Skip to content
Back to skills

Rules

ASecurity

Maintains project .codex/rules and the AGENTS.md rule index. Explicit user invocation only.

  • 32 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 5, 2026
ai-agents

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned October 1, 2026

npx -y skills add kochetkov-ma/claude-brewcode --skill rules --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rules?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Rules
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kochetkov-ma-rules-claude-brewcode/badge)](https://www.skillsdirectory.com/skills/kochetkov-ma-rules-claude-brewcode)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: rules
description: "Maintains project .codex/rules and the AGENTS.md rule index. Explicit user invocation only."
---

# Codex project rules

Use only when the user explicitly requests rule creation, synchronization, improvement, review, or inventory.

## Sources of truth

- Store rule bodies under the project `.codex/rules/`; never use personal or foreign-assistant rule paths.
- Treat hierarchical `AGENTS.md` files as Codex's automatically loaded instruction surface.
- Keep rule content in one file. `AGENTS.md` contains a compact index, not copied rule bodies.

## Modes and arguments

Position 1 of the arguments is a free-form prompt (RU/EN); mode tokens are optional and may follow. Resolve the mode from that prompt: `status` (default, read-only inventory), `list`, `create`, `improve`, `review`. An explicit mode token wins outright; otherwise take the mode the prompt describes, and ask at most one clarifying question, only when the answer changes what gets written.

Before the first write — and before the report on a read-only run — state in one block: the input verbatim, the resolved mode and why, the scope (rule files and `AGENTS.md` tables in play), what will be done, and the result the user ends up with.

## Workflow

1. Read the applicable `AGENTS.md` files and inventory every project rule with `rg --files .codex/rules | sort`.
2. Resolve the request to `status`, create, improve, review, list, or synchronize. Persist durable repository facts only; exclude secrets, transient session state, generated reports, and duplicate instructions.
3. Create or update English rule files under `.codex/rules/`. Reuse an existing rule when its scope matches.
4. Update the nearest applicable `AGENTS.md` rule-index table. The repository-root table lists every `.codex/rules/*.md` file exactly once with columns `Rule`, `Load when`, and `Purpose`. Nested tables add only subtree-specific rules not already covered by the inherited root index.
5. Invoke `$brewtools:text-optimize -l` for every changed rule and `AGENTS.md` index. Preserve paths, scope qualifiers, safety constraints, and table structure; apply the optimized patch only after comparing semantics.
6. Re-run the complete inventory. Fail validation when any rule path is missing from the root index, any indexed path is stale, or a rule body was duplicated into `AGENTS.md`.
7. Report changed rules, index rows, optimization measurements, and validation evidence.

The index makes rules discoverable; it does not auto-load their bodies. During later work, read the indexed rule whose `Load when` condition matches the task.

## Native user gates

Required approval: main presents a concrete, reviewable proposal in chat and waits for an actual user reply before dependent action. Existing authorization for the same scope remains valid; do not ask again. Optional clarification: use `request_user_input_async` only if exposed, or `request_user_input` only if available in the current runtime/mode, for optional choices and never approval. Otherwise ask in main chat. Delegated agents return unresolved questions to main. Silence, elapsed time and tool errors are not approval.

Files in this skill

  • LICENSE1.1 KB
  • README.md346 B
  • SKILL.md2.6 KB
  • agents/openai.yaml245 B
  • scripts/rules.sh13.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.