Borrowing it
Nothing to install: this file belongs to Getty/manage-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/Getty/manage-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/Getty/manage-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/getty/manage-skills/claude-md)<a href="https://agentmods.dev/instructions/getty/manage-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/getty/manage-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/getty/manage-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/getty/manage-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 | $0.05041 | $0.05041 |
| Opus 5.5 | $0.02016 | $0.02016 |
| Sonnet 5.5 | $0.01008 | $0.01008 |
| Haiku 4.5 | $0.00504 | $0.00504 |
Grade C, and why
manage-skills CLAUDE.md scanned grade C with 1 finding 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 23d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`unlink` gets the same treatment for a harder reason: it is an `rm -rf` over the whole How it starts
The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code working in this repository. Product documentation lives in README.md.
What This Is
manage-skills — one self-contained bash script that hardlinks skill files between
projects so every copy shares a single inode. No build step, no dependencies.
- Command surface:
./manage-skills --help - Tests:
bash test/smoke-test.sh - Syntax:
bash -n manage-skills
Editing skills — keep the inode
.claude/skills/manage-skills/SKILL.md is the source of truth that other projects
hardlink against. Edit and Write rewrite-and-replace: the path gets a fresh inode,
and every other project silently keeps the old content.
Edit hardlinked files with a shell redirect, which truncates in place:
cat > .claude/skills/<skill>/SKILL.md <<'SKILL'
…
SKILL
stat -c '%i %h' .claude/skills/<skill>/SKILL.md # inode and link count must match the pre-edit values
cp new old is equally safe. sed -i renames on GNU — treat it as unsafe here. Full
rules and the repair recipe live in that skill file.
Shell constraints
set -euo pipefail is enforced. These traps follow from it and from the platform floor:
A pipeline inside an assignment aborts the script. x=$(echo "$list" | grep foo | cut -d: -f1)
dies when grep matches nothing: pipefail propagates its exit 1 and set -e acts on
it. This shipped as a bug — check died in every project that owned a skill of its own,
leaving its originals branch unreachable. Match with a case inside a while read
loop instead, as cmd_check now does.
pipefail makes a short-circuiting reader lie. read_sources | grep -qxF "$path"
reads as a membership test, and is one only for the config's last line. grep -q exits
at its first match, the producer dies of SIGPIPE writing the line after it, and
pipefail hands the if that 141. self therefore called its own shipped skills
unregistered whenever another source followed them, and self install appended a second
copy of a line already there — an idempotence test caught neither, because self install
appends and the tests never put anything behind it. source_path_registered is the same
test written as a while read fed by a process substitution: no pipe, no status to
propagate. Every early-stopping consumer has this shape — grep -q, grep -m, head.
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.
- 23d ago Changed · +5 lines · +72 tokens per session c33e19b4aa50
- 2mo ago First seen · 346 lines · 4,969 tokens per session scan C 1d9bf8495276
manage-skills CLAUDE.md is an instructions file published in the GitHub repository Getty/manage-skills (13 stars, last pushed 23d ago), licensed MIT. It adds 5,041 tokens to every session, about $0.0202 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.