Waza is a collection of installed skills that turn familiar engineering practices into repeatable playbooks for coding agents. It helps agents plan work, design interfaces, review changes, debug problems, edit prose, research unfamiliar subjects, read URLs or PDFs, and check their own health. The catalogue entries are Waza’s skills and supporting agents or instructions.
Borrowing it
Nothing to install: this file belongs to tw93/Waza. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tw93/Waza/main/AGENTS.mdgit clone --depth 1 https://github.com/tw93/WazaWrote 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.
[](https://agentmods.dev/instructions/tw93/waza/agents-md)<a href="https://agentmods.dev/instructions/tw93/waza/agents-md"><img src="https://agentmods.dev/badge/instructions/tw93/waza/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/tw93/waza/agents-md"><img src="https://agentmods.dev/badge/instructions/tw93/waza/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05144 | $0.05144 |
| Opus 5.5 | $0.02058 | $0.02058 |
| Sonnet 5.5 | $0.01029 | $0.01029 |
| Haiku 4.5 | $0.00514 | $0.00514 |
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 11d 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`). How it starts
The opening of the file, as written. The whole thing — 180 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,package.json, and installerWAZA_REFdefaults must agree with this file (codegen-enforced). Per-skill frontmatter carries no version field; the verifier rejects a stalemetadata.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.mdis the shared Durable Context Preflight preamble; codegen copies it into each referencing skill asskills/<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. EditVERSIONor per-skillSKILL.mdfrontmatter and runmake regenerate; never hand-edit..agents/plugins/marketplace.json- generated Codex repo marketplace. Points Codex atplugins/wazafor plugin installs; never hand-edit.plugins/waza/- generated Codex plugin tree. Mirrorsskills/andrules/plusplugins/waza/.codex-plugin/plugin.json; edit source files and runmake regenerate.packaging.allowlist- default-deny list of paths that ship inwaza.zip. New shippable assets must be added here explicitly; everything else is excluded..github/workflows/- public test and release automation.release.ymlrunsmake testbeforemake packageso 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-scriptWAZA_REFdefaults. Run viamake regenerate; CI checks drift viamake verify-generated.scripts/verify_skills.py- the only validator entrypoint; a driver over the check inventory inscripts/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- builddist/waza.zipfrompackaging.allowlist.scripts/setup-rule.sh+scripts/setup-statusline.sh- public install helpers;WAZA_REFdefaults are codegen-pinned to the current release tag.Makefile- smoke discovery and packaging entrypoints. Adding atests/test_<name>.shfile is enough to create asmoke-<name>target automatically.tests/test_*.sh- one smoke per surface; sourcestests/test_helpers.shfor tmpdir / repo-copy / stub-curl / instruction-file fixture factories.tests/python/holds the pytest unit layer (make verify-unit).
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.
- 11d ago Changed · -1 lines · -73 tokens per session b26d1c2963e4
- 16d ago Changed · +1 lines · +85 tokens per session 46fd405fa8c5
- 17d ago Changed · +7 lines · +277 tokens per session 5c08c80e5a24
- 1mo ago Changed · +2 lines · +307 tokens per session 0fdbb915f5b2
- 1mo ago Changed · +41 tokens per session c6241384fc45
- 1mo ago Changed · +5 tokens per session 86c4d6431248
- 1mo ago First seen · 171 lines · 4,502 tokens per session scan A d1140f24905f
Waza AGENTS.md is an instructions file published in the GitHub repository tw93/Waza (7,366 stars, last pushed yesterday), licensed MIT. It adds 5,144 tokens to every session, about $0.0206 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.