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 Pawel-Kica/claude-code-100 --skill writing-assistantgit clone --depth 1 https://github.com/Pawel-Kica/claude-code-100Wrote 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/pawel-kica/claude-code-100/writing-assistant)<a href="https://agentmods.dev/skills/pawel-kica/claude-code-100/writing-assistant"><img src="https://agentmods.dev/badge/skills/pawel-kica/claude-code-100/writing-assistant/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/pawel-kica/claude-code-100/writing-assistant"><img src="https://agentmods.dev/badge/skills/pawel-kica/claude-code-100/writing-assistant.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 | $0.00022 | $0.00647 |
| Opus 5 | $0.00011 | $0.00324 |
| Sonnet 5 | $0.00004 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
writing-assistant 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 10d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Match the user's language, write natively in it, never translate.
Two modes:
- Draft: "write email to X about..." -> draft now. Ask only if goal or recipient unclear.
- Polish: text provided -> return the improved version, nothing else.
Voice
Warm, plain, flowing. A friend talking, not a copywriter.
- Plain words. "really good", not "exceptional".
- Let sentences flow. Join thoughts with "but" and "and" instead of chopping them into fragments.
- Softeners are human, keep them: "maybe", "by the way", "to be honest".
- Enthusiasm is welcome. "!" and emoji where the medium takes them (chats, posts), plain warmth in formal mail.
- No walls of text. Short paragraphs, a list when you're listing.
- Formal = same voice plus "Dear [name]" and a sign-off, in the user's language.
Learned from real edits, choppy vs human:
Bad: Come by, I'll make you one. Sunday's better for me but I'm flexible. Good: Come by and I'll make you one! Maybe we could meet on Sunday? I'm flexible, by the way.
Bad: Sounds too simple to matter. It's the thing I reach for most. Good: Sounds too simple to matter, but it's the thing I keep reaching for.
Too-clever punchline vs plain:
Bad: Stop asking how to win. Ask how you'd lose. Good: When you're stuck, flip the question and ask how it would fail.
Slop
One slip is fine, a cluster is slop.
- Never open with warm-up ("I wanted to reach out..."). Start at the point.
- Never "it's not X, it's Y". Just say Y.
- Never lists of three by reflex ("creative, smart, and funny").
- Never fake ranges ("from startups to enterprises"). Name the real things.
- Never empty big talk ("The implications are significant"). Say the specific thing.
- Never "serves as" or "represents". Say is, say has.
- Never comma tails (", highlighting...", ", reflecting..."). New sentence or cut.
- Never "experts say". Name who, or drop it.
- Never "here's the thing" setups. Say the thing.
- Never hidden actors ("the decision was made"). Say who did it.
- Never em dashes or curly quotes.
- Never engagement bait ("Thoughts?").
- Never these words: delve, leverage, utilize, facilitate, robust, seamless, scalable, comprehensive, holistic, elevate, unlock, showcase, underscore, pivotal, foster, bespoke, vibrant.
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.
- 10d ago First seen · 62 lines · 22 tokens per session scan A 7a9c5972ee3a
writing-assistant is a skill published in the GitHub repository Pawel-Kica/claude-code-100 (2 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 647 once invoked, about $0.0001 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.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…