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 duyet/oma --skill technical-writinggit clone --depth 1 https://github.com/duyet/omaWrote 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/duyet/oma/technical-writing)<a href="https://agentmods.dev/skills/duyet/oma/technical-writing"><img src="https://agentmods.dev/badge/skills/duyet/oma/technical-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/duyet/oma/technical-writing"><img src="https://agentmods.dev/badge/skills/duyet/oma/technical-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 | $0.00092 | $0.01012 |
| Opus 5.5 | $0.00037 | $0.00405 |
| Sonnet 5.5 | $0.00018 | $0.00202 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
technical-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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
technical-writing
Good technical writing answers the reader's actual question as fast as possible. Before writing a word, know: who's reading this, and what do they need to do after reading it (run a command, make a decision, understand a tradeoff)? Structure and cut ruthlessly around that.
Know the reader and their one question
- A new user wants: what is this, how do I get it running, what's the first thing to try. Lead there — not with project history or a philosophy statement.
- A maintainer six months from now wants: why does this work this way, what would break if I changed it, what did we already consider and reject.
- An on-call engineer at 3am wants: what's broken, how do I check, what's the fix — in that order, skimmable in under a minute.
Write for the reader you have, not the one who already knows the context you do.
Lead with the answer
Put the most useful sentence first — what it is, what to run, what the decision was. Explain why after, for the reader who needs it, not before, for the reader who doesn't. If a document buries the key fact in paragraph four, most readers never reach it.
README anatomy
- One-line description — what this is, in plain language.
- Quickstart — the fewest steps to a working example. A copy-pasteable command block beats three paragraphs of prose.
- Core concepts — only the vocabulary needed to use it correctly.
- Configuration/API reference — link out or collapse if long; don't make the reader scroll past it to find the quickstart.
- Where to go next — deeper docs, examples, how to get help.
ADRs: context, decision, consequences
An architecture decision record exists so nobody re-litigates a settled tradeoff without knowing what was already considered:
- Context — the problem and the constraints that shaped it (not a history lesson — just what a reader needs to evaluate whether the decision still holds).
- Decision — what was chosen, stated plainly in one or two sentences.
- Alternatives considered — what else was on the table and why it lost. This is the part that saves the next person from proposing the same rejected idea.
- Consequences — what this makes easier, what it makes harder, what becomes technical debt. Be honest about the downsides — an ADR that only lists benefits isn't trustworthy.
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.
- 1mo ago First seen · 89 lines · 92 tokens per session scan A ef21523ab493
technical-writing is a skill published in the GitHub repository duyet/oma (10 stars, last pushed 9d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,012 once invoked, about $0.0004 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 2026-08-31.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…