obey CLAUDE.md

obey CLAUDE.md is an instructions file for coding agents from Lexxes-Projects/obey. It costs 398 tokens per session, scanned A, original, MIT.

Project instructions for obey, a Claude Code plugin that stores user rules and adds them to future coding sessions. It uses Bash scripts, hooks, and separate global, stack, and project rule files.

In plain words
What is it for?
It supports adding, removing, and listing rules, injecting them into agent context, enforcing them before tool use, and detecting when a user may want to save a rule.
Why use it?
It helps an agent preserve coding preferences across sessions without modifying the user's CLAUDE.md files.

Instructions file

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 instructions/lexxes-projects/obey/claude-md
Clone the repo
git clone --depth 1 https://github.com/Lexxes-Projects/obey

Wrote 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.

agentmods badge for obey CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lexxes-projects/obey/claude-md.svg)](https://agentmods.dev/instructions/lexxes-projects/obey/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lexxes-projects/obey/claude-md"><img src="https://agentmods.dev/badge/instructions/lexxes-projects/obey/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 398 This file is loaded in full into every session.
When invoked 398 The same file — it is already loaded in full.
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 $0.00398 $0.00398
Opus 5 $0.00199 $0.00199
Sonnet 5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured 3d ago against content hash 8fa14cbcc996, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

obey CLAUDE.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 3d 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.

CLAUDE.md · 41 lines

What it actually says

obey — Claude Code Plugin

Makes Claude actually follow your rules by storing, injecting, and enforcing user instructions across sessions.

Stack

  • Language: Bash scripts (no compilation needed)
  • Dependencies: jq
  • Plugin format: Claude Code plugin (.claude-plugin/plugin.json)

Architecture

  • skills/ — /remember, /rules, /forget slash commands
  • agents/ — rule-classifier (Haiku-based scope detection)
  • hooks/ — SessionStart, PreToolUse, PreCompact, UserPromptSubmit
  • scripts/ — bash scripts for rule CRUD, context injection, enforcement

Key Design Decisions

  • Bash over Python: Zero external dependencies (unlike hookify which needs Python)
  • Grep-compatible regex: Patterns use POSIX ERE ((a|b) not (?:a|b)) for grep -iE
  • Three storage files: global, stack, project — maps to Claude Code's scope hierarchy
  • No CLAUDE.md modification: Rules injected via hook additionalContext, not by editing user files
  • Conservative auto-detection: UserPromptSubmit only suggests /remember, never auto-saves

Status: MVP

  • Rule storage (global/stack/project scopes)
  • Rule CRUD (add, remove, list)
  • SessionStart hook (inject rules into context)
  • PreCompact hook (rules survive compaction)
  • PreToolUse hook (block violations)
  • UserPromptSubmit hook (detect natural rule patterns)
  • /remember skill
  • /rules skill
  • /forget skill
  • rule-classifier agent
  • README
  • Testing with real Claude Code sessions
  • GitHub repo + release
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. 3d ago First seen · 41 lines · 398 tokens per session scan A 8fa14cbcc996

Subscribe to this mod's changes

obey CLAUDE.md is an instructions file published in the GitHub repository Lexxes-Projects/obey (1 stars, last pushed 5mo ago), licensed MIT. It adds 398 tokens to every session, about $0.0020 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.