Borrowing it
Nothing to install: this file belongs to bawbel/scanner. 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/bawbel/scanner/main/CLAUDE.mdgit clone --depth 1 https://github.com/bawbel/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/bawbel/scanner/claude-md)<a href="https://agentmods.dev/instructions/bawbel/scanner/claude-md"><img src="https://agentmods.dev/badge/instructions/bawbel/scanner/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/bawbel/scanner/claude-md"><img src="https://agentmods.dev/badge/instructions/bawbel/scanner/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 | $0.05253 | $0.05253 |
| Opus 5.5 | $0.02101 | $0.02101 |
| Sonnet 5.5 | $0.01051 | $0.01051 |
| Haiku 4.5 | $0.00525 | $0.00525 |
Grade A, and why
scanner CLAUDE.md scanned grade A with 2 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# How: urllib.request with 10s timeout, reads up to MAX_CONTENT_BYTES Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Never `eval()`, `exec()`, `subprocess.run(shell=True)`, How it starts
The opening of the file, as written. The whole thing — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bawbel Scanner — CLAUDE.md
Read first:
PROJECT_CONTEXT.md— business, product, and founder context. Then read: this file — code conventions and hard rules. Then read:.claude/<topic>.md— detailed guidance for specific tasks.When working on any task, also check
.claude/skills/for reusable task-specific instructions (security review, adding rules, writing tests, etc.)
.claude/is gitignored (.gitignore), so the.claude/files named in this document are local to the maintainer and are not in the repository.
Repository Structure
scanner/
├── CLAUDE.md ← YOU ARE HERE
├── PROJECT_CONTEXT.md ← Business context (gitignored)
├── PROJECT_CONTEXT.example.md ← Template for contributors
│
├── .claude/ ← AI context files
│ ├── architecture.md
│ ├── security.md
│ ├── testing.md
│ ├── contributing.md
│ ├── commands.md
│ ├── dev-workflow.md
│ └── skills/ ← Reusable task skills
│ ├── security-review.md
│ ├── add-detection-rule.md
│ ├── add-engine.md
│ └── write-test.md
│
├── scanner/ ← Core package
│ ├── __init__.py ← Package version
│ ├── scanner.py ← Orchestrator only — scan() entry point
│ ├── utils.py ← Shared helpers — always use, never inline
│ ├── messages.py ← ALL strings — errors, logs, UI text
│ ├── config/default.py ← ALL config: limits, paths, env vars
│ ├── cli/ ← CLI entry point (Click + Rich), scanner.cli:main
│ ├── models/ ← Data models
│ │ ├── __init__.py ← Exports Finding, ScanResult, Severity
│ │ ├── finding.py ← Finding dataclass + Severity enum
│ │ └── result.py ← ScanResult dataclass
│ ├── engines/ ← One file per detection engine
│ │ ├── __init__.py ← Engine registry + exports
│ │ ├── magika_engine.py ← Stage 0: Magika file type verification
│ │ ├── pattern_engine.py ← Stage 1a: regex (stdlib, always runs)
│ │ ├── yara_engine.py ← Stage 1b: YARA (optional)
│ │ ├── semgrep_engine.py ← Stage 1c: Semgrep (optional)
│ │ ├── llm_engine.py ← Stage 2: LLM (optional)
│ │ ├── sandbox_engine.py ← Stage 3: behavioral sandbox
│ │ └── meta_analyzer.py ← FP-4 meta-analyzer
│ └── rules/
│ ├── yara/ave_rules.yar ← YARA rules
│ └── semgrep/ave_rules.yaml ← Semgrep rules
│
├── tests/
│ ├── test_scanner.py ← Golden fixture and core tests
│ ├── unit/ ← Unit tests per module
│ │ ├── engines/ ← Engine-specific tests
│ │ └── models/ ← Model tests
│ ├── integration/ ← End-to-end tests
│ └── fixtures/
│ ├── skills/
│ │ └── malicious/
│ │ └── malicious_skill.md ← GOLDEN FIXTURE: never modify
│ ├── golden/ ← Recorded golden scan output
│ └── mcp/ ← MCP manifest fixtures
│
├── scripts/
│
├── Dockerfile
├── docker-compose.yml
├── pyproject.toml
├── requirements.txt
├── .pre-commit-config.yaml
├── .github/workflows/
│ ├── ci.yml
│ ├── pr-review.yml
│ └── publish.yml
├── .gitignore
└── .dockerignore
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.
- 9d ago Changed · +1 lines · +30 tokens per session 84bc57400dfb
- 10d ago Changed · +5 lines · +134 tokens per session 9c3bf5db23e0
- 1mo ago First seen · 555 lines · 5,089 tokens per session scan A 942459ceed90
scanner CLAUDE.md is an instructions file published in the GitHub repository bawbel/scanner (12 stars, last pushed 2d ago), licensed Apache-2.0. It adds 5,253 tokens to every session, about $0.0210 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). 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.