catatz AGENTS.md

AGENTS.md instructions for kupzed/catatz, covering catatz - codex operating instructions, origin, source of truth, ecc workflow overlay and design contract.

Instructions file for CodexOpenCode

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/kupzed/catatz/agents-md
Clone the repo
git clone --depth 1 https://github.com/kupzed/catatz

Made for: Codex, OpenCode.

Per session 2,814 This file is loaded in full into every session.
When invoked 2,814 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 $0.02814 $0.02814
Opus 5 $0.01407 $0.01407
Sonnet 5 $0.00563 $0.00563
Haiku 4.5 $0.00281 $0.00281

Measured yesterday against content hash dd15283fa8d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

catatz 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 · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CatatZ - Codex Operating Instructions

Origin

CatatZ adalah aplikasi pencatatan keuangan berbasis Next.js 16 App Router, Supabase, Server Actions, dan PWA Serwist. File ini adalah instruksi repository-level untuk agent saat bekerja dari root repository CatatZ.

Instruksi detail tetap berada di docs/ai-development-rules.md. Anggap file ini sebagai operating manual singkat yang mengikat Codex agar setiap task selesai dengan perubahan yang rapi, dokumentasi yang sinkron, validasi yang jujur, dan suggested commit message yang teknis.

Source of Truth

Ada beberapa sumber kebenaran yang harus dipakai sebelum membuat perubahan:

  • Source code saat ini adalah kebenaran utama untuk behavior aplikasi.
  • docs/ adalah kebenaran dokumentasi dan harus mengikuti behavior aktual, bukan rencana.
  • docs/ai-development-rules.md adalah kebenaran utama untuk aturan kerja AI di repo ini.
  • DESIGN.md adalah kebenaran utama untuk semua keputusan visual, design token, dan component styling.
  • docs/frontend-guidelines.md adalah kebenaran implementasi desain di codebase ini (adaptasi DESIGN.md ke Tailwind/shadcn).
  • src/migrations adalah lokasi migration project ini. Jangan mengasumsikan supabase/migrations.
  • .env.example hanya boleh berisi nama variable dan placeholder aman. Jangan expose nilai secret dari .env.

Jika dokumentasi dan source code berbeda, percaya source code dulu, lalu update dokumentasi yang relevan dalam task yang sama.

ECC Workflow Overlay

CatatZ memakai subset Everything Claude Code (ECC) secara project-local untuk Codex dan Claude Code.

  • .agents/skills/ adalah canonical skill surface. .claude/skills/ hanya berisi wrapper kompatibilitas yang menunjuk ke canonical skill.
  • Gunakan skills coding-standards, frontend-patterns, security-review, verification-loop, documentation-lookup, strategic-compact, agent-introspection-debugging, product-capability, tdd-workflow, dan e2e-testing sesuai task.
  • nextjs-turbopack adalah library reference, bukan aturan production build. Production CatatZ tetap memakai next build --webpack untuk Serwist.
  • Specialized agents di .codex/agents/ dan .claude/agents/ bersifat read-only. Main agent adalah satu-satunya pihak yang boleh mengedit file.
  • Hooks project memblokir command destruktif dan perubahan secret file, tetapi quality check hanya warning. CI tetap menjadi enforcement utama.
  • Memory hook hanya boleh menyimpan metadata di .ecc/runtime/: path file, status verifikasi, timestamp, dan identifier sesi yang sudah di-hash. Jangan simpan prompt, tool arguments, isi file, secret, atau data finansial.
  • MCP project hanya chrome-devtools. Jangan tambahkan Supabase, database production, GitHub, memory, atau connector lain tanpa review eksplisit.

Read the full file on GitHub · 212 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 · 212 lines · 2,814 tokens per session scan A dd15283fa8d3

Subscribe to this mod's changes

catatz AGENTS.md is an instructions file published in the GitHub repository kupzed/catatz (33 stars, last pushed yesterday), licensed MIT. It adds 2,814 tokens to every session, about $0.0141 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 2026-09-01.

Related

Other instructions, from other repositories