Waza AGENTS.md

Waza AGENTS.md is an instructions file for Codex, OpenCode from tw93/Waza. It costs 4,502 tokens per session, scanned A, original, MIT.

A guide for coding agents working on Waza, a collection of eight engineering-workflow skills. It explains the repository layout, ownership of health-related code, version rules, and available commands.

In plain words
What is it for?
Use it when adding or changing Waza skills, reviewing repository structure, running validation, updating versions, or deciding which files and specialists own a task.
Why use it?
It gives agents one shared source of project knowledge, including where each skill lives and how releases and generated metadata stay consistent. This helps prevent edits in the wrong file or stale version information.

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/tw93/waza/agents-md
Clone the repo
git clone --depth 1 https://github.com/tw93/Waza

Made for: Codex, OpenCode.

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 Waza AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tw93/waza/agents-md.svg)](https://agentmods.dev/instructions/tw93/waza/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tw93/waza/agents-md"><img src="https://agentmods.dev/badge/instructions/tw93/waza/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,502 This file is loaded in full into every session.
When invoked 4,502 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.04502 $0.04502
Opus 5 $0.02251 $0.02251
Sonnet 5 $0.00900 $0.00900
Haiku 4.5 $0.00450 $0.00450

Measured 4d ago against content hash d1140f24905f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Waza AGENTS.md scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `tests/test_*.sh` - one smoke per surface; sources `tests/test_helpers.sh` for tmpdir / repo-copy / stub-curl / instruction-file fixture factories. `tests/python/` holds the pytest unit layer (`make verify-unit`).
AGENTS.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Waza Agent Guide

This file is the canonical agent guide for the Waza repository. CLAUDE.md is a symlink to it, so Claude Code and Codex see identical content. Edit this file; do not edit CLAUDE.md.

Project

Waza is a skill collection for engineering workflows. The repository contains eight skills: think, ui, check, hunt, write, learn, read, and health.

Repository Map

  • VERSION - single source of truth for the lock-step version. Marketplace entries, README install URLs, and installer WAZA_REF defaults must agree with this file (codegen-enforced). Per-skill frontmatter carries no version field; the verifier rejects a stale metadata.version.
  • skills/RESOLVER.md - trigger and routing table for the skill set.
  • skills/*/SKILL.md - individual skill entrypoints.
  • skills/*/agents/ - specialist reviewer or inspector prompts.
  • skills/*/references/ - supporting references loaded only when needed.
  • skills/*/scripts/ - deterministic helper scripts.
  • rules/ - shared writing and behavior rules used by install and validation flows. rules/durable-context.md is the shared Durable Context Preflight preamble; codegen copies it into each referencing skill as skills/<name>/references/durable-context.md (direct installs get only the skill directory), and the six skills with optional memory context link to that skill-local copy.
  • .claude-plugin/marketplace.json - generated. Edit VERSION or per-skill SKILL.md frontmatter and run make regenerate; never hand-edit.
  • .agents/plugins/marketplace.json - generated Codex repo marketplace. Points Codex at plugins/waza for plugin installs; never hand-edit.
  • plugins/waza/ - generated Codex plugin tree. Mirrors skills/ and rules/ plus plugins/waza/.codex-plugin/plugin.json; edit source files and run make regenerate.
  • packaging.allowlist - default-deny list of paths that ship in waza.zip. New shippable assets must be added here explicitly; everything else is excluded.
  • .github/workflows/ - public test and release automation. release.yml runs make test before make package so the tagged commit is gated by the same suite as PRs.
  • scripts/build_metadata.py - codegen for Claude and Codex marketplace metadata, README install URLs, Codex plugin mirror files, skill-local durable-context copies, and installer-script WAZA_REF defaults. Run via make regenerate; CI checks drift via make verify-generated.
  • scripts/verify_skills.py - the only validator entrypoint; a driver over the check inventory in scripts/skill_checks.py (content, distribution, and routing checks). The facade's import list is the canonical inventory; do not re-enumerate it here.
  • scripts/package-skill.sh + scripts/packaging_filter.py - build dist/waza.zip from packaging.allowlist.
  • scripts/setup-rule.sh + scripts/setup-statusline.sh - public install helpers; WAZA_REF defaults are codegen-pinned to the current release tag.
  • Makefile - smoke discovery and packaging entrypoints. Adding a tests/test_<name>.sh file is enough to create a smoke-<name> target automatically.
  • tests/test_*.sh - one smoke per surface; sources tests/test_helpers.sh for tmpdir / repo-copy / stub-curl / instruction-file fixture factories. tests/python/ holds the pytest unit layer (make verify-unit).

Read the full file on GitHub · 171 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. 4d ago First seen · 171 lines · 4,502 tokens per session scan A d1140f24905f

Subscribe to this mod's changes

Waza AGENTS.md is an instructions file published in the GitHub repository tw93/Waza (6,948 stars, last pushed today), licensed MIT. It adds 4,502 tokens to every session, about $0.0225 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories