Borrowing it
Nothing to install: this file belongs to unblocked/repo-rules-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/unblocked/repo-rules-agent/main/AGENTS.mdgit clone --depth 1 https://github.com/unblocked/repo-rules-agentWrote 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/unblocked/repo-rules-agent/agents-md)<a href="https://agentmods.dev/instructions/unblocked/repo-rules-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/unblocked/repo-rules-agent/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/unblocked/repo-rules-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/unblocked/repo-rules-agent/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00844 | $0.00844 |
| Opus 5.5 | $0.00338 | $0.00338 |
| Sonnet 5.5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
repo-rules-agent 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 2mo 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-rules-agent Development Guide
Architecture
The pipeline flows: discover → extract → index → query
- Discovery (
rules/discovery.py): Scans a repo for rules files (CLAUDE.md, .cursorrules, etc.) organized by priority tiers defined inconfig.toml. - Extraction (
rules/extractor.py): Sends file contents to an LLM via tool use to extract structured rules. Large files are chunked usingchonkie(markdown-aware chunking). - Indexing (
rules/index.py): Deduplicates rules (text similarity), detects conflicts (contradictory severity), and builds aRuleIndex. - Query (
rules/query.py): Filters rules by task, language, scope, severity. Formats output as table, JSON, or prompt. - Eval (
rules/eval.py): Uses an LLM judge to score extraction quality (precision, recall, F1).
Data Flow
discover_rules_files(repo_path)→list[RuleFile], dict[str, str](files + contents)extract_rules_from_files(rule_files, contents)→list[ProcessedFile]build_index(repo_path, processed_files)→RuleIndexquery_rules(index, task=, lang=, ...)→list[Rule]
Adding a New CLI Command
- Add the command function in
cli.pywith@app.command(name="command-name") - Use
typer.Argument/typer.Optionfor parameters - Use
console(Rich) for output, notprint() - Add tests using
typer.testing.CliRunnerintests/test_<name>.py - Update the bundled skill files if the command should be user-facing:
src/rules_agent/skill/SKILL.md(bundled package copy)skills/repo-rules/SKILL.md(plugin copy).claude/skills/repo-rules/SKILL.md(local dev copy, usesuv run)
Adding Discovery Patterns
Edit src/rules_agent/config.toml to add new file patterns or tiers. The config is loaded via pydantic-settings at module import time.
Testing Conventions
- Tests live in
tests/test_*.py, one file per module - Mock all LLM/API calls — tests must run offline
- Use
tmp_pathfixture for filesystem tests - Use
typer.testing.CliRunnerfor CLI integration tests - Run
make test(which runsuv run pytest tests -v)
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.
- 2mo ago First seen · 67 lines · 844 tokens per session scan A faf0de5c92be
repo-rules-agent AGENTS.md is an instructions file published in the GitHub repository unblocked/repo-rules-agent (77 stars, last pushed 1mo ago), licensed MIT. It adds 844 tokens to every session, about $0.0034 per session on Opus 5.5. 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.
repo-rules-agent AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-rules-agent AGENTS.mdunblocked/repo-rules-agent | Instructions file | 77 | 1mo ago | MIT | A | 844 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |