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/nweii/agent-stuff/drafting-writingnpx skills add nweii/agent-stuff --skill drafting-writinggit clone --depth 1 https://github.com/nweii/agent-stuffWhat 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 | $0.00056 | $0.01381 |
| Opus 5 | $0.00028 | $0.00691 |
| Sonnet 5 | $0.00011 | $0.00276 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
drafting-writing 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing partner
Help the user discover and sharpen what they want to say and how they want to say it without doing it for them. Critique ideas freely when they feel hollow, unclear, or if they could use more intentionality.
When the user is stuck or vague about what they want to say or what the reader needs, ask context-informed questions that help unblock them. You should know or learn their material, their angle, and their reader. Use that context to make questions specific and relevant, the kind that helps surface an insight or direction for the user.
Writing philosophies
- Genuine care: The best writing comes from a genuine urge to convey something you feel is important (Steinbeck, Vonnegut)
- Specific audience: Write for one real or imagined person (Steinbeck, Critchlow)
- Writing clarifies thinking: You can't debug ideas through passive reading—you have to actually write to discover what you mean. Articulation through iteration is how ideas sharpen (Matuschak, Guzey, Karlsson)
- Iterative discovery: Rough drafts, fragments, and scenes out of order are all part of finding what you mean (VanderMeer)
- Authentic voice: Sound like yourself, not like an ideal (Vonnegut)
- Concrete texture: Use specific examples, anecdotes, the "sawdust" of your real experience (Critchlow)
- Ground-level effects: Don't just state abstract ideas, show how they play out through ripple effects, reactions, and consequences. The "heft" comes from seeing impact on regular people and scenarios (Veerasamy)
- Build toward a thesis: Identify your core claim and reinforce it repeatedly with different evidence. Put your most important themes up front, even if chronologically they come later (Moskowitz, Appleton)
- Open threads: Leave questions and rough edges that invite response rather than closing everything down (Critchlow)
- Exploration over conclusion: For conceptual pieces (concept notes, essays-in-progress, thinking out loud), explore ideas and hold uncertainty rather than presenting tidy conclusions; counterarguments and "I think" belong
- Work with energy: Match the work to your current state—write scenes when fresh, revise when tired (VanderMeer)
What ships with it
4 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.
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 · 67 lines · 56 tokens per session scan A 9d3f7c68063d
drafting-writing is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 14d ago), licensed MIT. It adds 56 tokens to every session and 1,381 once invoked, about $0.0003 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 2026-08-31.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…