agentmods.dev

codex-claw AGENTS.md

A project-specific instruction guide for coding agents working on the CodexClaw app. It documents the app structure, commands, coding conventions, file naming, routing, and styling rules.

In plain words
What is it for?
Use it when developing the React app to find development, build, test, lint, formatting, routing, and style guidance.
Why use it?
It gives an agent the project’s local expectations so changes fit the existing codebase and can be checked with the project’s commands.

Instructions file for CodexOpenCode

1 29d ago A scan 805 tokens original MIT
View the source file slashdevcorpse/codex-claw
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/slashdevcorpse/codex-claw/agents-md
Clone the repo
git clone --depth 1 https://github.com/slashdevcorpse/codex-claw

Made for: Codex, OpenCode.

Per session 805 This file is loaded in full into every session.
When invoked 805 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 $0.00805 $0.00805
Opus 5 $0.00402 $0.00402
Sonnet 5 $0.00161 $0.00161
Haiku 4.5 $0.00081 $0.00081

Measured yesterday against content hash 7dfc1c722627, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-claw 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 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.

AGENTS.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

Overview

CodexClaw app lives in apps/codex-claw and is built with React + TanStack Router + Tailwind CSS v4.

Commands

  • pnpm -C apps/codex-claw dev — Start development server
  • pnpm -C apps/codex-claw build — Build for production
  • pnpm -C apps/codex-claw preview — Preview production build
  • pnpm -C apps/codex-claw test — Run tests
  • pnpm -C apps/codex-claw lint — Run ESLint
  • pnpm -C apps/codex-claw format — Run Prettier
  • pnpm -C apps/codex-claw check — Format and lint fix

Conventions

Code Style

  • Functions: Always use the function keyword. Avoid const for function definitions.
  • Types: Always use type T = { ... }. Do not use interface.
  • File Naming: Use kebab-case for all files (e.g., chat-screen.tsx, use-session.ts).
  • NEVER use useEffect for anything that can be expressed as render logic
  • MUST use cn utility (clsx + tailwind-merge) for class logic

Routing & Structure

  • Routes live in apps/codex-claw/src/routes using TanStack file routing.
  • Global styles and CSS variables live in apps/codex-claw/src/styles.css.
  • Local environment values go in apps/codex-claw/.env.local.

UI & Styling

  • Typography: Never use font weights bolder than font-medium. Apply small negative tracking (tracking-tight or similar) on main titles.
  • Colors:
    • Use the custom Tailwind palette (e.g., bg-primary-50, text-primary-900).
    • Never use arbitrary color values.
    • Avoid bg-white, bg-black, text-white, text-black, and outline-black; use primary palette tokens instead.
  • Markdown Titles: Avoid top margin on markdown headings.
  • MUST use text-balance for headings and text-pretty for body/paragraphs
  • MUST use tabular-nums for data
  • SHOULD use truncate or line-clamp for dense UI
  • NEVER modify letter-spacing (tracking-*) unless explicitly requested
  • MUST use a fixed z-index scale (no arbitrary z-*)
  • SHOULD use size-_ for square elements instead of w-_ + h-*
  • Icons:
    • All icons should use size={20} and strokeWidth={1.5} consistently
  • React 19 Refs: Use regular function components with direct ref passing instead of React.forwardRef (React 19 supports refs as regular props)

Read the full file on GitHub · 64 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 · 64 lines · 805 tokens per session scan A 7dfc1c722627

Subscribe to this mod's changes

codex-claw AGENTS.md is an instructions file published in the GitHub repository slashdevcorpse/codex-claw (1 stars, last pushed 29d ago), licensed MIT. It adds 805 tokens to every session, about $0.0040 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.

Code reviewFrontendTestingcodexcodex-clideveloper-toolslocal-firstnpx
Related

Other instructions, from other repositories

codex-usage-desktop AGENTS.md

Instructions for itvincent-git/codex-usage-desktop, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

itvincent-git/codex-usage-desktop · 1,088 tokens

agentmemory-codex-windows AGENTS.md

Instructions for M-T-D-N/agentmemory-codex-windows, covering agentmemory — agent instructions, architecture, windows/codex downstream profile, consistency rules and code patterns.

M-T-D-N/agentmemory-codex-windows · 2,120 tokens

hermes-codex-operator AGENTS.md

Instructions for AlekseiUL/hermes-codex-operator, a project described as: A local-first operator that turns plain-language ideas into tracked, verified Codex work—planned by Hermes, executed by Codex, and explained back to you.

AlekseiUL/hermes-codex-operator · 147 tokens

ctxwise AGENTS.md

Instructions for FramY2/ctxwise, a project described as: CtxWise — see and control what Codex loads. Local-first context audit, profiles, drift detection, and honest token receipts.

FramY2/ctxwise · 144 tokens

codex-tg AGENTS.md

Instructions for mideco-tech/codex-tg, covering agents, repository purpose, working mode, agent workflow kernel and context pull map.

mideco-tech/codex-tg · 2,868 tokens

codex-agent-mem AGENTS.md

Instructions for MarceloCaporale/codex-agent-mem, covering agents, public name vs import name, what this project is, working rules for agents and fastest commands.

MarceloCaporale/codex-agent-mem · 1,043 tokens