Binary Modification

Binary Modification is a skill for Claude Code, Codex from buzzer-re/Rikugan. It costs 17 tokens per session (917 once invoked), scanned A, original, MIT.

A workflow for changing the behavior of a compiled program from a natural-language request. It explores the binary, identifies relevant functions and instructions, then applies and saves a minimal patch.

In plain words
What is it for?
Use it to inspect executables, find code related to a requested behavior, and patch that behavior with binary-analysis tools.
Why use it?
It gives binary changes a traceable investigation and verification process before modifying the file.

Skill for Claude CodeCodex

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 skills/buzzer-re/rikugan/modify
Any agent
npx skills add buzzer-re/Rikugan --skill modify
Clone the repo
git clone --depth 1 https://github.com/buzzer-re/Rikugan

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 Binary Modification

README.md
[![agentmods](https://agentmods.dev/badge/skills/buzzer-re/rikugan/modify.svg)](https://agentmods.dev/skills/buzzer-re/rikugan/modify)
Your own site
<a href="https://agentmods.dev/skills/buzzer-re/rikugan/modify"><img src="https://agentmods.dev/badge/skills/buzzer-re/rikugan/modify.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 917 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 $0.00017 $0.00917
Opus 5 $0.00009 $0.00458
Sonnet 5 $0.00003 $0.00183
Haiku 4.5 $0.00002 $0.00092

Measured 4d ago against content hash 505eb37b75e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Binary Modification 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.

rikugan/skills/builtins/modify/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task: Modify the binary's behavior based on the user's natural language description. You will autonomously explore the binary to understand it, formulate a concrete plan, and apply minimal patches.

Phase 1: Exploration Strategy

Your goal is to build enough understanding of the binary to know WHERE and HOW to make the requested change. Use exploration_report to log every significant finding.

Step 1: Orientation (1-2 turns)

  • get_binary_info — architecture, format, size
  • list_imports + list_exports — what APIs does the binary use?
  • search_strings / list_strings_filter with keywords from the user's request
    • For a game mod request mentioning "snake", search for: "snake", "score", "point", "length", "size", "spawn", "init", "level", "life", "speed"
    • Cast a wide net with goal-relevant keywords

Step 2: Targeted Search (2-5 turns)

  • From string hits, use xrefs_to to find which functions reference them
  • From import hits, use xrefs_to to find call sites
  • search_functions for names containing relevant keywords
  • Build a shortlist of candidate functions
  • Log each candidate with exploration_report(category="function_purpose")

Step 3: Deep Dive (3-10 turns)

  • decompile_function on the most promising candidates
  • Trace data flow: where does the target value come from? Where is it used?
  • Identify exact instructions and constants that control the behavior
  • Use get_il for detailed intermediate representation when needed
  • Form concrete hypotheses and log with exploration_report(category="hypothesis")
    • Example: "Changing the constant 3 at 0x401248 to 6 would double the snake's initial length"
    • Example: "Multiplying the score increment at 0x4015C2 by 2 would double points"

Step 4: Transition Decision

  • When you have identified ALL locations that need to change, call phase_transition(to_phase="plan")
  • If you're stuck or the binary is too complex, use ask_user to get hints
  • Don't transition too early — make sure you understand the full picture

Read the full file on GitHub · 83 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. 4d ago First seen · 83 lines · 17 tokens per session scan A 505eb37b75e9

Subscribe to this mod's changes

Binary Modification is a skill published in the GitHub repository buzzer-re/Rikugan (672 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 917 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 2026-08-30.

Related

Other skills, from other repositories

spike

Throwaway experiments to validate an idea before build.

mateaix/mateclaw · 13 tokens

environment-discovery

Systematic exploration of unknown environments before starting work.

vstorm-co/pydantic-deepagents · 13 tokens

trtllm-codebase-exploration

Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations. Teaches how to discover existing infrastructure, trace code paths, and avoid reimplementing what already exists. Derived from real mistakes where 250 lines of code were written and deleted because existing…

NVIDIA/TensorRT-LLM · 92 tokens

forgetful-files

File binary content into the knowledge base — screenshots, PDFs, diagrams, fonts, assets. Use when a binary artifact is worth keeping alongside knowledge, or when a stored procedure needs a bundled asset. The description is the entire search surface: say what the file shows and when to reach for it.

ScottRBK/forgetful · 63 tokens

arkana-analyze

Binary analysis skill for Arkana. Handles malware triage, reverse engineering, PE/ELF/Mach-O analysis, shellcode emulation, firmware inspection, vulnerability auditing, C2 config extraction, unpacking, deobfuscation, and threat intelligence. Triggers on: binary, malware, PE, ELF, Mach-O, shellcode, firmware, analyze…

JameZUK/Arkana · 158 tokens

arkana-learn

Interactive reverse engineering tutor using Arkana. Teaches binary analysis concepts from beginner to expert, adapting to the learner's level. Guides users through hands-on analysis or structured lessons using Arkana's 308 tools as the teaching platform. Triggers on: teach, learn, tutorial, lesson, explain, guide, how…

JameZUK/Arkana · 118 tokens