agentmods.dev

vuln-scout: Instructions file for Claude Code

CLAUDE.md

vuln-scout CLAUDE.md is an instructions file for Claude Code from allsmog/vuln-scout. It costs 789 tokens per session, scanned A, original, MIT.

Development instructions for VulnScout, a Claude Code add-on for white-box penetration testing, which checks source code for security weaknesses across nine languages, including Solidity smart contracts.

In plain words
What is it for?
Running full security audits, threat modelling, finding dangerous functions, handling large codebases, and checking whether suspected vulnerabilities are false positives.
Why use it?
It gives the coding agent the project layout, commands, and security-review methods needed to work consistently in the repository.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code.

This is allsmog/vuln-scout's own configuration. It tells Claude Code how to work on vuln-scout 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 vuln-scout configures →

not rated 24repo 2mo ago A scan 789 tokens original MIT
View source ↗ allsmog/vuln-scout
Reuse

Borrowing it

Nothing to install: this file belongs to allsmog/vuln-scout. 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/allsmog/vuln-scout/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/allsmog/vuln-scout

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 vuln-scout CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/allsmog/vuln-scout/claude-md/github.svg)](https://agentmods.dev/instructions/allsmog/vuln-scout/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/allsmog/vuln-scout/claude-md"><img src="https://agentmods.dev/badge/instructions/allsmog/vuln-scout/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.

agentmods 80×15 button for vuln-scout CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/allsmog/vuln-scout/claude-md"><img src="https://agentmods.dev/badge/instructions/allsmog/vuln-scout/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 789 This file is loaded in full into every session.
When invoked 789 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 $0.00789 $0.00789
Opus 5 $0.00394 $0.00394
Sonnet 5 $0.00158 $0.00158
Haiku 4.5 $0.00079 $0.00079

Measured 9d ago against content hash 2e15a8c9ee04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vuln-scout 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 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.

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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VulnScout - Development Guide

A Claude Code plugin for whitebox penetration testing, supporting 9 languages including Solidity smart contracts.

Project Structure

vuln-scout/
├── .claude-plugin/plugin.json  # Plugin manifest
├── agents/                      # Autonomous security analysts
├── commands/                    # Slash commands (/full-audit, /scope, etc.)
├── hooks/                       # Background automation
├── skills/                      # Auto-activated knowledge modules
└── scripts/                     # Helper scripts (Joern queries, etc.)

Key Commands

  • /vuln-scout:full-audit - Main entry point for security audits
  • /vuln-scout:scope - Handle large codebases with compression
  • /vuln-scout:threats - STRIDE threat modeling
  • /vuln-scout:sinks - Find dangerous functions
  • /vuln-scout:verify - CPG-based false positive verification

Development Notes

  • Skills are in skills/ with a SKILL.md and optional references/ folder
  • Agents are markdown files in agents/ with frontmatter
  • Commands are markdown files in commands/ with YAML frontmatter
  • Hooks are in hooks/ for event-driven automation
  • Prompt-first orchestration artifacts live in .claude/audit-plan.md and .claude/review-ledger.json
  • Prompt eval definitions live in vuln-scout/evals/; validate with python3 vuln-scout/scripts/validate_evals.py

Supported Languages

Go, TypeScript/JS, Python, Java, Rust, PHP, C#/.NET, Ruby, Solidity

External Tools

  • Semgrep - Fast pattern matching
  • Joern - Code Property Graph analysis
  • Slither - Solidity static analysis
  • repomix - Codebase compression for large repos

Release Checklist

Before tagging a release, verify:

  • python3 vuln-scout/scripts/check_consistency.py passes
  • Skill count matches across root README, vuln-scout/README.md, and filesystem (ls skills/)
  • Agent and command counts match across both READMEs
  • OWASP mapping language uses official OWASP Top 10 names in public docs
  • Every skill directory has a SKILL.md entry point
  • Every command's argument-hint includes all flags documented in its body
  • No stale command references (bare /audit, /scan without whitebox-pentest: prefix)
  • references/findings.schema.json is the shared source of truth for /scan, /verify, and /full-audit
  • .claude/audit-plan.md sections match the prompt-orchestration contract in scripts/prompt_artifacts.py
  • .claude/review-ledger.json shape matches scripts/prompt_artifacts.py
  • findings.json field conventions are consistent across scan.md, verify.md, full-audit.md, and report.md
  • stable_key, kind, source_tool, and evidence are present anywhere findings are documented
  • hotspot vs finding semantics are consistent across commands, agents, and examples
  • --since-commit, --suppressions, --fail-on, and --format are documented wherever supported
  • whitebox-pentest-state.json schema matches between full-audit.md and session-init.md
  • python3 vuln-scout/scripts/validate_evals.py passes before running prompt benchmarks

Read the full file on GitHub · 65 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. 9d ago First seen · 65 lines · 789 tokens per session scan A 2e15a8c9ee04

Subscribe to this mod's changes

vuln-scout CLAUDE.md is an instructions file published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 789 tokens to every session, about $0.0039 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 2026-08-30.

Claude CodeSecurityappsecclaude-code-pluginsastsemgrepthreat-modeling
Related

Other instructions, from other repositories

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

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 · 5,153 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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens