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.
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.
npx skills add tw93/Waza --skill writegit 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/skills/tw93/waza/write)<a href="https://agentmods.dev/skills/tw93/waza/write"><img src="https://agentmods.dev/badge/skills/tw93/waza/write/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/skills/tw93/waza/write"><img src="https://agentmods.dev/badge/skills/tw93/waza/write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 133 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00041 | $0.03249 |
| Opus 5.5 | $0.00016 | $0.01300 |
| Sonnet 5.5 | $0.00008 | $0.00650 |
| Haiku 4.5 | $0.00004 | $0.00325 |
Grade A, and why
write 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- write — 92% identical, 157 lines differ
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write: Cut the AI Taste
Prefix your first line with 🥷 inline, not as its own paragraph.
Strip AI patterns from prose and rewrite it to sound human. Do not improve vocabulary; remove the performance of improvement.
Outcome Contract
- Outcome: the prose preserves the author's intent while sounding natural for its audience and surface.
- Done when: meaning, factual claims, and structure are preserved unless the user asked to change them, and AI-like wording is removed; punctuation and CJK/Latin mixing pass the Punctuation Gate for the output language.
- Evidence: supplied text, target audience, project style references, release or product state, and requested language.
- Output: edited prose for pasted text; for repository edits, a scoped diff and the requested verification or delivery receipt.
Durable Context Preflight
See references/durable-context.md for when durable context is in scope and the redaction gate that applies before any of it becomes a durable rule.
For /write: the supplied text and current release state override memory. Durable preferences can set brevity, tone, and social-post shape; they do not override the hard rule to edit in place, keep meaning intact, and avoid change lists unless the user explicitly asks or the input is the author's own finished draft.
Core Stance
This skill is a catalog of smells, not a checklist to run top to bottom. Use it to recognize AI taste, then make judgment calls. The reference files are catalogs; do not try to apply every rule to every text. Applying more rules is not doing a better job.
- Over-editing is failure, equal to under-editing. If a sentence is already natural, clear, and stable, leave it. Most polish is subtraction (cut repetition, summary-tone, restated conclusions), not phrase-by-phrase replacement. When the input is the author's own finished draft, the default scope shrinks to typos, broken sentences, and clear AI tells: never rewrite their sentences for style, and return a per-sentence list of every deleted or rewritten sentence so the author can veto each one.
- A piece has a speaker. Smooth prose that could belong to anyone has lost something. Keep the author's colloquial words, cadence, knowledge and judgments; deliberate authorial or genre choices take precedence over these defaults. The author's affection, frustration, pride, gratitude and personal convictions are content, even when abstract or phrased as a conclusion. Preserve their intensity; do not require external evidence for a feeling or replace it with a neutral observation. Distinguish authentic colloquialisms, emotional markers, and deliberate series branding from AI corporate jargon and translationese: protect the author's real voice (including signature informal words or established series titles); remove synthetic PR buzzwords. Read nearby paragraphs and author revisions to separate a real stance from stock rhetoric. If that distinction is uncertain, keep the sentence. Do not invent emotion or turn "what I did" into "what you must do."
- Banned-phrase lists and replacement tables are examples, not find-and-replace. A flagged word that reads naturally in context stays. Match the smell, not the string. When source material exists, check it before flagging the author's wording; restore their words rather than paraphrasing them. When restoring copy, trace that passage's diffs to the nearest version before the unwanted edit and compare the restored text exactly; do not choose an older, shorter version or rewrite unrelated paragraphs.
- Prefer fewer, stronger edits. Three changes that matter beat thirty mechanical swaps that flatten the voice.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/durable-context.md 2.0 KB
- references/mode-long-form.md 2.5 KB
- references/mode-public-reply.md 4.3 KB
- references/mode-release-notes.md 4.3 KB
- references/write-en.md 9.3 KB
- references/write-product-localization.md 13 KB
- references/write-technical.md 8.5 KB
- references/write-zh-bilingual.md 1.5 KB
- references/write-zh-release-notes.md 2.3 KB
- references/write-zh.md 54 KB
- scripts/check_punctuation.py 19 KB runs code
- scripts/check-punctuation.sh 151 B runs code
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.
- 4d ago Changed ed57ea5d024b
- 6d ago Changed · +1 lines 36bfd4aaa70f
- 7d ago Changed 19faa0d395cf
- 10d ago Changed · +1 lines · +4 tokens per session 8abed35d3f9f
- 21d ago Changed · -22 lines b4843a2f9268
- 24d ago Changed b8781b5bfbe4
- 27d ago Changed · +1 lines 1cfd21f6a329
- 29d ago Changed · -50 tokens per session b951e989e0ce
- 1mo ago Changed a27fcb848710
- 1mo ago First seen · 148 lines · 87 tokens per session scan A d35ead1c5f70
write is a skill published in the GitHub repository tw93/Waza (7,311 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 3,249 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
finalize
Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy. Use when the user wants to ship, merge, or finalize a surface and needs a verdict (READY / NOT READY / BLOCKED) before committing. Invoke when the user asks for finalize on their UI, or…
friction-log
File contributor or agent papercuts as GitHub issues labeled friction, or investigate those issues as the daily friction-log Cloud Agent. Use when you hit repo friction, when asked to log friction, or when spawned to resolve open friction issues.
harden
Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for production or when the user says "it crashes on empty data" / "there's no loading state"…
huashu-agent-swarm
Multi-agent swarm parallel collaboration using pure git self-organisation, ideal for large-scale project development. Use when the user mentions "swarm mode", "multi-agent", "parallel development", or "agent swarm".
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.