manage-skills: Skill for Claude Code

.claude/skills/manage-skills/SKILL.md

manage-skills is a skill for Claude Code from Getty/manage-skills. It costs 36 tokens per session (3,494 once invoked), scanned A, original, MIT.

A command-line tool for sharing complete skill folders between projects using hard links, which let files in different locations point to the same stored data.

In plain words
What is it for?
Use it to add, remove, sync, inspect, and locate shared skills. It also provides rules for safely editing files in hard-linked skill folders.
Why use it?
It keeps shared skills aligned across projects and helps prevent edits from quietly disconnecting one project’s files from the others.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; mentions Codex.

This is Getty/manage-skills's own configuration. It tells Claude Code how to work on manage-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything manage-skills configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is ../../../manage-skills list # relative to this SKILL.md.

Part of the manage-skills plugin — 2 skills shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Getty/manage-skills/main/.claude/skills/manage-skills/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Getty/manage-skills

Made for: Claude Code.

Or install manage-skills, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for manage-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/getty/manage-skills/manage-skills/github.svg)](https://agentmods.dev/skills/getty/manage-skills/manage-skills)
Your own site
<a href="https://agentmods.dev/skills/getty/manage-skills/manage-skills"><img src="https://agentmods.dev/badge/skills/getty/manage-skills/manage-skills/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.

agentmods 80×15 button for manage-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/getty/manage-skills/manage-skills"><img src="https://agentmods.dev/badge/skills/getty/manage-skills/manage-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,494 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.03494
Opus 5 $0.00018 $0.01747
Sonnet 5 $0.00007 $0.00699
Haiku 4.5 $0.00004 $0.00349

Measured 12d ago against content hash 4831ffd91fc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

manage-skills 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 12d 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.

.claude/skills/manage-skills/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI tool for sharing whole skill directories across projects via hardlinks. Config lives in ~/.manage-skills/.

⚠️ Editing any file in a linked skill? Use cat > file — NOT the Edit/Write tools. They rewrite-and-replace → new inode → silently breaks the hardlink to every other project. Full rules + repair in Editing hardlinked skills below.

What gets linked: the directory

A skill is a directory, and the whole directory is what gets hardlinked — SKILL.md, references/, templates/, scripts/, every regular file in it. Each one shares an inode with its counterpart in the source, subdirectories included.

SKILL.md is not the linked thing. It is the file that identifies a directory as a skill, which is why discovery keys on it and why a target definition names it (claude:.claude/skills:SKILL.md). It gets linked exactly like every other file in the directory, with no special status once linking starts.

This matters for the rule below: it applies to every file in the skill, not just the entry file. A references/api.md detaches from its source exactly the way a SKILL.md does, and just as silently.

A project linked by an older version holds only its SKILL.md. manage-skills sync upgrades it in place — the rest of the directory is hardlinked in, subdirectories and all. No unlink, no flag.

Commands

manage-skills                        # Interactive mode (fzf or numbered menu)
manage-skills list                   # Show all skills with status
manage-skills locations              # Where skills come from, per source
manage-skills link <skill>...        # Hardlink skills into current project
manage-skills unlink <skill>...      # Remove skills from current project
manage-skills unlink <skill> --force # …even if it holds files no source has
manage-skills sync                   # Re-hardlink stale copies (keeps diverged ones)
manage-skills sync --force           # …and relink the diverged ones too
manage-skills update [name...]       # Pull remote sources (--check only reports)
manage-skills package [dir]          # Make a skill directory installable by others
manage-skills check                  # Verify hardlink integrity
manage-skills sources                # List source directories
manage-skills sources add <dir|repo|owner> [label]  # Add a source: directory,
                                     #   repo, or GitHub owner (their skills repo)
manage-skills sources remove <dir>   # Remove a skill source
manage-skills targets                # List configured targets
manage-skills targets add <n> <p> <f> # Add target (name:path:file)
manage-skills self                   # Where this install and its own skills live
manage-skills self install           # Register the shipped skills as a source
manage-skills self update            # Update the script and the shipped skills
manage-skills init                   # Create ~/.manage-skills/ config

Read the full file on GitHub · 302 lines

Changes

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.

  1. 12d ago First seen · 302 lines · 36 tokens per session scan E 4831ffd91fc6

Subscribe to this mod's changes

manage-skills is a skill published in the GitHub repository Getty/manage-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 36 tokens to every session and 3,494 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens