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/vcav-io/agentvault/claude-mdgit clone --depth 1 https://github.com/vcav-io/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/vcav-io/agentvault/claude-md)<a href="https://agentmods.dev/instructions/vcav-io/agentvault/claude-md"><img src="https://agentmods.dev/badge/instructions/vcav-io/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 | $0.00433 | $0.00433 |
| Opus 5 | $0.00217 | $0.00217 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00043 | $0.00043 |
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.
What it actually says
AgentVault
Open agent-native bounded-disclosure coordination protocol.
Build & Test
# Rust (relay)
cargo build --workspace
cargo test --workspace
cargo clippy --workspace -- -D warnings
cargo fmt --all -- --check
# TypeScript (client)
cd packages/agentvault-client && npm install && npm test
# TypeScript (MCP server)
cd packages/agentvault-mcp-server && npm install && npm run build
Requires Rust 1.88.0+ (pinned in rust-toolchain.toml).
Packages
| Package | Language | Description |
|---|---|---|
packages/agentvault-relay |
Rust | Ephemeral API-mediated relay with receipt signing (no persistent storage) |
packages/agentvault-client |
TypeScript | Standalone relay client library (fetch-based) |
packages/agentvault-mcp-server |
TypeScript | MCP server exposing agentvault.* tools |
packages/agentvault-demo-ui |
TypeScript | Three-panel protocol observatory (demo/debugging) |
Dependencies
- vault-family-core (git dep) -- shared IFC vocabulary, receipt envelope, escalation interface
- MCP server depends on
agentvault-clientviafile:link - av-tee/tee-verifier — TEE receipt verification (Rust). The TS client surfaces TEE fields for introspection; full cryptographic verification requires tee-verifier. Intended path: published crate or VFC-hosted. Do not let this calcify as a git dep.
Key Directories
docs/— architecture docs, threat model, guides,environment-variables.mdfor relay configschemas/output/— content-addressed output schemas (registry lookup by hash)prompt_programs/— model profiles and enforcement policies with lockfile validation
CI
GitHub Actions (ci.yml) runs fmt, clippy, build, and test for Rust.
TypeScript packages are covered by ci-typescript.yml.
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 · 48 lines · 433 tokens per session scan A 4d60c9d56560
agentvault CLAUDE.md is an instructions file published in the GitHub repository vcav-io/agentvault (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 433 tokens to every session, about $0.0022 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
Avernet AGENTS.md
AGENTS.md instructions for inclusionAI/Avernet, covering agents.md, source of truth, project overview, repository layout and module responsibilities.
AgentNetworkProtocol AGENTS.md
AGENTS.md instructions for agent-network-protocol/AgentNetworkProtocol, covering repository guidelines, project structure & module organization, protocol ownership boundary, build, test, and development commands and coding style & naming conventions.
Cotal AGENTS.md
AGENTS.md instructions for Cotal-AI/Cotal, covering agents.md, what this is, read these first, commands and repository map.
guild AGENTS.md
AGENTS.md instructions for mathomhaus/guild, covering guild — agent bootstrap, first action — bootstrap guild mcp, repo facts, tool discipline and when onboarding.
nelson CLAUDE.md
Instructions for Aspegio/nelson, covering nelson, key references, maintainability sensors, active sensors and suppressing or bumping a sensor.
protocol-launcher AGENTS.md
Instructions for zhensherlock/protocol-launcher, covering agents.md - protocol launcher, repo shape, commands that matter, protocol library and docs.