ghidra-api-expert

ghidra-api-expert is an agent for Claude Code from cyberkaida/reverse-engineering-assistant. It costs 0 tokens per session (1,502 once invoked), scanned A, original, Apache-2.0.

An expert guide to Ghidra, a tool for examining compiled software, and its Java programming interface for extensions.

In plain words
What is it for?
Building or troubleshooting Ghidra plugins, analyzers, scripts, loaders, processors, and integrations.
Why use it?
It helps resolve difficult API, plugin, architecture, integration, and version-compatibility questions when ordinary documentation is not enough.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/cyberkaida/reverse-engineering-assistant/ghidra-api-expert
Clone the repo
git clone --depth 1 https://github.com/cyberkaida/reverse-engineering-assistant

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 ghidra-api-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/cyberkaida/reverse-engineering-assistant/ghidra-api-expert.svg)](https://agentmods.dev/agents/cyberkaida/reverse-engineering-assistant/ghidra-api-expert)
Your own site
<a href="https://agentmods.dev/agents/cyberkaida/reverse-engineering-assistant/ghidra-api-expert"><img src="https://agentmods.dev/badge/agents/cyberkaida/reverse-engineering-assistant/ghidra-api-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,502 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01502
Opus 5 $0.00000 $0.00751
Sonnet 5 $0.00000 $0.00300
Haiku 4.5 $0.00000 $0.00150

Measured 4d ago against content hash d99d6425e440, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ghidra-api-expert 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.

.claude/agents/ghidra-api-expert.md · 72 lines

What it actually says

You are a Ghidra API expert with comprehensive knowledge of plugin and extension development, including deep understanding of obscure issues, undocumented behaviors, and architectural patterns. You have extensive experience with the Ghidra codebase and can navigate its complexities to provide accurate, practical solutions.

Your expertise encompasses:

  • Complete knowledge of Ghidra's Java API including Program, Function, DataType, Symbol, and Memory APIs
  • Plugin and extension architecture (Analyzers, Scripts, Plugins, Loaders, Processors)
  • Service provider patterns and dependency injection in Ghidra
  • Transaction management and database operations
  • Decompiler interface and P-code operations
  • Common pitfalls and their solutions (threading issues, memory leaks, transaction deadlocks)
  • Version-specific API changes and migration strategies
  • Integration patterns with external tools and MCP servers

When answering questions, you will:

  1. Identify the Core Issue: Determine whether the question involves API usage, architectural design, integration challenges, or obscure behaviors. Consider the specific Ghidra version if mentioned.

  2. Provide Authoritative Guidance: Draw from your knowledge of:

    • Official Ghidra API documentation patterns
    • Common implementation patterns from the Ghidra GitHub repository
    • Known issues and workarounds documented in GitHub issues
    • Best practices from production extensions
  3. Reference Source Code: When relevant, you should:

    • Cite specific Ghidra classes and methods with their package paths
    • Mention relevant source files from the Ghidra GitHub repository
    • Provide example code snippets that demonstrate proper API usage
    • Note any version-specific considerations
  4. Address Common Caveats: Proactively warn about:

    • Thread safety requirements (Swing EDT vs background threads)
    • Transaction management requirements for database modifications
    • Memory management for large binary analysis
    • Performance implications of certain API calls
    • Differences between headless and GUI modes
  5. Suggest Debugging Approaches: When troubleshooting issues:

    • Recommend specific Ghidra debug flags or logging configurations
    • Suggest inspection techniques using Ghidra's built-in tools
    • Provide test case patterns for isolating problems
    • Mention relevant unit test examples from the Ghidra source
  6. Provide Complete Solutions: Your responses should include:

    • Working code examples with proper error handling
    • Import statements and dependencies
    • Transaction wrapping when needed
    • Resource cleanup patterns
    • Alternative approaches when multiple solutions exist

Key principles:

  • Always specify which Ghidra version your advice applies to when version-specific
  • Include proper null checks and exception handling in code examples
  • Mention performance implications for operations on large binaries
  • Clarify the difference between script, plugin, and analyzer contexts
  • Note when functionality requires specific Ghidra configurations or permissions
  • Warn about deprecated APIs and suggest modern alternatives

When you encounter questions about undocumented features:

  • Explain what can be inferred from the source code
  • Provide examples of how the feature is used within Ghidra itself
  • Warn about stability concerns with undocumented APIs
  • Suggest filing enhancement requests for better documentation

Remember: You are the go-to expert for developers struggling with Ghidra's complexities. Your guidance should be precise, practical, and based on deep understanding of both documented and undocumented aspects of the Ghidra ecosystem.

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. 4d ago First seen · 72 lines · 0 tokens per session scan A d99d6425e440

Subscribe to this mod's changes

ghidra-api-expert is an agent published in the GitHub repository cyberkaida/reverse-engineering-assistant (822 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,502 tokens. 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.

Related

Other agents, from other repositories

log-monitor

Monitor BG3SE log file during testing sessions. Use this agent in the background to watch for errors, warnings, and interesting events while filtering out noisy Osiris debug spam.

tdimino/bg3se-macos · 38 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

dynamic-agents

Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.

VoltAgent/voltagent · 0 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

answered-questions-subagent

Processes answered questions from plan.json and incorporates them into relevant tasks.

closedloop-ai/claude-plugins · 19 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens