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 cfcosta/writing-styles --skill asd-ste100git clone --depth 1 https://github.com/cfcosta/writing-stylesWrote 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/cfcosta/writing-styles/asd-ste100)<a href="https://agentmods.dev/skills/cfcosta/writing-styles/asd-ste100"><img src="https://agentmods.dev/badge/skills/cfcosta/writing-styles/asd-ste100/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/cfcosta/writing-styles/asd-ste100"><img src="https://agentmods.dev/badge/skills/cfcosta/writing-styles/asd-ste100.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 | $0.00065 | $0.01335 |
| Opus 5 | $0.00032 | $0.00668 |
| Sonnet 5 | $0.00013 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
asd-ste100 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASD-STE100 Simplified Technical English (Issue 9)
STE is a controlled natural language and an international standard for technical documentation. Its writing rules (Part 1) have 9 sections that contain 53 rules. Its dictionary (Part 2) gives 875 approved words and alternatives for words that are not approved. This skill tells you how to apply the rules and the dictionary when you write.
When to use
Apply this skill when you write or rewrite technical documentation in STE. STE has two types of writing:
- Procedural writing (Section 5). Procedures give instructions that tell the reader how to do a task. Write each instruction in the imperative (command) form.
- Descriptive writing (Section 6). Descriptions give information, not instructions. The imperative form is not permitted. Examples: a description of a system, a report, or a note in a procedure.
How to write STE
- Identify the type of text: procedural (Section 5) or descriptive (Section 6).
- Select the words. Obey the word-selection flow in references/word-selection.md. When you do not know if a word is approved, find it in the dictionary files:
- Approved words:
grep -i "^ACCESS " references/dictionary-approved.md - Words that are not approved:
grep -i "^accomplish " references/dictionary-unapproved.md
- Approved words:
- Apply the core limits in the table below.
- Apply all 53 rules in references/writing-rules.md.
- Write the safety instructions. Obey Section 7 and the "Safety instructions" section below.
- Do a check of your text with the checklist below.
Core limits
These limits always apply. The rule numbers refer to Part 1 of the standard.
| Limit | Rule |
|---|---|
| Maximum 20 words in each sentence of a procedure (safety instructions included) | 5.1 |
| Maximum 25 words in each sentence of descriptive text | 6.3 |
| Maximum 25 words in each sentence of a note | 5.5 |
| Maximum of six sentences in each paragraph | 6.6 |
| Multi-word nouns of no more than three words | 2.1 |
| Only the approved verb forms and tenses: infinitive, imperative, simple present, simple past, simple future, past participle (as an adjective) | 3.2 |
| Use the active voice. In descriptive writing, the passive voice is permitted only if the agent is unknown | 3.6 |
| Only one instruction in each sentence, unless two or more actions occur at the same time | 5.2 |
| No semicolon (;) | 8.1 |
| In a vertical list, a colon (:) has the same effect on word count as a period | 8.4 |
| Text in parentheses counts as one word in its sentence | 8.5 |
| These count as one word each: numbers, numbers with units, abbreviations, alphanumeric identifiers, quoted text, titles, headings, placard text, and proper nouns | 8.6 |
| Hyphenated words count as one word | 8.7 |
| When applicable, use an article (the, a, an) or a demonstrative adjective (this, these) before a noun or a multi-word noun | 4.5 |
What ships with it
7 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.
- 10d ago First seen · 83 lines · 65 tokens per session scan A 4fa0b3b3c80b
asd-ste100 is a skill published in the GitHub repository cfcosta/writing-styles (32 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,335 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 2026-08-30.
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…