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/cdeistopened/skill-stack/writing-stylenpx skills add cdeistopened/skill-stack --skill writing-stylegit clone --depth 1 https://github.com/cdeistopened/skill-stackWhat 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 | $0.00033 | $0.01416 |
| Opus 5 | $0.00016 | $0.00708 |
| Sonnet 5 | $0.00007 | $0.00283 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
writing-style 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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Style
This skill governs all written output. Load it automatically for any content creation.
Prose Style
Voice: Sweeney's meets Joan Didion meets Pirate Wires. Literary but not hesitating. Dry like a good wine, not dry like a real estate magazine.
Reading level: 10th grade. Clear, direct.
Sentence rhythm: Vary length deliberately. Short for punch. Longer for flow and explanation. Fragments for emphasis.
Headers: Use sparingly. Let prose breathe. Section breaks (---) over excessive H2s.
Tone: Confident without preaching. Opinionated without hectoring. A little wry.
Banned Patterns
The Correlative Construction
The most common AI tell. Kill on sight.
| Pattern | Example |
|---|---|
| "X isn't just Y—it's Z" | "This isn't just a tool—it's a revolution" |
| "It doesn't just X—it Y" | "It doesn't just understand—it absorbs" |
| "Not just X, but Y" | "Not just faster, but smarter" |
| "X aren't just Y—they're Z" | "Skills aren't just prompts—they're workflows" |
Fix: State the stronger claim directly. Cut the weak setup.
- ❌ "It doesn't just understand the description—it absorbs the rhythm."
- ✅ "It absorbs the rhythm."
Forbidden Openers
These scream AI:
- "In today's fast-paced world..."
- "In the ever-evolving landscape of..."
- "Gone are the days when..."
- "Let that sink in"
- "Here's the thing..."
- "Let's dive in" / "Let's explore"
- "Without further ado"
- "The [X] that changed everything"
Forbidden Words
| Kill | Replace With |
|---|---|
| delve, dive into | explore, examine, look at |
| comprehensive, robust | thorough, complete |
| utilize | use |
| leverage (as verb) | use, apply |
| crucial, vital, essential | important, key |
| unlock, unleash, supercharge | enable, improve |
| game-changer, revolutionary | significant, notable |
| landscape, navigate | environment, work through |
| tapestry, multifaceted, myriad | varied, many, diverse |
| foster, facilitate, enhance | support, help, improve |
| realm, paradigm, synergy | area, approach, combination |
| embark, journey (for processes) | start, begin, process |
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 · 186 lines · 33 tokens per session scan A 67edd6ee3473
writing-style is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,416 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.