Borrowing it
Nothing to install: this file belongs to choi88andys/skills. 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/choi88andys/skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/choi88andys/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/instructions/choi88andys/skills/claude-md)<a href="https://agentmods.dev/instructions/choi88andys/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/choi88andys/skills/claude-md/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/instructions/choi88andys/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/choi88andys/skills/claude-md.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 | $0.00894 | $0.00894 |
| Opus 5.5 | $0.00358 | $0.00358 |
| Sonnet 5.5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
skills 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 1mo 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — choi88andys/skills
Repo language is English: commits, CHANGELOG.md, PR bodies, and this file.
Release procedure
Gitflow. develop integrates unreleased work; main is what marketplace clients pull.
- Branch off
develop→ PR → squash-merge intodevelop. --no-ffmergedevelop→main, messageMerge branch 'develop' into main for vX.Y.Z release. Pushmaindirectly — develop→main takes no PR.- Tag the
mainmerge commit and push the tag. That fires.github/workflows/release.yml, which creates a GitHub Release titledvX.Y.Z(the workflow strips only theimmutable--prefix, so thevstays).
Use a lightweight tag — git tag immutable--vX.Y.Z <sha>, never git tag -a. Every release tag is a commit object, and release.yml calls gh release create --generate-notes, which never reads a tag message.
develop is never merged back from main; it stays at the last feature squash.
The version is declared once, in immutable/.claude-plugin/plugin.json. The changelog is immutable/CHANGELOG.md — there is no top-level one, and .claude-plugin/marketplace.json carries no version field.
Gotchas
- A new skill must be registered in BOTH
skillsarrays —immutable/.claude-plugin/plugin.jsonand.claude-plugin/marketplace.json. Skills live at the plugin root, not underskills/, so nothing is discovered by convention. The marketplace array serves marketplace installs; the plugin.json array serves every other load path —claude --plugin-dir, a.zip. Missing the first shipped v0.6.2 with five unregistered skills; missing the second made--plugin-dirload zero skills (and, because a same-named--plugin-dirplugin shadows the installed one, removed/immutable:*from the session) until v0.11.0, whileclaude plugin validatepassed.bash immutable/scripts/plugin_manifest.test.shchecks both against the directories on disk. immutable/.claude-plugin/plugin.json'sdescriptionandkeywordsare mirrored verbatim into.claude-plugin/marketplace.json. Edit one, edit the other;plugin_manifest.test.shis the only check.- Dogfood a branch with
claude --plugin-dir <checkout>/immutable, never by releasing. It loads the directory directly (no cache copy) and wins over the installedimmutable@skillsfor that session; SKILL.md edits are live,hooks/and manifest edits need/reload-plugins. - Any new field in
immutable/examples/_profiles/default-*.ymlbumpsprofile_schemain both files./immutable:migrate's universal diff runs only when the team profile'sprofile_schemais below the bundled one; a field added without a bump is invisible to every team that already migrated (measured 2026-09-09:deferral_patternsadded under schema 3 reached no team profile until copied by hand). Additive is not exempt — the bump is the signal, not a statement about breakage. immutable/strings/strings.en.ymlandstrings.ko.ymlmust stay at key parity. A key present inenbut missing fromkodoes not error — it silently falls back to the English string, so a Korean team (theteam_languagedefault) reads English. This shipped as a real bug in v0.7.4 and was fixed in v0.7.6.immutable/strings/strings.ja.ymlis a deliberate scaffold holding zero keys, designed to fall back to English wholesale. Do not "fix" its parity againsten.immutable/scripts/validate_docs.pyvalidates a consumer's SDD repo (itspitches/and ADRs), not this plugin's own source. Running it here checks nothing.
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.
- 1mo ago Changed · +2 lines · +309 tokens per session f0cdc89b04da
- 2mo ago First seen · 26 lines · 585 tokens per session scan A 5f863d600432
skills CLAUDE.md is an instructions file published in the GitHub repository choi88andys/skills (9 stars, last pushed 6d ago), licensed MIT. It adds 894 tokens to every session, about $0.0036 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.