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/alphacrack/iac-scanner/claude-mdgit clone --depth 1 https://github.com/alphacrack/iac-scannerWrote 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/alphacrack/iac-scanner/claude-md)<a href="https://agentmods.dev/instructions/alphacrack/iac-scanner/claude-md"><img src="https://agentmods.dev/badge/instructions/alphacrack/iac-scanner/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 | $0.01699 | $0.01699 |
| Opus 5 | $0.00849 | $0.00849 |
| Sonnet 5 | $0.00340 | $0.00340 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
iac-scanner 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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this project is
iac-scanner is a Python CLI (iac-scan) and MCP server (iac-scan-mcp) that scans Terraform (main.tf) and AWS CDK (index.ts/index.js) IaC, then uses an LLM to both generate findings (structured output) and produce fixed code. It is AI-augmented, not rule-only — it complements Checkov/tfsec/KICS rather than replacing them. Version is derived from git tags (signed vX.Y.Z) by setuptools-scm; pyproject.toml has dynamic = ["version"] and no hardcoded version. The package reads the version from _version.py (written at build time) or falls back to importlib.metadata.
Commands
# Setup
pip install -e ".[dev]" # editable install + dev deps
pre-commit install # ruff + bandit + gitleaks + hygiene
# Test
pytest tests/ -m "not e2e" # fast suite (mocked LLM, no keys)
pytest tests/ -m smoke # CLI end-to-end smoke
pytest tests/ -m e2e # opt-in: real provider APIs, needs keys
pytest tests/test_runner.py -v # single file
pytest tests/test_runner.py::test_name # single test
pytest tests/ --cov=iac_scanner # coverage (CI threshold 80%, target 90%)
# Lint / type / security
ruff check src/ tests/ # lint
ruff format src/ tests/ # format
mypy src/iac_scanner # CI hard-fails on any issue (strict mode)
bandit -r src/ -ll -c pyproject.toml
pip-audit
# Version + release (tag-driven, setuptools-scm)
make version # print version setuptools-scm would emit
make release-dry # preview a patch release
make release-patch | release-minor | release-major # promote CHANGELOG + signed tag
# then: git push --follow-tags origin <branch> # tag push → GitHub Release → PyPI publish
Make targets mirror most of the above (make test, make lint, make check, make build).
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.
- 3d ago First seen · 81 lines · 1,699 tokens per session scan A 6dd6684b0a4c
iac-scanner CLAUDE.md is an instructions file published in the GitHub repository alphacrack/iac-scanner (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 1,699 tokens to every session, about $0.0085 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
chainloop CLAUDE.md
Claude Code instructions for chainloop-dev/chainloop, covering claude.md, architecture, control plane (app/controlplane/), artifact cas (app/artifact-cas/) and cli (app/cli/).
secure-sdlc-agents CLAUDE.md
Claude Code instructions for Kaademos/secure-sdlc-agents, covering secure sdlc — multi-agent orchestration, agent roster, lifecycle phases & handoffs, 1. plan and 2. design.
ai-safe2-framework AGENTS.md
AGENTS.md instructions for CyberStrategyInstitute/ai-safe2-framework, covering ai safe² v3.1 agent entry point, start here, version model, normative interpretation and enforcement planes.
controlkeel AGENTS.md
AGENTS.md instructions for aryaminus/controlkeel, covering controlkeel governance, issue and pr quality, planning and architecture, project commands and phoenix v1.8.
sicario-spec AGENTS.md
AGENTS.md instructions for dfirs1car1o/sicario-spec: For additional context about technologies to be used, project structure, shell commands, and other important information, read the current plan.
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).