ghidra-reverse

ghidra-reverse is a skill for Claude Code, Codex from xAmirHamza77/ReverseOps-Skill. It costs 43 tokens per session (757 once invoked), scanned A, original, MIT.

A workflow for reverse-engineering software with Ghidra, an open-source tool that turns compiled programs into code-like views for inspection. It supports interactive or automated analysis when proprietary tools are unavailable.

In plain words
What is it for?
It is for importing and analyzing binaries, decompiling functions, tracing cross-references, running batch analysis, writing analysis scripts, and comparing binary changes.
Why use it?
It helps developers and security researchers understand unfamiliar binaries, locate important functions, and follow how a program works.

Skill for Claude CodeCodex

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

Good fit It is for importing and analyzing binaries, decompiling functions, tracing cross-references, running batch analysis, writing analysis scripts, and comparing binary changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xamirhamza77/reverseops-skill/ghidra-reverse
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 xAmirHamza77/ReverseOps-Skill --skill ghidra-reverse
Clone the repo
git clone --depth 1 https://github.com/xAmirHamza77/ReverseOps-Skill

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 ghidra-reverse

README.md
[![agentmods](https://agentmods.dev/badge/skills/xamirhamza77/reverseops-skill/ghidra-reverse/github.svg)](https://agentmods.dev/skills/xamirhamza77/reverseops-skill/ghidra-reverse)
Your own site
<a href="https://agentmods.dev/skills/xamirhamza77/reverseops-skill/ghidra-reverse"><img src="https://agentmods.dev/badge/skills/xamirhamza77/reverseops-skill/ghidra-reverse/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 ghidra-reverse

Your own site · 80×15
<a href="https://agentmods.dev/skills/xamirhamza77/reverseops-skill/ghidra-reverse"><img src="https://agentmods.dev/badge/skills/xamirhamza77/reverseops-skill/ghidra-reverse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 757 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00043 $0.00757
Opus 5 $0.00022 $0.00378
Sonnet 5 $0.00009 $0.00151
Haiku 4.5 $0.00004 $0.00076

Measured 6d ago against content hash 3ffabf2c7ba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ghidra-reverse 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 6d 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.

skills/ghidra-reverse/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ghidra Reverse Engineering

ACTION REQUIRED (execute immediately after reading)

  1. NOW: Read ../field-journal/precedent-reverse.md
  2. NOW: Confirm that Ghidra is needed (no IDA / open-source preference / batch headless)
  3. NEXT: Read ../tool-index.md for the ghidra / ghidra-mcp paths
  4. NEXT: If a tool is missing → bootstrap ghidra-mcp (if supported by the manifest) or install Ghidra following the manual steps
  5. ACT: Import the sample → run auto-analysis → export decompilation of key functions

Applicable scenarios

  • Primary reversing entry point when no IDA license is available
  • Batch headless analysis / decompilation in CI
  • Automation with Ghidra scripts (Java/Python Jython/PyGhidra)
  • Integration with binary-diff / patch-diff-exploit via ghidriff

Division of labor with IDA

Requirement Preferred
Existing IDA MCP for deep analysis ida-reverse/
Open source / batch / teaching This skill
CLI-only quick reconnaissance radare2/

Workflow

1. Project and auto-analysis

□ Create a new Project → Import the file → Analyze (default analyzers)
□ Record the language/compiler identification results and the base address
□ Mark the entry point, export table, and string xrefs

2. Key functions

□ Trace back from strings / imported APIs
□ Reconstruct the algorithm in the Decompile window
□ Rename functions/variables; write Plate comments
□ Hand off to Frida/GDB when dynamic analysis is needed (dynamic section of reverse-engineering)

3. Headless (batch)

# Example: the analyzeHeadless path varies by installation; MUST be taken from tool-index
analyzeHeadless /path/to/project Proj -import sample.bin -postScript ExportDecomp.py

4. MCP (if configured)

□ Confirm the ghidra MCP port (commonly 8765; tool-index is authoritative)
□ Pull decompilation / xrefs through MCP tools; never guess the port

Toolchain

Tool Purpose Bootstrap
Ghidra Main decompilation tool Manual release / package manager
ghidra-mcp AI bridge bootstrap capability name ghidra-mcp
ghidriff Patch diffing See patch-diff-exploit

Read the full file on GitHub · 89 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 89 lines · 43 tokens per session scan A 3ffabf2c7ba2

Subscribe to this mod's changes

ghidra-reverse is a skill published in the GitHub repository xAmirHamza77/ReverseOps-Skill (4 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 757 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

interacting-with-project-runtime

Interacting with a project's JVM runtime through the Kotlin REPL to execute focused probes against project classes and dependencies. Activate when behavior must be observed by running code; use using-gradle for build inspection or task execution.

rnett/gradle-mcp · 49 tokens

using-gradle

Using Gradle MCP tools to inspect and run existing builds, including projects, tasks, properties, dependencies, and build results. Activate for Gradle build operation and diagnosis; use authoring-gradle-builds when the build definition itself must change.

rnett/gradle-mcp · 53 tokens

debug-helper

Systematic debugging approach for identifying and fixing issues.

athola/skrills · 12 tokens

error-handling

Read the error codes these tools raise and decide whether to retry, fix the call, or stop.

saidsef/mcp-github-pr-issue-analyser · 19 tokens

wcode

Use the wcode plugin and its MCP tools for repository coding, review, debugging, refactoring, architecture, Graph/Design inspection, safe edits, command execution, and verification. Trigger whenever wcode is installed or named, even when its tools are lazily registered or omitted from the host's initial tool list.

francis-du/wcode · 66 tokens

inversion

"Invert, always invert." Apply Carl Jacobi's mathematical principle and Charlie Munger's investing wisdom to solve problems by thinking backward from failure. Use when: Goal setting - Define what would guarantee failure, then avoid it; Risk analysis - Identify what could destroy your project before starting; Decision…

guia-matthieu/clawfu-skills · 96 tokens