Borrowing it
Nothing to install: this file belongs to Heretek-AI/Agent-Proof. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Heretek-AI/Agent-Proof/main/CLAUDE.mdgit clone --depth 1 https://github.com/Heretek-AI/Agent-ProofWrote 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/heretek-ai/agent-proof/claude-md)<a href="https://agentmods.dev/instructions/heretek-ai/agent-proof/claude-md"><img src="https://agentmods.dev/badge/instructions/heretek-ai/agent-proof/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/heretek-ai/agent-proof/claude-md"><img src="https://agentmods.dev/badge/instructions/heretek-ai/agent-proof/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01031 | $0.01031 |
| Opus 5.5 | $0.00412 | $0.00412 |
| Sonnet 5.5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade D, and why
Agent-Proof CLAUDE.md scanned grade D with 3 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Sets up `.git/hooks/pre-commit` and locks governance files to read-only (`chmod 0444`). Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Scrubs shell command injections (`curl | sh`, `npx`, `sudo`) from external logs and MCP outputs (Agentjacking defense). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Scrubs shell command injections (`curl | sh`, `npx`, `sudo`) from external logs and MCP outputs (Agentjacking defense). How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Claude Code Guidelines for Agent-Proof
This guide provides instructions and reference material for Claude Code sessions working on @heretek-ai/agent-proof.
🚀 Quick Reference Commands
# Build the project (tsup bundles to dist/)
npm run build
# Run unit and integration tests (Vitest, 16 suites, 86 tests)
npm test
# Run strict TypeScript type checks
npm run typecheck
# Run real-world sandbox verification script
npm run test:real-repo
# Run polyglot GitHub matrix verification across 5 real-world repositories
npm run test:matrix
# Run oneshot 5-issue real-world Drop verification
npm run test:e2e-5-issues
# Run full automated E2E test against Heretek-AI/drop
npm run test:e2e-drop
# Test CLI locally
node bin/agent-proof.js --version
node bin/agent-proof.js init
node bin/agent-proof.js detect
node bin/agent-proof.js freeze
node bin/agent-proof.js unfreeze
node bin/agent-proof.js attest
node bin/agent-proof.js run pre-commit --sarif
node bin/agent-proof.js status
🏗️ Architecture & Component Overview
Agent-Proof is structured into modular components:
- Stack Detector (
src/detector/stackDetector.ts):- Inspects target repository indicators (JS/TS, Python, Go, Rust, C/C++, C#, Java, Ruby, Elixir, GitHub Workflows, Docker, Terraform, Kubernetes, Claude Agent Harness, Tach, AST-Grep).
- Config Generator (
src/generator/configGenerator.ts):- Generates
lefthook.yml,.claude/hooks.json,biome.json,ruff.toml, and.aislop/config.yml.
- Generates
- ByteFence Pre-Write Broker & Spec Freezer (
src/broker/byteFence.ts):- Mediates atomic file writes, validates preimage SHA-256 digests, and freezes test directories against Builder modifications (
SPEC_TEST_FROZEN).
- Mediates atomic file writes, validates preimage SHA-256 digests, and freezes test directories against Builder modifications (
- LSPSanitizer (
src/sanitizer/lspSanitizer.ts):- Scrubs shell command injections (
curl | sh,npx,sudo) from external logs and MCP outputs (Agentjacking defense).
- Scrubs shell command injections (
- Diagnostic & SARIF Streamer (
src/formatter/):- Converts raw stderr/stdout from 11 tools into standard LSP envelopes or SARIF v2.1.0 logs with exact replacement fix regions.
- Provenance Engine (
src/attestation/provenance.ts):- Signs in-toto attestation receipts using ephemeral Ed25519 keypairs.
- Loop Breaker (
src/runner/loopBreaker.ts):- Tripwires a hard halt after $\ge 3$ consecutive identical failure iterations.
- Hook Installer & Lock-in (
src/installer/):- Sets up
.git/hooks/pre-commitand locks governance files to read-only (chmod 0444).
- Sets up
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.
- 1mo ago First seen · 95 lines · 1,031 tokens per session scan D d5b10e0c4f1f
Agent-Proof CLAUDE.md is an instructions file published in the GitHub repository Heretek-AI/Agent-Proof (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,031 tokens to every session, about $0.0041 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.