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 instructions/ekozmaster/vibe-reverse-engineering/agents-mdgit clone --depth 1 https://github.com/Ekozmaster/Vibe-Reverse-EngineeringWhat 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 | $0.02209 | $0.02209 |
| Opus 5 | $0.01104 | $0.01104 |
| Sonnet 5 | $0.00442 | $0.00442 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
Vibe-Reverse-Engineering AGENTS.md 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe Reverse Engineering — Agent Instructions
LLM-friendly static and dynamic analysis toolkit for x86/x64 PE binaries (.exe / .dll), combining static analysis (retools), dynamic analysis (livetools via Frida), and D3D9 frame tracing. Work is organized around per-game knowledge base files (kb.h) that accumulate discoveries and feed back into richer decompilation.
This file is the canonical, harness-agnostic instruction set. Claude Code loads it via .claude/CLAUDE.md; Cursor, Copilot, Codex, and other agents read it directly. Deeper references live under .claude/ and apply to every harness:
- Tool catalog (every retools / livetools / dx9tracer command, syntax, caveats):
.claude/references/tool-catalog.md - Tool dispatch (which tool for which question; what runs inline vs delegated):
.claude/rules/tool-dispatch.md - Analysis workflow (bootstrap ordering, Ghidra backend, index/query, parallel patterns):
.claude/rules/subagent-workflow.md - Skills (
dx9-ffp-port,dynamic-analysis):.claude/skills/— canonical copies. Non-Claude harnesses self-install them (see "Skill Setup" below). - Custom agents (
static-analyzer):.claude/agents/— canonical definitions..cursor/agents/,.github/agents/, and.kiro/agents/hold thin harness-native mirrors that defer to the canonical files, so only the.claude/agents/copies get edited.
Skill Setup (do this first on non-Claude harnesses)
Claude Code reads .claude/skills/ natively — skip this section. Every other harness: check whether the dx9-ffp-port and dynamic-analysis skills are available to you. If not, install them into your own skills directory before starting work:
npx skills add ./.claude/skills -a <your-agent> -y # e.g. -a cursor, -a copilot, -a kiro-cli
Omit -a to let the CLI auto-detect your harness. The source path must be ./.claude/skills — a bare . finds nothing (the CLI skips the current project's agent directories).
If npx is unavailable or your harness isn't supported by the CLI, copy manually: each .claude/skills/<name>/ folder goes verbatim into your harness's skills directory (Cursor: .cursor/skills/, Copilot: .github/skills/, Kiro: .kiro/skills/, .agents/skills/ for agents following that convention).
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.
- 2d ago First seen · 124 lines · 2,209 tokens per session scan A d80657def820
Vibe-Reverse-Engineering AGENTS.md is an instructions file published in the GitHub repository Ekozmaster/Vibe-Reverse-Engineering (46 stars, last pushed 1mo ago), licensed MIT. It adds 2,209 tokens to every session, about $0.0110 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.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.