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/asaiuta/reverse-workbench-skill/claude-mdgit clone --depth 1 https://github.com/Asaiuta/reverse-workbench-skillWrote 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/asaiuta/reverse-workbench-skill/claude-md)<a href="https://agentmods.dev/instructions/asaiuta/reverse-workbench-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/asaiuta/reverse-workbench-skill/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 | $0.00341 | $0.00341 |
| Opus 5 | $0.00170 | $0.00170 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
reverse-workbench-skill 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 4d 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.
This is a copy
91% identical to reverse-skill CLAUDE.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
CLAUDE.md
This repository is a task skill router for authorized reverse engineering, mobile/security analysis, and pentest workflows.
On Any Task
RULES.md is the single source of truth for behavior chain and authorization.
Routing order:
skills/MASTER-ROUTING.mdorskills/scripts/master-route.ps1 -Hint "..."skills/scripts/case-init.ps1→work/<case>/scope.md(must grant auth before ACT)skills/routing.mdwhen ambiguous; roles inskills/ops/role-map.md- Open PRIMARY
SKILL.mdand execute ACTION REQUIRED - Timeline/workitems + Evidence→Finding→Path (
skills/ops/) skills/tool-index.mdfor real tool paths (never guess)- Missing tool →
skills/scripts/bootstrap-reverse.ps1(manifest capabilities only)
Identity: lightweight skill router — see skills/ops/IDENTITY.md (not a Z3r0 platform).
First-Run Setup
skills/tool-index.md is not in fresh clones. Generate it:
# Windows
powershell -NoProfile -ExecutionPolicy Bypass -File skills/scripts/refresh-tool-index.ps1
# macOS / Linux
bash skills/scripts/refresh-tool-index.sh
# Kali
bash kali/scripts/refresh-tool-index.sh
Read README_AI.md for full bootstrap sequence.
Coherence check
powershell -NoProfile -ExecutionPolicy Bypass -File skills/scripts/verify-routing-coherence.ps1
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.
- 4d ago First seen · 43 lines · 341 tokens per session scan A a400cec43302
reverse-workbench-skill CLAUDE.md is an instructions file published in the GitHub repository Asaiuta/reverse-workbench-skill (2 stars, last pushed 20d ago), licensed MIT. It adds 341 tokens to every session, about $0.0017 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to reverse-skill CLAUDE.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
pentest-ai AGENTS.md
AGENTS.md instructions for 0xSteph/pentest-ai, covering agent guide for pentest-ai, build, test, lint, types, format and layout.
SecAtlas AGENTS.md
AGENTS.md instructions for shuaiqideyu/SecAtlas, covering agents.md — secatlas 多 agent 协作入口, 这是什么, 快速接入（3步）, 1. 注册你的 agent and 2. 选模板，创建内容.
pentest-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/pentest-mcp-server, covering developer protocol, core rules, patterns, tool (representative — pentestlookuptechnique) and server instructions.
pentest-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/pentest-mcp-server, covering developer protocol, core rules, patterns, tool (representative — pentestlookuptechnique) and server instructions.
cyber-agent CLAUDE.md
Claude Code instructions for waybarrios/cyber-agent, covering cyber agent - claude code instructions, how to use the agents, step 1: navigate to the project, step 2: start claude code and step 3: view available agents.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.