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/flutter/agent-plugins/natural-writingnpx skills add flutter/agent-plugins --skill natural-writinggit clone --depth 1 https://github.com/flutter/agent-pluginsWhat 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 | $0.00036 | $0.01823 |
| Opus 5 | $0.00018 | $0.00911 |
| Sonnet 5 | $0.00007 | $0.00365 |
| Haiku 4.5 | $0.00004 | $0.00182 |
Grade A, and why
natural-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.
This is a copy
100% identical to natural-writing — 63 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules for Natural Writing
This document outlines strict rules to avoid common "AI-isms"—stylistic and structural patterns that language models typically fall into. Follow these rules to produce content that is more understandable, and reads as natural, human-authored text.
1. Vocabulary & Phrasing Controls
The "Banned" List
Avoid these words, which are statistically overrepresented in AI text. Use simpler, more direct alternatives.
- Verbs: delve, underscore, highlight (as verb), foster, cultivate, maximize, leverage, democratize, ensure, align with, resonate with, encompass, bridge.
- Nouns: tapestry, landscape (abstract), realm, testament, interplay, synergy, cornerstone, hub, ecosystem (abstract).
- Adjectives: pivotal, crucial, vibrant, intricate, nuanced, unwavering, indelible, uncharted, rapidly evolving, transformative, breathtaking, nestled, dynamic.
Avoid "Copula" Substitutions
Do not replace simple "is/are" verbs with flowery equivalents.
- Bad: "The library serves as a center for learning."
- Bad: "The statue stands as a monument to..."
- Good: "The library is a center for learning."
- Good: "The statue is a monument to..."
Eliminate "Elegant Variation"
Do not use synonyms just to avoid repeating a subject's name (e.g., "the eponymous character," "the titular protagonist," "the celebrated author"). It is acceptable to repeat the name or use pronouns naturally.
Banned Temporal Words in Code & Comments
Do not use relative temporal terms in code, variable names, function names, or comments. These words lose their meaning as the codebase evolves over time.
- Banned Words: now, currently, existing behavior, previous behavior, old, new, modern.
- Bad:
// This function now uses the config parser instead of hardcoding. - Good:
// Resolves paths via [ConfigParser.loadConfig] to support custom config locations.
2. Content & Tone
No "Puffery" or Forced Significance
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 · 151 lines · 36 tokens per session scan A f89735df6046
natural-writing is a skill published in the GitHub repository flutter/agent-plugins (2,895 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 36 tokens to every session and 1,823 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to natural-writing, differing in 63 lines, and is treated as a copy.
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.