name: repo-rules
description: Query AI coding rules for this repo (extracted from CLAUDE.md, AGENTS.md, .cursorrules, .github/copilot-instructions.md, and ~40 other rules-file conventions). Invoke when the user asks about team rules, coding standards, or conventions — or when reviewing, generating, or refactoring code and you need to know which rules apply. Builds a fresh index if one doesn't exist yet.
argument-hint: [command] [args...]
allowed-tools: Bash(repo-rules-agent *)
repo-rules-agent
Extract and query AI coding rules (CLAUDE.md, .cursorrules, .github/copilot-instructions.md, etc.) from the current repository.
Default workflow
When you need to consult the rules for a task, go straight to query (or stats for overview questions). Don't pre-check whether the index exists — the commands print a clear error with the exact remedy if it doesn't.
-
If a subsequent command reports "no index found at …", build the index (one-time per repo, or after a rules file changes):
repo-rules-agent index .
The index is written to a per-user cache directory (not the repo). The command prints the exact path.
-
Query the index scoped to the current task:
repo-rules-agent query \
--task <code-review|code-generation|code-questions> \
[--lang py|ts|go|...] \
[--severity must|should|can] \
--format prompt
Use --format prompt when injecting rules into your own context. Use --format table when showing them to the user.
Overview questions ("what rules does this repo have?", "how many rules per file?")
Use stats — it reads the cached index and prints rule counts per file plus breakdowns by severity, task, and language. Do NOT pipe query into a custom script for this.
repo-rules-agent stats
Commands
index — Extract rules and build a JSON index
repo-rules-agent index <repo-path> [-o output.json] [-v]
- Discovers rules files, extracts individual rules via any OpenAI-compatible LLM, and writes a JSON index.
- Default output location is a per-user cache directory keyed by the absolute repo path.
-o path: override the output path.- Defaults to local Ollama (
glm-4.7-flash:latest); configure provider via RULES_AGENT_LLM__BASE_URL and RULES_AGENT_LLM__API_KEY_ENV.
stats — Summarize a rules index
repo-rules-agent stats [index.json] [-v]
Reads the cached index (or a path you give) and prints total rule count, rules per file, and breakdowns by severity, task, and language. Use this for overview questions instead of piping query output into a script.
query — Filter and retrieve rules from an index
repo-rules-agent query [index.json] [options]
With no positional argument, reads the cached index for the current directory.
Options:
-t, --task: Filter by task type (code-review, code-generation, code-questions)-l, --lang: Filter by language (py, ts, go, java, rust, etc.)-s, --scope: Filter by scope (repo, directory, file-pattern)--severity: Filter by severity (must, should, can)-f, --format: Output format (table, json, prompt)
discover — Find rules files without extracting
repo-rules-agent discover <repo-path> [-v]
Lists all rules files found in a repository with their priority tiers and sizes.
cache — Manage the per-repo index cache
repo-rules-agent cache path [repo-path]
repo-rules-agent cache list
repo-rules-agent cache clear <repo-path>
repo-rules-agent cache clear --all
eval — Evaluate extraction quality with LLM judge
repo-rules-agent eval <source> [--repo <path>] [-o results.json] [--judge-model <model>] [-v]
<source>: index JSON path or a repository directory (directory runs the full pipeline).--judge-model: model used as judge (default: qwen3-coder:30b).- Reports precision, recall, and F1 per file and overall.
install-skill — Install this skill
repo-rules-agent install-skill [--target claude|codex|cursor|all] [--scope project|user] [--force]
The same SKILL.md works across Claude Code, Codex CLI, and Cursor. Only the destination directory differs:
| Target | Project scope | User scope |
|---|
claude (default) | .claude/skills/repo-rules/SKILL.md | ~/.claude/skills/repo-rules/SKILL.md |
codex | n/a (use --scope user) | ~/.codex/skills/repo-rules/SKILL.md |
cursor | .cursor/skills/repo-rules/SKILL.md | ~/.cursor/skills/repo-rules/SKILL.md |
all | claude + cursor (codex skipped) | claude + codex + cursor |
--force: overwrite any existing SKILL.md without confirmation.
