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 skills/fire3/aida-audit/aida-cli-mcp-guidenpx skills add fire3/aida-audit --skill aida-cli-mcp-guidegit clone --depth 1 https://github.com/fire3/aida-auditWrote 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/skills/fire3/aida-audit/aida-cli-mcp-guide)<a href="https://agentmods.dev/skills/fire3/aida-audit/aida-cli-mcp-guide"><img src="https://agentmods.dev/badge/skills/fire3/aida-audit/aida-cli-mcp-guide.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 5.1 | $0.00013 | $0.01565 |
| Opus 5 | $0.00006 | $0.00783 |
| Sonnet 5 | $0.00003 | $0.00313 |
| Haiku 4.5 | $0.00001 | $0.00156 |
Grade A, and why
aida-audit-guide 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDA MCP Reverse Engineering Skills Guide
This document aims to guide users (and AI models) on how to efficiently perform reverse engineering using the toolset provided by AIDA MCP. We decompose the analysis process into common "Skill Patterns", where each pattern corresponds to a specific sequence of tool calls.
1. Core Concepts
- Binary Name (binary_name): The
binary_namehere usually refers to the filename of the IDA database (without extension, or depending on the specific loading context), for example,chilli. This parameter is required when using all tools specific to a binary. - Address: Addresses typically support Hexadecimal Strings (e.g.,
"0x401000") or Integers (e.g.,4198400). - Context: Analysis is not isolated; it usually requires combining Disassembly, Pseudocode, and Cross-References (Xrefs) to understand.
2. Skill Patterns
2.1 Exploration & Overview
Scenario: Starting to analyze a new binary file and needing to understand its basic structure, exported functions, and referenced external libraries.
- List all binary files:
get_project_binaries()- Purpose: Determine what analysis targets are currently available.
- View Exported Functions (Public API):
list_binary_exports(binary_name)- Purpose: Understand what functionality this module provides externally (if it is a DLL/SO).
- View Imported Functions (Dependencies):
list_binary_imports(binary_name)- Purpose: Understand what external functionality this module depends on (e.g., network
socket, fileCreateFile, encryptionCrypt, etc.).
- Purpose: Understand what external functionality this module depends on (e.g., network
- Browse Internal Functions:
list_binary_functions(binary_name, limit=20)- Purpose: Get a list of functions, can be used with
offsetfor pagination.
- Purpose: Get a list of functions, can be used with
2.2 String Analysis
Scenario: The program outputs specific error messages or logs, or specific text is displayed on the interface, and you want to find the code logic that handles this text.
- Search Strings:
search_strings(search_string="Error", match="contains")- Purpose: Search for the string in all binaries. If the binary is known,
search_string_symbol_in_binarycan also be used. - Output: Get the
addressof the string (e.g.,0x4050A0).
- Purpose: Search for the string in all binaries. If the binary is known,
- Find References (Xrefs):
get_string_xrefs(binary_name, string_address="0x4050A0")- Purpose: Find who uses this string.
- Output: Get a list of code addresses referencing this string (e.g.,
0x401200).
- Locate Code:
get_disassembly_context(binary_name, address="0x401200")- Purpose: View the assembly code context at the reference location to analyze the logic.
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.
- 6d ago First seen · 92 lines · 13 tokens per session scan A 7cb2fbea5757
aida-audit-guide is a skill published in the GitHub repository fire3/aida-audit (5 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 1,565 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
deep-analysis
Performs focused, depth-first investigation of specific reverse engineering questions through iterative analysis and database improvement. Answers questions like "What does this function do?", "Does this use crypto?", "What's the C2 address?", "Fix types in this function". Makes incremental improvements (renaming…
ctf-rev
Solve CTF reverse engineering challenges using systematic analysis to find flags, keys, or passwords. Use for crackmes, binary bombs, key validators, obfuscated code, algorithm recovery, or any challenge requiring program comprehension to extract hidden information.
pyghidra-scripting
Write and run Python (PyGhidra) code inside the Ghidra session that ReVa's MCP server is already attached to, using the five ReVa scripting tools — run-script, list-scripts, read-script, write-script, edit-script. Use this whenever the user asks to execute Python against the current program, reach for the Ghidra Flat…
binary-triage
Performs initial binary triage by surveying memory layout, strings, imports/exports, and functions to quickly understand what a binary does and identify suspicious behavior. Use when first examining a binary, when user asks to triage/survey/analyze a program, or wants an overview before deeper reverse engineering.
IDA Scripting
Write and execute IDAPython scripts — full API reference included.
Smart Patch (IDA Pro)
Patch binary code in IDA Pro using natural language — read, assemble, write, verify.