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.
npx agentmods add instructions/autoworks-ai/autovault/agents-mdgit clone --depth 1 https://github.com/autoworks-ai/autovaultWrote 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.
[](https://agentmods.dev/instructions/autoworks-ai/autovault/agents-md)<a href="https://agentmods.dev/instructions/autoworks-ai/autovault/agents-md"><img src="https://agentmods.dev/badge/instructions/autoworks-ai/autovault/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01738 | $0.01738 |
| Opus 5 | $0.00869 | $0.00869 |
| Sonnet 5 | $0.00348 | $0.00348 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
autovault AGENTS.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 6d 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). How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Project
AutoVault is a capability library with local stdio and remote Streamable HTTP MCP entry points 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 local entry point dist/index.js is designed to be spawned by an MCP host (Codex, Cursor, Codex) over stdio. The remote entry point dist/remote.js exposes Streamable HTTP MCP at /mcp with OAuth-backed bearer auth. The autovault CLI also exposes library workflows such as profile sync and skill setup.
Common commands
npm ci # install deps
npm run build # tsc → dist/
npm run dev # tsx watch (rebuild on save)
npm run start:remote # run dist/remote.js after build
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/remote-smoke.mjs # remote HTTP/OAuth smoke (spawns dist/remote.js)
node scripts/probe.mjs # negative-path probing
The bootstrap/smoke/probe/remote-smoke scripts require npm run build first because they spawn compiled files from dist/.
Pull request workflow
- Open PRs ready for review by default, not draft, so CI and review automation run. Use draft only when explicitly requested.
- After creating a PR from Codex, wait 4-5 minutes before finishing the handoff so GitHub Copilot has time to post review threads.
- After the wait, check the PR for unresolved per-line Copilot review threads. If any exist, run the
copilot-reviewskill/workflow against that PR: evaluate each comment, make valid fixes, reply, resolve handled threads, commit, and push the PR branch. Never merge unless Jack explicitly authorizes it. - If no unresolved Copilot review threads exist, report that there is nothing to do and include the current CI status when available.
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.
- 6d ago First seen · 106 lines · 1,738 tokens per session scan A 06e6b986c74a
autovault AGENTS.md is an instructions file published in the GitHub repository autoworks-ai/autovault (3 stars, last pushed yesterday), licensed MIT. It adds 1,738 tokens to every session, about $0.0087 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.
Other instructions, from other repositories
langgraphjs AGENTS.md
AGENTS.md instructions for langchain-ai/langgraphjs, covering repository instructions and corridor security analysis.
opengeni AGENTS.md
AGENTS.md instructions for Cloudgeni-ai/opengeni, covering agent / automation notes (opengeni), full local stack, architecture notes, pull-request delivery across moving main and keeping these notes current.
newsjack CLAUDE.md
Claude Code instructions for elvisun/newsjack: Load AGENTS.md before editing this repo — follow it.
airails AGENTS.md
AGENTS.md instructions for AdamBien/airails, covering installing airails.dev skills, skill directories per agent, how to install, 1. interactive terminal available (user is driving) and 2. agent shell (no tty).
zephyr-rtos-ai AGENTS.md
Instructions for ksachdeva/zephyr-rtos-ai, covering ai coding assistant context, repository structure, project overview, development setup and prohibited.
voltagent CLAUDE.md
Instructions for VoltAgent/voltagent, a project described as: AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework.