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 Mark-Life/agent-skills --skill writing-for-readersgit clone --depth 1 https://github.com/Mark-Life/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/mark-life/agent-skills/writing-for-readers)<a href="https://agentmods.dev/skills/mark-life/agent-skills/writing-for-readers"><img src="https://agentmods.dev/badge/skills/mark-life/agent-skills/writing-for-readers/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/mark-life/agent-skills/writing-for-readers"><img src="https://agentmods.dev/badge/skills/mark-life/agent-skills/writing-for-readers.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 | $0.00053 | $0.03255 |
| Opus 5 | $0.00026 | $0.01628 |
| Sonnet 5 | $0.00011 | $0.00651 |
| Haiku 4.5 | $0.00005 | $0.00326 |
Grade A, and why
writing-for-readers 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing for Readers
Write it the way you would explain it out loud to a colleague. Short, common words. The reader knows the field and is skimming, on a phone, half-deciding whether to keep going.
Assume the first draft is twice as long as it needs to be. Cutting half with no fact lost is the normal result. This file is instructions, not published prose: apply its rules, do not copy its shape.
What human prose does
Says "I" and takes a side. The writer is a person with a stake, and breaks in with an aside or a word said out loud: "Durable Objects are, well, durable." Another: "Most of this comes down to the fact that I was really good at the old software engineering."
Admits what it does not know, once, as a position: "This naive approach to memory through files has worked surprisingly well, but there's more work to do." Hedges stacked across a sentence do the opposite.
Names things. Every paragraph carries one number, proper noun or date a reader could dispute, like "a $500 iPhone". A paragraph someone who knew nothing could have written is the problem, and no sentence-level edit fixes it.
Calls back by repeating the exact words. Rotating a dashboard into an interface, then a portal, then the analytics hub is the machine move. Say "the dashboard" three times.
Variance you can measure
Print the sentences-per-paragraph sequence before publishing, then check:
- No four consecutive paragraphs with the same sentence count, except runs of single-sentence paragraphs.
- At least one paragraph in seven is a single sentence. Human posts run 20% to 52%.
- Sentence-length standard deviation of 8 words or more. Reach it by mixing about a quarter of sentences under 10 words with roughly one in twelve over 30, never by padding.
- One sentence under 5 words and one over 35 per 1000 words, the extremes on top of item 3's mix. A one-word paragraph answering its own heading counts.
- Opening sentences vary in length like every other sentence. In any four consecutive paragraphs, at most one opens on a sentence under 10 words. Short opener then explanation is a mould, and four of them in a row reads as one even when every word differs. Merge the extra short openers into the sentence that follows.
What ships with it
1 file 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 · 283 lines · 53 tokens per session scan A 7d19f956dd2a
writing-for-readers is a skill published in the GitHub repository Mark-Life/agent-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 53 tokens to every session and 3,255 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
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…