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/divar-ir/ai-doc-gen/agents-mdgit clone --depth 1 https://github.com/divar-ir/ai-doc-genWrote 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/divar-ir/ai-doc-gen/agents-md)<a href="https://agentmods.dev/instructions/divar-ir/ai-doc-gen/agents-md"><img src="https://agentmods.dev/badge/instructions/divar-ir/ai-doc-gen/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 5.1 | $0.01434 | $0.01434 |
| Opus 5 | $0.00717 | $0.00717 |
| Sonnet 5 | $0.00287 | $0.00287 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
ai-doc-gen 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 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Documentation Generator
Multi-agent Python CLI tool that analyzes codebases and generates documentation: .ai/docs/*.md analyses, README.md, and AI assistant config files (CLAUDE.md, AGENTS.md, .cursor/rules/).
Build & Test
# Install dependencies (Python 3.13 required, <3.14)
uv sync
# Run analysis (writes .ai/docs/*.md)
uv run src/main.py analyze --repo-path .
# Generate README
uv run src/main.py generate readme --repo-path .
# Generate AI assistant config files (CLAUDE.md, AGENTS.md, .cursor/rules/)
uv run src/main.py generate ai-rules --repo-path .
# GitLab batch mode
uv run src/main.py cronjob analyze --max-days-since-last-commit 14
# Format and lint (run both before submitting)
uv run ruff format src/
uv run ruff check src/
Setup: cp .env.sample .env (fill in LLM keys), optionally cp config_example.yaml .ai/config.yaml.
Architecture
- Multi-agent system: 5 analysis agents (structure, dependencies, data flow, request flow, API) run through a
WorkerPool(src/utils/worker_pool.py, concurrency fromANALYZER_MAX_WORKERS, 0 = CPU count); 2 AI-rules generators (markdown + cursor) run viaasyncio.gather(return_exceptions=True). - Handler pattern: each CLI command maps to a handler in
src/handlers/implementingAbstractHandler.handle(); handler configs subclassBaseHandlerConfig+ the agent config (e.g.,AnalyzeHandlerConfig(BaseHandlerConfig, AnalyzerAgentConfig)). - Tool-based agents: pydantic-ai agents with
FileReadToolandListFilesTool(src/agents/tools/); prompts are Jinja2 templates insrc/agents/prompts/*.yaml. - Configuration hierarchy: Pydantic defaults →
.ai/config.yaml→ CLI arguments (merge_dicts()); secrets come from.envvia module-level constants insrc/config.py. - LLM providers: OpenAI-compatible only (
OpenAIChatModel+OpenAIProviderwith base URL override). Three env config sets:ANALYZER_LLM_*,DOCUMENTER_LLM_*,AI_RULES_LLM_*(AI_RULES falls back to DOCUMENTER values).
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 · 96 lines · 1,434 tokens per session scan A c312ac5d8200
ai-doc-gen AGENTS.md is an instructions file published in the GitHub repository divar-ir/ai-doc-gen (752 stars, last pushed 1mo ago), licensed MIT. It adds 1,434 tokens to every session, about $0.0072 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
Lody AGENTS.md
AGENTS.md instructions for LodyAI/Lody, covering repository guidelines, context maintenance, repository boundary, project map and checks and commits.
sprawling AGENTS.md
Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.
AgentCore AGENTS.md
AGENTS.md instructions for Lawofall/AgentCore, covering agents.md, 先读哪里, docs 与 rules and 开发 / 测试（最短）.
Mutsumi AGENTS.md
Instructions for NERDSORG/Mutsumi, covering mutsumi 项目开发指南（agent 贡献者版）, 1. 架构总览, 核心分层原则, 2. notebook 系统与 ui 层 and 2.1 .mtm 文件模型与 serializer（notebook/serializer.ts）.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
wikifier CLAUDE.md
Claude Code instructions for IronAdamant/wikifier, covering claude.md, what this is, hard constraints, mandatory workflow (the project's own protocol) and ... edit source (prioritize 🔴 red, then 🟡 yellow) ...