reverse-engineering-skill

reverse-engineering-skill is a skill for Claude Code, Codex from satiricalguru/Agents-skills. It costs 247 tokens per session (3,138 once invoked), scanned A, original, MIT.

A skill for examining compiled software such as desktop programs, phone apps, firmware, and installers to understand how they work. It covers decompiling code and inspecting binaries, which are packaged programs rather than editable source files.

In plain words
What is it for?
It is for inspecting functions, references, imports, and other details in Windows, macOS, Linux, Android, .NET, Java, and firmware files.
Why use it?
It provides a defined process for analysing programs when source code is unavailable or insufficient.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for inspecting functions, references, imports, and other details in Windows, macOS, Linux, Android, .NET, Java, and firmware files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/satiricalguru/agents-skills/reverse-engineering
Install

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.

Any agent
npx skills add satiricalguru/Agents-skills --skill reverse-engineering
Clone the repo
git clone --depth 1 https://github.com/satiricalguru/Agents-skills

Made for: Claude Code, Codex.

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 reverse-engineering-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/satiricalguru/agents-skills/reverse-engineering/github.svg)](https://agentmods.dev/skills/satiricalguru/agents-skills/reverse-engineering)
Your own site
<a href="https://agentmods.dev/skills/satiricalguru/agents-skills/reverse-engineering"><img src="https://agentmods.dev/badge/skills/satiricalguru/agents-skills/reverse-engineering/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 reverse-engineering-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/satiricalguru/agents-skills/reverse-engineering"><img src="https://agentmods.dev/badge/skills/satiricalguru/agents-skills/reverse-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 247 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00247 $0.03138
Opus 5.5 $0.00099 $0.01255
Sonnet 5 $0.00049 $0.00628
Haiku 4.5 $0.00025 $0.00314

Measured 10d ago against content hash 8a734e28a5a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-28, from the pricing page.

Security

Grade A, and why

reverse-engineering-skill scanned grade A with 1 finding 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 10d 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.

1. If user gave a file path, confirm it exists. If a URL, `curl -L -o /tmp/target <url>`.
skills/reverse-engineering-skill.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reverse Engineering Skill

You are an expert reverse engineer. When this skill triggers, your goal is full autonomous analysis — run the tools, interpret output, and produce actionable intelligence. Don't ask the user to do manual steps.

Read reverse-engineering-skill/references/tooling.md for installation commands before installing anything.
Read reverse-engineering-skill/references/report-template.md for the final report structure.
Read reverse-engineering-skill/references/mcp-backends.md for Ghidra/IDA/radare2-mcp server setup and tool APIs.
Read reverse-engineering-skill/references/cheatsheet.md during analysis for fast command lookup, import pattern recognition, and decision trees.


Tool Priority: Which Backend to Use

Check what's available in this order — use the first one that's connected:

  1. GhidraMCP / GhidrAssistMCP (best decompilation quality — 31 tools, free)
    → If Ghidra is running with MCP enabled, use list_functions, decompile_function, xrefs_to, etc.
  2. IDA Pro MCP (commercial, highest quality for stripped binaries)
    → If IDA is running with mcp-server, use the same function/xref API calls
  3. radare2-mcp (official, r2-mcp binary — CLI-native, great for automation)
    → Translates r2 commands into MCP tool calls
  4. Built-in FastMCP server (re_mcp_server.py — always available, no external tools needed)
    → Falls back to this if none of the above are running

When using Ghidra/IDA/radare2-mcp, always start with get_program_info before anything else.


Phase 0: Resolve & Orient

  1. If user gave a file path, confirm it exists. If a URL, curl -L -o /tmp/target <url>.
  2. If the target is an archive (.zip, .tar, .gz, .ipa, .aab), extract it first.
  3. Detect format using inspect_binary (built-in) or get_program_info (Ghidra/IDA/r2-mcp).
  4. Determine the analysis goal — pick the right workflow below:
    • Malware triage → Malware Analysis workflow
    • CVE/vuln hunting → Vulnerability Research workflow
    • CTF challenge → CTF workflow
    • General understanding → Standard Triage workflow
    • Firmware → Firmware workflow

Read the full file on GitHub · 259 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. 10d ago First seen · 259 lines · 247 tokens per session scan A 8a734e28a5a3

Subscribe to this mod's changes

reverse-engineering-skill is a skill published in the GitHub repository satiricalguru/Agents-skills (6 stars, last pushed 8d ago), licensed MIT. It adds 247 tokens to every session and 3,138 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-18.

Related

Other skills, from other repositories

vscode-doctor

Diagnose slow or freezing VS Code-compatible editors with evidence-first, zero-hardcoded-assumption workflow. Use when the user reports editor lag, typing delay, UI freezes, extension host stalls, file watcher noise, high editor CPU/RSS, uses VS Code/Cursor as a file browser over a large folder, or wants a safe editor…

majiayu000/spellbook · 75 tokens

review-agent-harness

Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. Use when asked to assess agent readiness, repeated agent failures, Rules/Skills/Hooks/Memory effectiveness, missing validation or recovery loops, or whether a…

majiayu000/spellbook · 90 tokens

codebase-audit

A read-only method for auditing an entire codebase across contracts, data integrity, errors, security, architecture, technical debt, configuration, and caching. It produces prioritized findings and a repair roadmap.

majiayu000/spellbook · 176 tokens

codex-agent

Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.

majiayu000/spellbook · 45 tokens

codex-log-guard

Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user mentions logs2.sqlite, logs2.sqlite-wal, blockloginserts, SSD/TBW wear, or explicitly asks to protect, clean up, verify, or restore Codex diagnostic logging.

majiayu000/spellbook · 68 tokens

flowguard

Guard long, ambiguous, or stateful AI-agent work from drift. Use when the user asks to run or continue a multi-step task, autonomous loop, bug fix, repo change, PR readiness check, compaction handoff, resume from previous context, cost-control checkpoint, or any task likely to span many tool calls, files, sessions…

majiayu000/spellbook · 78 tokens