signet-eval: Instructions file for Claude Code

CLAUDE.md

signet-eval CLAUDE.md is an instructions file for Claude Code from jmcentire/signet-eval. It costs 1,659 tokens per session, scanned A, original, MIT.

A set of project instructions for signet-eval, a Rust program that checks AI agent tool calls against policy rules.

In plain words
What is it for?
Use it when working on signet-eval, especially to build or test it, inspect or validate policies, preview automatic fixes, or connect it to agent hook events.
Why use it?
It gives an agent clear commands for building, testing, installing, and using signet-eval as a hook that reads and checks tool-call data.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions Claude Code; mentions Codex; mentions OpenCode.

This is jmcentire/signet-eval's own configuration. It tells Claude Code how to work on signet-eval 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 signet-eval configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jmcentire/signet-eval. 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/jmcentire/signet-eval/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jmcentire/signet-eval

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 signet-eval CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jmcentire/signet-eval/claude-md.svg)](https://agentmods.dev/instructions/jmcentire/signet-eval/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jmcentire/signet-eval/claude-md"><img src="https://agentmods.dev/badge/instructions/jmcentire/signet-eval/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,659 This file is loaded in full into every session.
When invoked 1,659 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01659 $0.01659
Opus 5 $0.00830 $0.00830
Sonnet 5 $0.00332 $0.00332
Haiku 4.5 $0.00166 $0.00166

Measured 7d ago against content hash e27146e2fd4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

signet-eval 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 7d 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 · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

signet-eval

Deterministic policy enforcement for AI agent tool calls. Rust. Single binary.

Quick Reference

cargo build --release          # build
cargo test                     # 231 tests (unit, integration, adversarial, self-protection, inject)
cargo install --path .         # install to ~/.cargo/bin

# Hook mode (default — reads stdin, writes stdout)
echo '{"tool_name":"Bash","tool_input":{"command":"rm foo"}}' | signet-eval
echo '{"hook_event_name":"PreToolUse","tool_name":"Bash","tool_input":{"command":"rm foo"}}' | signet-eval --adapter codex
echo '{"hook_event_name":"PermissionRequest","tool_name":"Bash","tool_input":{"command":"rm foo"}}' | signet-eval --adapter codex-permission
echo '{"toolCall":{"name":"run_command","args":{"CommandLine":"rm foo","Cwd":"/tmp"}}}' | signet-eval --adapter antigravity

# CLI
signet-eval init               # write system policy + sample.yaml (never touches rules.yaml)
signet-eval rules              # show merged rules (LOCKED/USER/SYSTEM tagged)
signet-eval validate           # check policy
signet-eval validate --fix     # auto-fix clampable issues
signet-eval validate --fix --dry-run  # preview fixes
signet-eval test '<json>'      # test a tool call
signet-eval setup              # create vault
signet-eval unlock             # refresh session
signet-eval status             # vault info + enforcement state
signet-eval store <n> <v>      # store credential
signet-eval delete <n>         # delete credential
signet-eval log                # action log
signet-eval reset-session      # clear spending
signet-eval sign               # HMAC-sign policy + user rules
signet-eval injections         # recent inject fires
signet-eval inject-test <rule> # force-fire one inject rule for testing
signet-eval serve              # MCP management server (17 tools)
signet-eval proxy              # MCP proxy

Structure

src/
  embedded_checks.rs — trusted ENSURE scripts installed atomically on first use
  main.rs          — CLI entry point (clap), 24 subcommands
  policy.rs        — Policy engine, condition functions, first-match-wins auth + advisory inject pass
  vault.rs         — Encrypted vault (Argon2id + AES-256-GCM), 3-tier, spending ledger, scoped credentials
  hook.rs          — Claude/Codex/Antigravity/OpenCode hook I/O adapters (stdin JSON → stdout JSON)
  mcp_server.rs    — MCP management server (17 tools, rmcp), locked-rule guards, auto-sign
  mcp_proxy.rs     — MCP proxy for upstream servers (rmcp), hot-reload policy
tests/
  integration_hook.rs  — End-to-end hook subprocess tests (including self-protection)
  integration_cli.rs   — CLI subcommand integration tests
examples/
  basic_policy.yaml       — Simple deny/ask rules
  spending_limits.yaml    — Cumulative spending with vault
  enterprise_policy.yaml  — Strict controls for regulated environments
  inject_examples.yaml    — INJECT trigger/payload examples

Read the full file on GitHub · 109 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. 7d ago First seen · 109 lines · 1,659 tokens per session scan A e27146e2fd4a

Subscribe to this mod's changes

signet-eval CLAUDE.md is an instructions file published in the GitHub repository jmcentire/signet-eval (3 stars, last pushed 10d ago), licensed MIT. It adds 1,659 tokens to every session, about $0.0083 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.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

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