autovault: Instructions file for Claude Code

CLAUDE.md

autovault CLAUDE.md is an instructions file for Claude Code from autoworks-ai/autovault. It costs 1,660 tokens per session, scanned A, original, MIT.

Repository instructions for AutoVault, a Node and TypeScript server that stores, checks, and serves skill files to coding-agent hosts.

In plain words
What is it for?
Use them when building, testing, debugging, or reviewing changes in the AutoVault repository.
Why use it?
They give agents the project's architecture, commands, testing steps, and rules for working safely in the codebase.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is autoworks-ai/autovault's own configuration. It tells Claude Code how to work on autovault 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 autovault configures →

Reuse

Borrowing it

Nothing to install: this file belongs to autoworks-ai/autovault. 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/autoworks-ai/autovault/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/autoworks-ai/autovault

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 autovault CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/autoworks-ai/autovault/claude-md.svg)](https://agentmods.dev/instructions/autoworks-ai/autovault/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/autoworks-ai/autovault/claude-md"><img src="https://agentmods.dev/badge/instructions/autoworks-ai/autovault/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,660 This file is loaded in full into every session.
When invoked 1,660 The same file — it is already loaded in full.
Security scan A 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 $0.01660 $0.01660
Opus 5 $0.00830 $0.00830
Sonnet 5 $0.00332 $0.00332
Haiku 4.5 $0.00166 $0.00166

Measured 8d ago against content hash f77032364d2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

autovault CLAUDE.md scanned grade A 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

5. `checkCapabilityDeclaration` (`capability.ts`) — cross-check declared capabilities against content (e.g. `network: false` vs. a `curl` in the body).
CLAUDE.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 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.

Project

AutoVault is a stdio-only MCP server that stores, validates, and serves agent SKILL.md files. It is Node/TypeScript (ESM, NodeNext modules, strict TS). It does not execute skills — it validates them and serves them to MCP hosts.

The entry point dist/index.js is designed to be spawned by an MCP host (Claude Code, Cursor, Codex) over stdio. It is not an interactive CLI and has no HTTP surface.

Common commands

npm ci                             # install deps
npm run build                      # tsc → dist/
npm run dev                        # tsx watch (rebuild on save)
npm test                           # vitest run (one-shot)
npm run test:watch                 # vitest in watch mode
npx vitest run tests/dedup.test.ts # run a single test file
npx vitest run -t "name substring" # run tests matching a name
node scripts/bootstrap-skills.mjs  # seed bundled skills into $AUTOVAULT_STORAGE_PATH
node scripts/smoke.mjs             # end-to-end smoke (spawns dist/index.js)
node scripts/probe.mjs             # negative-path probing

The bootstrap/smoke/probe scripts require npm run build first because they spawn dist/index.js as a child process over stdio.

Architecture

Request flow

src/index.tsloadConfig()ensureStorage()createServer() (src/mcp/server.ts) registers 7 MCP tools, each wrapping a handler in src/tools/. Tool handlers return plain objects; runTool in server.ts serializes them to the MCP content[0].text envelope.

Validation pipeline (shared by install_skill and propose_skill)

Both write paths funnel through validateSkillInput() in src/validation/index.ts, which runs in this order:

  1. attemptRepair (frontmatter.ts) — normalizes frontmatter formatting.
  2. parseFrontmatter — gray-matter parse.
  3. validateSchema (schema.ts) — zod schema for name/description/capabilities/etc.
  4. runSecurityScan (security.ts) — denylist regex match against scripts/security/patterns.json (loaded lazily, cached).
  5. checkCapabilityDeclaration (capability.ts) — cross-check declared capabilities against content (e.g. network: false vs. a curl in the body).

Read the full file on GitHub · 99 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. 8d ago First seen · 99 lines · 1,660 tokens per session scan A f77032364d2b

Subscribe to this mod's changes

autovault CLAUDE.md is an instructions file published in the GitHub repository autoworks-ai/autovault (3 stars, last pushed 4d ago), licensed MIT. It adds 1,660 tokens to every session, about $0.0083 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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

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 · 5,153 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

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

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

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