rules

A project-rules manager that creates shared instruction files for coding assistants, including Claude Code and Codex.

In plain words
What is it for?
Use it to inspect rule status, generate rules, or create CLAUDE.md and AGENTS.md files.
Why use it?
It turns a codebase's working conventions into written rules that assistants can follow across different tools.

Command

Install

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.

agentmods
npx agentmods add commands/drag88/claude-dev-framework/rules
Clone the repo
git clone --depth 1 https://github.com/drag88/claude-dev-framework
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,078 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.09078
Opus 5 $0.00010 $0.04539
Sonnet 5 $0.00004 $0.01816
Haiku 4.5 $0.00002 $0.00908

Measured yesterday against content hash 85dda2503ba0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rules 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 yesterday.

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.

commands/rules.md · 736 lines

How it starts

The opening of the file, as written. The whole thing — 736 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cdf:rules - Project Rules Management

Generate and manage project rules in .claude/rules/, CLAUDE.md (Claude Code), and AGENTS.md (Codex and other coding agents).

Quick Start

# No subcommand — full chain: status → generate (if missing) → claudemd + agentsmd
/cdf:rules

# Generate full rules + both host instruction files from codebase analysis
/cdf:rules generate

# Generate CLAUDE.md (Claude Code, current models) from existing rules
/cdf:rules claudemd

# Generate AGENTS.md (Codex / GPT-5.5 and 20+ other agents) from existing rules
/cdf:rules agentsmd

# Check if rules need refresh
/cdf:rules status

Default Behavior (No Subcommand)

When invoked as bare /cdf:rules with no argument, run the full chain in order:

  1. Inspect state: check whether .claude/rules/ and at least one rule file exist.
  2. Generate rules if missing: if .claude/rules/ is empty or absent, run the generate subcommand first.
  3. Generate CLAUDE.md if missing: if neither CLAUDE.md nor CLAUDE.generated.md exists in the project root, run the claudemd subcommand.
  4. Generate AGENTS.md if missing: if neither AGENTS.md nor AGENTS.generated.md exists in the project root, run the agentsmd subcommand.
  5. Report: tell the user exactly which files were created or skipped (and why each was skipped).

This default is the safety net for the most common ask ("set up rules for this repo"). Never stop after CLAUDE.md without also writing AGENTS.md — both host files come from the same .claude/rules/ source and must stay in sync.

When to Use

Use /cdf:rules when:

  • Setting up a new project (generate initial rules)
  • After major refactors (refresh rules to match new architecture)
  • Rules are outdated (regenerate to match current code)
  • Need CLAUDE.md (Claude Code) or AGENTS.md (Codex) for quick reference
  • Working in a repo that targets both Claude Code and Codex — both files stay in sync from one source

Don't use this command for: Dev documentation or task planning (use /cdf:docs plan instead).

Read the full file on GitHub · 736 lines

Changes

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.

  1. yesterday First seen · 736 lines · 21 tokens per session scan A 85dda2503ba0

Subscribe to this mod's changes

rules is a command published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 9,078 once invoked, about $0.0001 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 2026-08-31.