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 TimoBakx/ai-journaling-template --skill natural-writinggit clone --depth 1 https://github.com/TimoBakx/ai-journaling-templateWrote 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/timobakx/ai-journaling-template/natural-writing)<a href="https://agentmods.dev/skills/timobakx/ai-journaling-template/natural-writing"><img src="https://agentmods.dev/badge/skills/timobakx/ai-journaling-template/natural-writing/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/timobakx/ai-journaling-template/natural-writing"><img src="https://agentmods.dev/badge/skills/timobakx/ai-journaling-template/natural-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00142 | $0.02589 |
| Opus 5.5 | $0.00057 | $0.01036 |
| Sonnet 5.5 | $0.00028 | $0.00518 |
| Haiku 4.5 | $0.00014 | $0.00259 |
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 17d 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:
- natural-writing — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Natural Writing
LLM text has tells: overused words, formulaic structures, hollow emphasis, and length padding. This skill removes them so the result reads like a skilled human wrote it. It covers English and Dutch.
Scope: if a human reads it as sentences, this skill applies. It governs wording and structure, not warmth: persona or tone preferences configured elsewhere (emoji use in chat, informal register) stay in effect. If project instructions conflict with this skill on a specific point, the project instructions win.
Core principles
- Specific beats generic. Facts beat significance claims. Direct beats hedged. AI text drifts toward the statistical mean: concrete details blur into vague importance. Fight that drift.
- Get to the point. Never restate or paraphrase the question before answering it. Never open with empty affirmations ("Great question!", "Zeker!", "Goede vraag!").
- Length matches complexity. Simple topic, short text. Never pad to look thorough.
- First person where natural. "I chose this because...", "we liepen hier tegenaan". Don't hide behind passive voice.
- Honest about limits and trade-offs. Say "It wasn't pretty" or "dit is een aanname" when it's true.
- When rewriting, preserve weight. Keep the original's certainty level. An open observation stays an open observation; don't upgrade "misschien handig" to "moet gebeuren". Don't swap words for synonyms that shift meaning.
Forbidden patterns
Em-dash
Don't use — in either language. Replace with a colon, comma, parentheses, or two sentences.
- Bad: "The tool — released last year — is stable."
- Good: "The tool (released last year) is stable."
- Bad: "Eén groot voordeel — snelheid."
- Good: "Eén groot voordeel: snelheid."
Filler adverbs and empty transitions
If the sentence works without the word, drop it.
- EN: effectively, essentially, basically, seamlessly, effortlessly, notably, furthermore, additionally, moreover, incredibly, "It's worth noting that", "It's important to understand that", "Interestingly".
- NL: "Het is belangrijk om te vermelden/benadrukken dat", "Interessant genoeg", "Zoals eerder genoemd", and "Bovendien"/"Daarnaast"/"Verder"/"Tevens" as paragraph openers that connect nothing.
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.
- 17d ago First seen · 164 lines · 142 tokens per session scan A 857e59c200a1
natural-writing is a skill published in the GitHub repository TimoBakx/ai-journaling-template (34 stars, last pushed 18d ago), licensed MIT. It adds 142 tokens to every session and 2,589 once invoked, about $0.0006 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 2026-10-15.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.