agentmods.dev

skill-graveyard: Instructions file for Claude Code

CLAUDE.md

skill-graveyard CLAUDE.md is an instructions file for Claude Code from sfrangulov/skill-graveyard. It costs 3,047 tokens per session, scanned A, original, MIT.

Project instructions for skill-graveyard, a command-line tool that compares installed Claude Code skills with skills actually used in local session logs. It groups skills as active, unused, missing, or incorrectly reported as used.

In plain words
What is it for?
Use it when changing the parser, skill discovery, command-line tools, documentation, tests, or workspace packages. It also guides safe sample data and screenshot updates.
Why use it?
It helps contributors understand the repository's stable behavior and protect its public documentation from exposing private names or session data. It also explains that the project uses an npm workspaces monorepo, meaning several related packages are managed together.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; names the TodoWrite tool; mentions Claude Code.

This is sfrangulov/skill-graveyard's own configuration. It tells Claude Code how to work on skill-graveyard 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 skill-graveyard configures →

not rated 10repo 1mo ago A scan 3,047 tokens original MIT
View source ↗ sfrangulov/skill-graveyard sfrangulov.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to sfrangulov/skill-graveyard. 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/sfrangulov/skill-graveyard/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sfrangulov/skill-graveyard

Made for: Claude Code.

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 skill-graveyard CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sfrangulov/skill-graveyard/claude-md.svg)](https://agentmods.dev/instructions/sfrangulov/skill-graveyard/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sfrangulov/skill-graveyard/claude-md"><img src="https://agentmods.dev/badge/instructions/sfrangulov/skill-graveyard/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,047 This file is loaded in full into every session.
When invoked 3,047 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.03047 $0.03047
Opus 5 $0.01523 $0.01523
Sonnet 5 $0.00609 $0.00609
Haiku 4.5 $0.00305 $0.00305

Measured 7d ago against content hash 62da5e736363, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

skill-graveyard 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 7d 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.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

A CLI that audits which Claude Code skills the user actually invokes. It parses local session JSONL logs and cross-references the skill installs on disk to surface two signals from one parser:

  1. Dead installs — skills present on disk, never invoked → safe to remove.
  2. Hallucinated invocations — skills invoked that aren't installed → external-framework registrations, model tool/skill confusion, or typos.

The four user-facing buckets (active / dead / missing / hallucinated) and their definitions are documented in README.md and are a stable contract.

This repo is public

No secrets, no proprietary client names, no real session data ever lands in docs/ or README.md. Sample CLI output on the live site uses anonymized project names (e.g. client-analytics, clientco/web-platform) — keep that pattern when refreshing screenshots. If you spot a real-looking name slipping in, mask it before pushing.

Layout

This is an npm workspaces monorepo:

  • packages/core/ — @skill-graveyard/core (published). Shared parser, discovery, paths, tokenizer, known_tools. Generic parseToolCalls<T> lets sister CLIs reuse the JSONL stream.
  • packages/skill-graveyard/ — published as skill-graveyard. CLI, all subcommand implementations (audit, prune, suggest, projects, cost, outdated), format.ts.
  • packages/mcp-graveyard/ — published as mcp-graveyard. CLI for auditing MCP server tool usage. Mirrors skill-graveyard's bucket model (active/dead/missing/hallucinated) but for MCP servers.
  • packages/memory-graveyard/ — published as memory-graveyard. CLI auditing per-project MEMORY.md index + memory/*.md entries. v1 surface: audit, lint, prune, projects. Same monorepo conventions; no plugin distribution.
  • skills/skill-graveyard/SKILL.md, skills/mcp-graveyard/SKILL.md, skills/memory-graveyard/SKILL.md — Agent Skill manifests for skills.sh. Discovered when users run npx skills add sfrangulov/skill-graveyard. NOT shipped in any npm tarball — read directly from the GitHub repo.
  • release-please-config.json, .release-please-manifest.json — release-please configuration (per-package settings, current version baseline). See the Release section below.
  • .github/workflows/release-please.yml — automated release workflow (open Release PR on push to main, publish + tag + GH release on PR merge).
  • docs/ — Pages site (docs/index.html) and design specs (docs/specs/).

Read the full file on GitHub · 157 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. 7d ago First seen · 157 lines · 3,047 tokens per session scan A 62da5e736363

Subscribe to this mod's changes

skill-graveyard CLAUDE.md is an instructions file published in the GitHub repository sfrangulov/skill-graveyard (10 stars, last pushed 1mo ago), licensed MIT. It adds 3,047 tokens to every session, about $0.0152 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 2026-08-31.

Claude Codeanthropicauditclaudeclaude-code-plugincli
Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens