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/geoloeg-ist/agents-reverse-engineer/agents-mdgit clone --depth 1 https://github.com/GeoloeG-IsT/agents-reverse-engineerWrote 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/instructions/geoloeg-ist/agents-reverse-engineer/agents-md)<a href="https://agentmods.dev/instructions/geoloeg-ist/agents-reverse-engineer/agents-md"><img src="https://agentmods.dev/badge/instructions/geoloeg-ist/agents-reverse-engineer/agents-md.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 | $0.04955 | $0.04955 |
| Opus 5 | $0.02478 | $0.02478 |
| Sonnet 5 | $0.00991 | $0.00991 |
| Haiku 4.5 | $0.00496 | $0.00496 |
Grade A, and why
agents-reverse-engineer AGENTS.md 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
execSync('npm view agents-reverse-engineer version', {timeout: 10000}) How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agents-reverse-engineer
npx-installable CLI toolkit for AI coding assistants that generates AI-optimized .sum file summaries, AGENTS.md hierarchical documentation, and runtime integration hooks for Claude Code, OpenCode, Gemini CLI, and Codex, with A/B testing framework for measuring AI planning and implementation quality impact.
Stack
Runtime: Node.js 18+ with TypeScript (ES2022 modules via tsconfig.json)
AI Backends: Claude CLI, OpenAI Codex, Google Gemini, OpenCode (subprocess adapters)
File Discovery: fast-glob with ignore/isbinaryfile filters
Git Operations: simple-git (change detection, worktree isolation)
Schema Validation: zod (config.yaml schema)
Output Formats: YAML frontmatter (.sum files), NDJSON (telemetry traces), HTML (dashboard reports via Chart.js CDN)
Entry Points: bin.agents-reverse-engineer and bin.are → dist/cli/index.js
Core API: exports["./core"] → dist/core/index.js with types at dist/core/index.d.ts (@beta stability)
Contents
Configuration & Licensing
- CONTRIBUTING.md — Developer workflow:
npm install(dependencies),npm run build(tsc → dist/),npm run dev(tsx watch live reload). Project structure: src/cli/ (CLI entry + commands), src/config/ (schema + loading), src/discovery/ (file discovery + plan gen), src/generation/ (AI-driven doc gen), src/orchestration/ (concurrency pool + tracing + process mgmt), src/ai/ (AI service abstraction + subprocess mgmt), src/plan/ (A/B plan comparison), src/implement/ (A/B implementation comparison). Fork-branch-PR contribution workflow. Bug reports require repro steps + environment. Feature requests useenhancementlabel. MIT licensed. - LANGUAGES-MANIFEST.md — Mapping of 24 languages to package manifest files: JavaScript/TypeScript (package.json), Python (requirements.txt, pyproject.toml, setup.py, Pipfile), Go (go.mod), Rust (Cargo.toml) marked supported (✓); Ruby (Gemfile), Java (pom.xml, build.gradle), and 17 others currently unsupported. Used by src/generation/prompts/builder.ts for import map construction.
- LICENSE — MIT license granting unrestricted use/modification/distribution with copyright notice requirement. AS IS warranty disclaimer. Copyright holder: GeoloeG-IsT (2026).
- package.json — npm package metadata v1.2.17. Entry points:
bin.agents-reverse-engineer/bin.are→dist/cli/index.js,exports["."]→dist/cli/index.js,exports["./core"]→dist/core/index.jswith type definitions atdist/core/index.d.ts. Build scripts:build(tsc),build:hooks(scripts/build-hooks.js),prepublishOnly(sequential builds),prepack(removes LICENSE.sum/README.md.sum),dev(tsx watch). Dependencies: fast-glob, ignore, isbinaryfile, jsonc-parser, simple-git, yaml, zod, picocolors. Node >=18.0.0 required. - tsconfig.json — TypeScript compiler config: target ES2022, module/moduleResolution NodeNext, outDir dist/, rootDir src/, declaration/declarationMap/sourceMap true, strict true, forceConsistentCasingInFileNames true, isolatedModules true, resolveJsonModule true. Include src/**/*, exclude node_modules/dist.
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.
- 4d ago First seen · 195 lines · 4,955 tokens per session scan A a091a4c53980
agents-reverse-engineer AGENTS.md is an instructions file published in the GitHub repository GeoloeG-IsT/agents-reverse-engineer (20 stars, last pushed 27d ago), licensed MIT. It adds 4,955 tokens to every session, about $0.0248 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
fastagent AGENTS.md
AGENTS.md instructions for fastagent-sh/fastagent, covering fastagent — agent guide, what this is, source of truth, repo map and devx principle stack.
trellis AGENTS.md
Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.
scopeglass AGENTS.md
AGENTS.md instructions for zackabrah/scopeglass, covering scopeglass contributor instructions, project, commands, conventions and boundaries.
agentic-coding-workflow AGENTS.md
Instructions for abhilash-m96/agentic-coding-workflow, covering agentic coding workflow, rules, step 1 — understand the full scope, step 2 — propose the chunk plan and step 3 — write the finalised plan.
android-qa-kit AGENTS.md
Instructions for willbytee-sudo/android-qa-kit, covering agents.md — setting up and driving an android device, 1. how to work with the user, 2. start by finding out what's already there, 3. what you can do in each mode and 4. if there's no device: ask first.
agentscribe copilot-instructions.md
Instructions for Lucabiz/agentscribe, covering agentscribe, setup & commands, code style & conventions, testing and do not.