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 instructions/fix2015/load-skill/claude-mdgit clone --depth 1 https://github.com/fix2015/load-skillWhat 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 | $0.00712 | $0.00712 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
load-skill CLAUDE.md 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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Project Is
load-skill is a CLI tool (published to npm) that aggregates AI coding skills from multiple GitHub repositories into a single searchable registry. Users run npx load-skill install <name> to install skills for Claude Code, Cursor, Codex, or Gemini CLI.
Commands
npm install # Install dependencies
npm test # Run all tests (node:test runner)
npm run lint # ESLint across src/ bin/ test/
npm run scrape # Rebuild registry from GitHub sources (needs GITHUB_TOKEN for rate limits)
node bin/load-skill.js --help # Test CLI locally
Run a single test file:
node --test test/registry.test.js
Architecture
bin/load-skill.js— CLI entry point (shebang, commander arg parsing, routes to commands)src/commands/— One file per CLI command (install, list, search, info, tags, sources, update). Each exports a single function.src/registry.js— Core module: loadsdata/skills-registry.json, provides search/filter/find functions. Used by all commands and the public API.src/installer.js— Fetches SKILL.md from GitHub raw URLs and writes to the correct tool-specific path (~/.claude/skills/,.cursor/rules/, etc.)src/scraper/index.js— Standalone script that hits GitHub API to discover skills across configured repos and rebuilds the registry JSON. Also exportsinferTagsandparseYamlFrontmatterutilities.src/index.js— Public programmatic API (re-exports from registry + installer)data/skills-registry.json— The skill index: sources array + skills array. Each skill has name, description, tags, source, compatible tools, raw_url, repo_url. This is the single source of truth shipped with the npm package.
Key Design Decisions
- Uses CommonJS (
require) and chalk v4 / ora v5 (CJS-compatible versions) to avoid ESM complications withnpx commanderfor CLI parsing — all commands registered inbin/load-skill.js. Bareload-skill <name>(no subcommand) defaults to install.- The registry is a single JSON file cached in memory (not a database) —
clearCache()must be called after writes - Skills are fetched at install-time from
raw.githubusercontent.comURLs, not bundled - The scraper uses
inferTags()to auto-tag skills based on keyword matching against name + description - Node.js built-in test runner (
node:test+node:assert) — no test framework dependency
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.
- 2d ago First seen · 52 lines · 712 tokens per session scan A acfee3fbfd4c
load-skill CLAUDE.md is an instructions file published in the GitHub repository fix2015/load-skill (2 stars, last pushed 4mo ago), licensed MIT. It adds 712 tokens to every session, about $0.0036 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 instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
deepseekCLI CLAUDE.md
Instructions for cynchro/deepseekCLI, covering tarea actual, progreso, decisiones clave, próximos pasos and contexto importante.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
agentoscope AGENTS.md
Instructions for rafaelcg/agentoscope, covering agentoscope — agent instructions, what this is, layout, commands and conventions.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).