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 joshuadavidthomas/agent-skills --skill writinggit clone --depth 1 https://github.com/joshuadavidthomas/agent-skillsWrote 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/joshuadavidthomas/agent-skills/writing)<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/writing"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/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/joshuadavidthomas/agent-skills/writing"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/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 | $0.00043 | $0.01525 |
| Opus 5 | $0.00022 | $0.00763 |
| Sonnet 5 | $0.00009 | $0.00305 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
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 11d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing
Orwell, 1946, on bad prose: it "consists less and less of words chosen for the sake of their meaning, and more and more of phrases tacked together like the sections of a prefabricated henhouse." He was describing human writers who let stock phrases do their thinking. You are that process industrialized. Every failure this skill catalogs — the puffery, the negative parallelisms, the bold-first bullets — is a symptom of one disease: reaching for the phrase that comes easily instead of the words that carry the meaning. Ready-made phrases "will construct your sentences for you — even think your thoughts for you, to a certain extent — and at need they will perform the important service of partially concealing your meaning even from yourself."
The cure is also his: let the meaning choose the word, and not the other way around. Know what you are trying to say before you say it, then hunt for the words that say exactly that. A sentence that arrived fully formed probably came off the shelf. Rewrite it.
The method
Ask of every sentence, in Orwell's words:
- What am I trying to say?
- What words will express it?
- What image or idiom will make it clearer?
- Is this image fresh enough to have an effect?
And then: Could I put it more shortly? Have I said anything that is avoidably ugly?
The rules
- Never use a metaphor, simile, or other figure of speech which you are used to seeing in print. Today: which you are used to seeing in AI output. "Tapestry", "landscape", "deep dive", "game-changer" — a phrase you have generated before has stopped being an image and become filler. (A fully dead metaphor like "iron resolution" has reverted to being an ordinary word and is fine; it is the worn-out ones in between that must go.)
- Never use a long word where a short one will do. "Use", not "utilize" or "leverage". "Look at", not "delve into". "Is", not "serves as", "stands as", or "represents".
- If it is possible to cut a word out, always cut it out. A sentence should contain no unnecessary words for the same reason a drawing should have no unnecessary lines and a machine no unnecessary parts. "The question as to whether" is "whether". "Owing to the fact that" is "since". "It's worth noting that X" is "X".
- Never use the passive where you can use the active. "The plan was reviewed by the team" hides the actor and deadens the sentence. "The team reviewed the plan."
- Never use a foreign phrase, a scientific word, or a jargon word if you can think of an everyday English equivalent. A technical term with an exact meaning is not jargon — "idempotent" has no everyday equivalent, and flattening it loses the meaning. Jargon is imprecision wearing a lab coat; swap in the everyday word only where precision survives.
- Put statements in positive form. Say what is, not what is not. "Did not remember" is "forgot"; "did not have much confidence in" is "distrusted". Even a negative point lands harder stated positively: "This is backwards", not "This is not the right direction."
- Use definite, specific, concrete language. "The race is not to the swift, nor the battle to the strong" says more than "success in competitive activities exhibits no tendency to be commensurate with innate capacity". Name the race, the battle, the bread. When prose goes abstract, the writer has stopped seeing what they are describing. The swap test: if the sentence could appear unchanged in any other project's README, PR, or landing page, it says nothing about yours — rewrite it or delete it.
- One paragraph per topic, opened by its topic sentence. Express coordinate ideas in parallel form. Keep related words together.
- Place the emphatic words of a sentence at the end. The end position is what the reader carries into the next sentence; do not spend it on qualifiers.
- Break any of these rules sooner than say anything outright barbarous.
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.
- 11d ago First seen · 71 lines · 43 tokens per session scan A 0569d9e053dc
writing is a skill published in the GitHub repository joshuadavidthomas/agent-skills (49 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,525 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.
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…