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/docs-finder"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/docs-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/ngocsangyem/meowkit/docs-finder"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/docs-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 | $0.00148 | $0.02669 |
| Opus 5 | $0.00074 | $0.01334 |
| Sonnet 5 | $0.00030 | $0.00534 |
| Haiku 4.5 | $0.00015 | $0.00267 |
Grade A, and why
mk:docs-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 8d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Discovery via Scripts
Overview
Script-first documentation discovery using Context7 (llms.txt) + Context Hub (chub).
Execute scripts to handle the entire workflow — no manual URL construction needed. Scripts handle source detection, fetching, fallback chains, and result analysis automatically.
Primary Workflow
ALWAYS execute scripts in this order:
# 1. DETECT query type + recommended source
node scripts/detect-source.js "<user query>"
# 2a. FETCH via Context7 (for library/framework docs)
node scripts/fetch-context7.js "<user query>"
# 2b. FETCH via Context Hub (for curated/internal docs)
node scripts/fetch-chub.js "<user query>" [--lang py] [--version v2]
# 3. ANALYZE results (context budget + URL categorization)
echo '<content>' | node scripts/analyze-results.js -
# 4. [TIER-4 FALLBACK] If all above return empty or off-target:
node scripts/fetch-web-to-markdown.js "<exact-url>"
# → outputs delegationCommand; execute it via Bash tool
Scripts handle URL construction, source routing, fallback chains, and error handling automatically.
Scripts
detect-source.js — Classify query + route to source
- Determines: LIBRARY_DOCS vs INTERNAL_DOCS
- Extracts: library name, topic keyword, language hint
- Resolves: known library → context7 repo path
- Returns JSON:
{queryType, source, fallbackSource, library, repo, topic, isTopicSpecific} - Zero-token execution
fetch-context7.js — Retrieve docs from context7.com
- Constructs context7.com URLs automatically
- Handles fallback: topic URL → general URL → official llms.txt
- Includes timeout handling (30s)
- Returns JSON:
{success, source, content, tokenEstimate, topicSpecific} - Zero-token execution
fetch-chub.js — Retrieve docs from Context Hub
What ships with it
19 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.
- .env.example 337 B
- package.json 779 B
- references/chub-patterns.md 4.2 KB
- references/context7-patterns.md 2.0 KB
- references/errors.md 2.3 KB
- scripts/analyze-results.js 7.5 KB runs code
- scripts/detect-source.js 7.1 KB runs code
- scripts/fetch-chub.js 7.7 KB runs code
- scripts/fetch-context7.js 5.3 KB runs code
- scripts/fetch-web-to-markdown.js 3.7 KB runs code
- scripts/tests/run-tests.js 1.5 KB runs code
- scripts/tests/test-analyze-results.js 7.3 KB runs code
- scripts/tests/test-detect-source.js 6.2 KB runs code
- scripts/tests/test-fetch-chub.js 2.5 KB runs code
- scripts/tests/test-fetch-context7.js 3.5 KB runs code
- scripts/utils/env-loader.js 2.3 KB runs code
- workflows/internal-search.md 1.8 KB
- workflows/library-search.md 1.9 KB
- workflows/topic-search.md 2.2 KB
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.
- 8d ago First seen · 215 lines · 148 tokens per session scan E 425f2965b360
mk:docs-finder is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 2,669 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.