manage-skills: Skill for Claude Code

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

manage-skills-drift-triage is a skill for Claude Code from Getty/manage-skills. It costs 42 tokens per session (2,169 once invoked), scanned B, original, MIT.

A troubleshooting guide for skill folders whose contents differ between repositories or no longer update together. A repository is a project’s stored code and files.

In plain words
What is it for?
Use it to audit skills across repositories, identify why they drifted, and choose what to do before syncing a changed copy.
Why use it?
It explains how hard-linked files can become separate copies and helps decide how to handle differences that the normal sync command cannot resolve.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

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 →

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-drift-triage/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-drift-triage

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/getty/manage-skills/manage-skills-drift-triage"><img src="https://agentmods.dev/badge/skills/getty/manage-skills/manage-skills-drift-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,169 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00042 $0.02169
Opus 5 $0.00021 $0.01085
Sonnet 5 $0.00008 $0.00434
Haiku 4.5 $0.00004 $0.00217

Measured 12d ago against content hash 9261013305b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

manage-skills-drift-triage scanned grade B 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 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

# 1. find every .claude/skills dir, skip build artifacts / plugin caches / snapshots
.claude/skills/manage-skills-drift-triage/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

manage-skills keeps skills in sync via hardlinks: one inode, many paths. Copies drift apart anyway. This skill covers the two things the CLI does not do for you: auditing across repos (check/sync only ever look at $PWD), and deciding what to do once the content actually differs.

The rule for the easy case lives in skill manage-skills: byte-identical files on different inodes get linked on sight, no permission needed. Everything below is for when that rule does not apply.

How drift actually happens

  • A hardlinked SKILL.md was edited with Edit/Write. Both rewrite-and-replace → new inode for the edited path, old inode (and its stale content) stays behind on every other path. Linkcount on the edited file drops to 1. Skill manage-skills has the rule (cat > file) and the repair steps.
  • A project got a one-time copy instead of a link. Common when a skill set was bootstrapped by copying files in, not by manage-skills link. The copy never enters the sync loop — it just ages while the source keeps evolving.
  • A project is shadowed by priority order. discover_skills dedups by name and the first source in the file wins. If project B provides its own foo but project A is listed earlier and also provides a foo, B's copy never wins — and never gets refreshed either, because sync only relinks against the winning source. manage-skills locations marks these with *, so this one is now visible without an audit.
  • Someone changed the skill on purpose. A project needed something different, edited its copy and committed it. This looks identical to the accident above — [~], linkcount 1 — but sync no longer overwrites it: since v0.8, a copy whose content differs is reported as diverged and kept, and only sync --force relinks it. The commit in that project's history is what tells a deliberate change from an accident, so read it before reaching for --force; the question is whether the change belongs upstream, not how to undo it.
  • A directory that should be a source isn't registered at all (~/.claude/skills is the usual one). Project-local copies of those skills have no sync path back to the canonical copy, so nothing ever compares them.

Read the full file on GitHub · 161 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 · 161 lines · 42 tokens per session scan B 9261013305b8

Subscribe to this mod's changes

manage-skills-drift-triage is a skill published in the GitHub repository Getty/manage-skills (12 stars, last pushed 17d ago), licensed MIT. It adds 42 tokens to every session and 2,169 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). 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