skilltree CLAUDE.md

A dependency manager for AI-agent skills, which are instruction packages for coding agents, plus agents and slash commands. It uses Git repositories as its package catalogue and records exact versions in lockfiles.

In plain words
What is it for?
Use it to add, update, pin, and manage skill packages, agents, and Claude Code commands from Git repositories.
Why use it?
It helps install skills with their required dependencies and keep installations repeatable across machines or projects. It also handles dependencies that depend on other dependencies.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/imarios/skilltree/claude-md
Clone the repo
git clone --depth 1 https://github.com/imarios/skilltree
Per session 1,837 This file is loaded in full into every session.
When invoked 1,837 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01837 $0.01837
Opus 5 $0.00919 $0.00919
Sonnet 5 $0.00367 $0.00367
Haiku 4.5 $0.00184 $0.00184

Measured 2d ago against content hash d1aa87a6d03d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skilltree 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 2d 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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skilltree - Dependency Manager for AI Agent Skills

What is this?

Dependency-aware package manager for AI agent skills (SKILL.md), agents, and Claude Code slash commands. Uses git repos as the registry, resolves transitive dependencies, supports semver version pinning via git tags, and produces lockfiles for reproducible installs.

Docs

docs/
├── specs/
│   ├── spec.md              # Core spec: concepts, commands, phases
│   ├── reference.md         # Technical: file formats, algorithm, error messages
│   ├── decisions.md         # Design decisions (resolved + deferred), open questions
│   └── background.md        # Why skilltree, alternatives comparison
├── planning/                # Phase planning docs (hydrogen, helium, etc.)
└── PROJECTS.md              # Project tracking

Tech Stack

  • Language: TypeScript
  • Runtime: Bun (development + bun build --compile for single binary)
  • Also works with: Node.js (npx skilltree)
  • Key deps: simple-git, semver, yaml, commander

Project Structure

skilltree/
├── src/
│   ├── cli.ts              # CLI entry point (commander)
│   ├── commands/            # One file per command
│   ├── core/
│   │   ├── manifest.ts      # skilltree.yml parsing/writing
│   │   ├── lockfile.ts      # skilltree.lock parsing/writing
│   │   ├── resolver.ts      # Version resolution (semver constraints)
│   │   ├── graph.ts         # Dependency graph + topological sort
│   │   ├── git.ts           # Git operations (clone, fetch, tags)
│   │   ├── installer.ts     # File copy, symlinks, permissions
│   │   ├── scanner.ts       # Dependency detection (regex)
│   │   ├── llm.ts           # Optional LLM dependency detection
│   │   └── frontmatter.ts   # SKILL.md frontmatter parsing
│   └── types.ts
├── tests/
├── docs/
├── package.json
├── tsconfig.json
└── CLAUDE.md

Development

bun install
pre-commit install
pre-commit install --hook-type post-merge  # auto-rebuilds local binary after version bumps
bun test
bun run dev -- install
bun build --compile src/cli.ts --outfile dist/skilltree

Read the full file on GitHub · 144 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. 2d ago First seen · 144 lines · 1,837 tokens per session scan A d1aa87a6d03d

Subscribe to this mod's changes

skilltree CLAUDE.md is an instructions file published in the GitHub repository imarios/skilltree (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,837 tokens to every session, about $0.0092 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.