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 agentmods add skills/tw93/waza/writenpx skills add tw93/Waza --skill writegit clone --depth 1 https://github.com/tw93/WazaWhat 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 | $0.00087 | $0.03864 |
| Opus 5 | $0.00044 | $0.01932 |
| Sonnet 5 | $0.00017 | $0.00773 |
| Haiku 4.5 | $0.00009 | $0.00386 |
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 2d 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, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 176 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: the edited prose only, unless the user asked for notes, variants, or review comments.
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 (especially write-zh.md) are long because they accumulated examples over many sessions; 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.
- A piece has a speaker. The reader's test is not "any banned words" but "can I tell who is talking". Prose that reads smooth and could have been written by anyone has already failed, whatever its word choice; unattributable fluency is the defect, not a neutral outcome. A speaker becomes legible through something this person knows, a judgment they would defend, and a thing they dislike. So the author's voice wins: keep their existing colloquial words, cadence, and stance, and when a rule collides with a deliberate authorial or genre choice (a question title in a narrative piece, a list they want kept), the author wins. Rules are defaults, not laws. Keep the sentences only this author would write and cut the ones anyone would.
- 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.
- 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 2.7 KB
- references/mode-public-reply.md 3.3 KB
- references/mode-release-notes.md 4.3 KB
- references/write-en.md 9.7 KB
- references/write-product-localization.md 5.7 KB
- references/write-zh-bilingual.md 2.4 KB
- references/write-zh-prose.md 3.2 KB
- references/write-zh-release-notes.md 2.6 KB
- references/write-zh.md 52 KB
- scripts/check_punctuation.py 18 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.
- 2d ago First seen · 176 lines · 87 tokens per session scan A a267f6d7ea30
write is a skill published in the GitHub repository tw93/Waza (6,944 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 3,864 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
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"…
spark-ui
Install and compose Spark UI signature React components such as Widget Stack, Dynamic Island, Interactive Pets, Tactile Highlight, Shimmer Text, Image Trail, Animated Gradient, Ghost Ether, Logo Carousel, QR Code, Receipt, Number Ticker, Spotify Card, Masonry, Keyboard, and Hello from the Spark UI shadcn-compatible…
figma-translator
Translate any technical specification into five precise, self-contained Figma Make prompts ready to paste and generate. Use when you have an enterprise-design, visual-system-architect, or copywriting output and need to convert it into Figma Make–compatible prompts covering hero, features, social proof, CTA, and mobile…
verify
Build, run, and drive the Spark UI docs site to verify changes end-to-end.
uxloom
Validates UI/UX designs with UXLoom — models user journeys as state machines and proves what screens are missing (unreachable states, dead ends, empty/loading/error coverage, WCAG contrast, touch targets, localization overflow) before code exists. Use when designing screens or user flows, validating AI-generated UI…
component-guide
An intelligent component management assistant that automatically determines whether to create new components, reuse existing ones, or ask users for decisions based on their instructions. Ensures component consistency and compliance based on design system specifications. |…