What is skill-manager CLAUDE.md?

Documentation for a Rust command-line program that installs AI coding-assistant skill bundles for Claude, OpenCode, and Cursor. A skill bundle is a folder of instruction, agent, or command files.

It is for building and testing the tool, running its command line, and understanding how bundles move from local folders or Git repositories into each assistant's expected location.

It explains how the program is built, tested, and organized, so developers can work on it without tracing the whole codebase first.

How pyrex41/skill-manager configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pyrex41/skill-manager. 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/pyrex41/skill-manager/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/pyrex41/skill-manager

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pyrex41/skill-manager/claude-md/github.svg)](https://agentmods.dev/instructions/pyrex41/skill-manager/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/pyrex41/skill-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/pyrex41/skill-manager/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pyrex41/skill-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/pyrex41/skill-manager/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,333 This file is loaded in full into every session.

When invoked 1,333 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.

Model	Per session	Once invoked
Fable 5.1	$0.01333	$0.01333
Opus 5.5	$0.00533	$0.00533
Sonnet 5.5	$0.00267	$0.00267
Haiku 4.5	$0.00133	$0.00133

Measured 2mo ago against content hash 25b549a3fa61, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-manager 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 2mo 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 · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build & Test Commands

cargo build              # Debug build
cargo build --release    # Release build
cargo test               # Run all tests
cargo test <test_name>   # Run a single test
cargo run                # Run the CLI (lists bundles)
cargo run -- <bundle>    # Install a bundle

The binary is named skm (skill-manager).

Architecture

This is a Rust CLI tool for managing AI coding assistant skills across Claude, OpenCode, and Cursor. It copies skill bundles from configured sources to tool-specific locations.

Core Data Flow

Sources (source.rs) - Skill bundles come from local directories or git repositories
Bundles (bundle.rs) - A bundle is a directory containing skills/, agents/, and/or commands/ subdirectories with .md files
Targets (target.rs) - Each tool (Claude/OpenCode/Cursor) has different destination paths and file transformations
Install (install.rs) - Orchestrates copying from source bundle to target tool location

Module Responsibilities

main.rs - CLI argument parsing (clap) and command dispatch
config.rs - TOML config file at ~/.config/skm/config.toml, manages source list
source.rs - Source trait with LocalSource and GitSource implementations; git sources clone to cache dir
bundle.rs - Bundle struct representing a skill bundle with its files
target.rs - Tool enum handling per-tool path conventions and file transformations
discover.rs - Scans directories for installed skills across all three tools
install.rs - Copies bundle files to target locations
setup.rs - First-run interactive setup wizard

Tool-Specific Path Mappings

Type	Claude	OpenCode	Cursor	Codex
Skills	`.claude/skills/{bundle}-{name}/SKILL.md`	`.opencode/skills/{bundle}-{name}/SKILL.md`	`.cursor/skills/{bundle}-{name}/SKILL.md`	`.codex/skills/{bundle}-{name}/SKILL.md`
Agents	`.claude/agents/{bundle}/{name}.md`	`.opencode/agents/{bundle}-{name}.md`	`.cursor/agents/{bundle}-{name}.md`	`.codex/agents/{bundle}-{name}.md`
Commands	`.claude/commands/{bundle}/{name}.md`	`.opencode/commands/{bundle}-{name}.md`	`.cursor/commands/{bundle}-{name}.md`	`.codex/commands/{bundle}-{name}.md`
Rules	`.claude/rules/{bundle}-{name}/RULE.md`	`.opencode/rules/{bundle}-{name}/RULE.md`	`.cursor/rules/{bundle}-{name}/RULE.md`	`.codex/rules/{bundle}-{name}/RULE.md`

Read the full file on GitHub · 113 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.

2mo ago First seen · 113 lines · 1,333 tokens per session scan A 25b549a3fa61

Subscribe to this mod's changes

skill-manager CLAUDE.md is an instructions file published in the GitHub repository pyrex41/skill-manager (4 stars, last pushed 9mo ago), licensed MIT. It adds 1,333 tokens to every session, about $0.0053 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.

Building agents

skill-manager CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skill-manager CLAUDE.mdpyrex41/skill-manager	Instructions file	4	9mo ago	MIT	A	1,333	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

skill-manager: Instructions file for Claude Code