ghidra

ghidra is a skill for Claude Code, Codex from MingyiSecLab/Mingyi-Atlas. It costs 47 tokens per session (642 once invoked), scanned A, original, Apache-2.0.

A reverse-engineering toolkit for examining compiled programs with Ghidra, a free tool that turns machine code into a more readable representation. It supports analyzing program structure, listing functions, following cross-references, and producing C-like pseudocode.

In plain words
What is it for?
Use it to analyze executables, decompile functions, inspect imports and exports, trace references, emulate P-code, and run analyses in batches.
Why use it?
When source code is unavailable, compiled code is difficult to understand directly. This helps investigators see what a binary contains and how its parts connect.

Skill for Claude CodeCodex

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

Good fit Use it to analyze executables, decompile functions, inspect imports and exports, trace references, emulate P-code, and run analyses in batches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mingyiseclab/mingyi-atlas/ghidra
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 MingyiSecLab/Mingyi-Atlas --skill ghidra
Clone the repo
git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlas

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/ghidra"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/ghidra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 642 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 $0.00047 $0.00642
Opus 5 $0.00023 $0.00321
Sonnet 5 $0.00009 $0.00128
Haiku 4.5 $0.00005 $0.00064

Measured 7d ago against content hash eedccbc8034b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ghidra 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 7d 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.

the complete bethington/ghidra-mcp tool surface via bash + curl:
src/skills/standard/reverser/ghidra/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ghidra Deep Analysis

Ghidra is the primary reverse engineering backend. Two modes:

  • MCP bridge (preferred) — 245 tools via HTTP at $GHIDRA_MCP_URL
  • Headless (fallback) — analyzeHeadless + postScript for JSON output

Prerequisites

ghidra_status()

Check if Ghidra headless and/or MCP bridge are available.

1. Full Analysis

ghidra_analyze(binary="/workspace/target.exe")

Returns: functions (up to 500), imports, exports, language, image base. Auto-selects MCP if running, headless otherwise.

2. Decompile a Function

ghidra_decompile(binary="/workspace/target.exe", function="main")
ghidra_decompile(binary="/workspace/target.exe", function="0x401000")

Accepts symbol name or hex address. Returns C pseudocode.

3. Cross-References (MCP)

ghidra_xrefs(binary="/workspace/target.exe", address="0x401000")

Returns up to 200 xrefs with source function context.

4. Fallback: Script Generation

If headless/MCP are unavailable, generate a recon script and run via bash:

bin_ghidra_script(binary="/workspace/target.exe")

MCP Bridge — Full 245-Tool Coverage

When the Ghidra MCP bridge is running, the reverser also has access to the complete bethington/ghidra-mcp tool surface via bash + curl:

  • Function analysis — decompilation, call graphs, completeness scoring
  • Data flow — PCode-graph value propagation (forward / backward)
  • Structure discovery — struct/union/enum creation, field analysis
  • String extraction — regex search, quality filtering
  • Import/export analysis — symbol tables, ordinal resolution
  • Memory inspection — raw reads, byte pattern search
  • Cross-binary documentation — SHA-256 function hash matching
  • P-code emulation — run functions in isolation, brute-force API hashes
  • Batch operations — bulk rename, comment, type (93% fewer API calls)
  • Script management — create, run, update Ghidra scripts via MCP
  • Convention enforcement — auto-fix naming, type safety, documentation

Read the full file on GitHub · 66 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. 7d ago First seen · 66 lines · 47 tokens per session scan A eedccbc8034b

Subscribe to this mod's changes

ghidra is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 642 once invoked, about $0.0002 per session on Opus 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 2026-09-03.