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/bch1212/agentvault/claude-mdgit clone --depth 1 https://github.com/bch1212/agentvaultWrote 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/bch1212/agentvault/claude-md)<a href="https://agentmods.dev/instructions/bch1212/agentvault/claude-md"><img src="https://agentmods.dev/badge/instructions/bch1212/agentvault/claude-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 | $0.00885 | $0.00885 |
| Opus 5 | $0.00443 | $0.00443 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
agentvault 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentVault
AI-native credential management SaaS for autonomous AI agents.
What It Does
- Stores API keys/secrets with Fernet column-level encryption
- Issues unique API keys to registered "agent identities"
- Proxy endpoint: agents call
/api/v1/vault/get/{credential_name}with their API key - Per-agent daily/monthly spending budgets
- Full audit logs of every vault access
- MCP server interface (stdio + SSE on
/mcp) - Stripe billing (Free / Pro $49 / Business $149 / Enterprise $499)
Stack
- Backend: FastAPI (Python 3.12) on Railway
- Database: Postgres (asyncpg + SQLAlchemy async)
- Encryption: Fernet (cryptography lib) — column-level, not just at-rest
- Auth: Clerk (user) + custom API keys (agents)
- Payments: Stripe Checkout + webhooks
- Alerts: SendGrid
- MCP: FastMCP library
Project Structure
agentvault/
├── api/
│ ├── main.py # FastAPI app + lifespan
│ ├── config.py # Pydantic settings
│ ├── database.py # SQLAlchemy async engine
│ ├── models/
│ │ ├── db.py # ORM models (User, Agent, Credential, etc.)
│ │ └── schemas.py # Pydantic request/response schemas
│ ├── services/
│ │ ├── encryption.py # Fernet encrypt/decrypt
│ │ ├── auth.py # API key gen, hashing, agent lookup
│ │ ├── budget.py # Budget enforcement + tracking
│ │ ├── audit.py # Audit log service
│ │ └── alerts.py # SendGrid email alerts
│ ├── middleware/
│ │ ├── agent_auth.py # X-Agent-Key header validation
│ │ └── user_auth.py # Authorization header (Clerk JWT / email)
│ └── routers/
│ ├── users.py # POST /users
│ ├── agents.py # CRUD agent identities
│ ├── credentials.py # CRUD encrypted credentials
│ ├── vault.py # Agent-facing proxy endpoint
│ ├── audit.py # Query audit logs
│ ├── budgets.py # Budget management
│ └── billing.py # Stripe checkout/webhooks/portal
├── mcp_server/
│ ├── server.py # FastMCP tools (list, get, status)
│ └── __main__.py # python -m mcp_server
├── tests/
│ ├── conftest.py # SQLite fixtures, test client
│ ├── test_encryption.py # Encryption roundtrip tests
│ ├── test_auth.py # API key tests
│ └── test_api.py # Full integration tests
├── deploy.sh # Railway deploy script
├── Dockerfile
├── railway.toml
└── requirements.txt
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.
- 4d ago First seen · 89 lines · 885 tokens per session scan A 37dc5287cf33
agentvault CLAUDE.md is an instructions file published in the GitHub repository bch1212/agentvault (0 stars, last pushed 3mo ago), licensed MIT. It adds 885 tokens to every session, about $0.0044 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.
Other instructions, from other repositories
Kokoro-FastAPI AGENTS.md
AGENTS.md instructions for remsky/Kokoro-FastAPI, covering agents.md, layout, commands, conventions and gotchas.
geolens CLAUDE.md
Claude Code instructions for geolens-io/geolens: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
Huntable-CTI-Studio AGENTS.md
AGENTS.md instructions for dfirtnt/Huntable-CTI-Studio, covering agents.md, orientation, local context, prompt-injection alerting and change-type quick reference.
dev-challenge CLAUDE.md
Claude Code instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.
deckforge CLAUDE.md
Instructions for Whatsonyourmind/deckforge, covering deckforge, tech stack, project structure, key commands and local development.