Borrowing it
Nothing to install: this file belongs to byronxlg/skillfold. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/byronxlg/skillfold/main/CLAUDE.mdgit clone --depth 1 https://github.com/byronxlg/skillfoldWrote 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/instructions/byronxlg/skillfold/claude-md)<a href="https://agentmods.dev/instructions/byronxlg/skillfold/claude-md"><img src="https://agentmods.dev/badge/instructions/byronxlg/skillfold/claude-md.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 | $0.01673 | $0.01673 |
| Opus 5 | $0.00837 | $0.00837 |
| Sonnet 5 | $0.00335 | $0.00335 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
skillfold 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 3d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skillfold
Declarative skill manager for Claude config. Declare skills and rules in skillfold.yaml, pin exact revisions in skillfold.lock, install them into .claude/skills and .claude/rules.
GitHub
- Repo: https://github.com/byronxlg/skillfold
- Issues, PRs, releases, actions, and all other GitHub features are available for use
Operations
runbook/- how the package, site and blog cron ship, what healthy means, and how to roll back (fleet standard, tier 3)
Quick Reference
- Run the CLI:
npx tsx src/cli.ts <command> - Install skills:
npx tsx src/cli.ts install(--frozenfor CI-exact installs) - Add a skill:
npx tsx src/cli.ts add <source> - Verify sync:
npx tsx src/cli.ts check - List status:
npx tsx src/cli.ts list - Tests:
npm test(node:test via tsx, no extra deps) - Type check:
npm run typecheck(src + scripts) - Build:
npm run build - Build the blog:
npm run build:blog(regenerates site/blog/, output is gitignored, except the marker-fenced block in site/index.html which is committed) - Write a blog post: follow
skills/blog-post/SKILL.md. The blog is current-events-first (news in the agent config / skill distribution / supply chain space), with an evergreen queue indocs/blog-todo.mdas the quiet-week fallback. It is not a product blog.
Project Structure
src/
cli.ts - CLI entry point: arg parsing, command dispatch, output formatting
manifest.ts - skillfold.yaml parsing, validation, comment-preserving add/remove edits
source.ts - source string parsing (local paths, github:, npm:) and @ref extraction
skill.ts - SKILL.md frontmatter parsing, skill directory reading, sha256 integrity hashing
lock.ts - skillfold.lock read/write and manifest-vs-lock diffing
resolve.ts - central resolver: manifest + lock -> concrete files, pin reuse, frozen mode
github.ts - GitHub ref -> SHA resolution and skill fetching (contents API, injectable fetch)
npm.ts - npm skill resolution: node_modules first, then registry via npm pack into cache
cache.ts - shared content cache (~/.cache/skillfold), keyed by SHA / exact version
compose.ts - composed skill generation (body concatenation, topological ordering)
targets.ts - install-target layouts (claude, codex) mapping targets to locations
agentsmd.ts - managed rules block in AGENTS.md for the codex target
install.ts - sync into skillsDir (managed-dir safety, pruning) and offline check
init.ts - skillfold init scaffolding
list.ts - status table (ok / modified / not installed / not locked)
search.ts - npm registry search for skillfold-skill packages
index.ts - public API exports
testutil.ts - test helpers (tmp dirs, fixture skills, fetch stub); excluded from build
library/ - 11 general-purpose skills published with the package (agentskills map)
site/ - static docs site deployed to GitHub Pages
index.html - landing page (page-specific CSS inline)
assets/ - vendored fonts, base.css (shared chrome), blog.css
blog/posts/ - blog sources: markdown + YAML frontmatter (the only committed blog files)
scripts/
build-blog.ts - renders site/blog/posts/*.md into site/blog/, feed.xml,
sitemap.xml, robots.txt, and the marker-fenced block in index.html
skills/blog-post/ - repo-specific skill driving the weekly blog automation
docs/blog-todo.md - blog editorial state: news beats, fallback queue, rollouts, shipped log
docs/ - markdown docs (getting started, manifest, CLI, publishing)
skillfold.yaml - this repo's own manifest (dogfood; installs from library/)
skillfold.schema.json - JSON Schema for manifest validation and IDE autocompletion
action.yml - GitHub Action wrapper for skillfold check
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.
- 3d ago Changed · +4 lines · +37 tokens per session 2bd7a0e672a7
- 7d ago First seen · 107 lines · 1,636 tokens per session scan A 30206a6dfea1
skillfold CLAUDE.md is an instructions file published in the GitHub repository byronxlg/skillfold (12 stars, last pushed 5d ago), licensed MIT. It adds 1,673 tokens to every session, about $0.0084 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 2026-08-30.
Other instructions, from other repositories
ai-agent-rules-generator ui-design.instructions.md
Glitch Payment Gateway admin UI design rules — mandatory element & component reference for WooCommerce settings.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.