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 AnthonyPoschen/agent-skills --skill technical-writinggit clone --depth 1 https://github.com/AnthonyPoschen/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/anthonyposchen/agent-skills/technical-writing)<a href="https://agentmods.dev/skills/anthonyposchen/agent-skills/technical-writing"><img src="https://agentmods.dev/badge/skills/anthonyposchen/agent-skills/technical-writing.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01021 |
| Opus 5 | $0.00023 | $0.00511 |
| Sonnet 5 | $0.00009 | $0.00204 |
| Haiku 4.5 | $0.00005 | $0.00102 |
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 6d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writing
Use this skill to write for a tired developer who should understand the first read. It is adapted from pstack's technical writing skill under its MIT license, but stands alone and has no pstack only dependencies.
Write Plain English
- Cut words that do no work. Write “to”, not “in order to”. Delete “it is important to note that”.
- Use short, ordinary words unless a technical term adds needed precision. Write “use”, not “utilize”; “move”, not “relocate”; and “help”, not “facilitate”.
- Write the real symbol, file path, flag, command, type, or field name. Do not replace it with a vague description.
- Use one name for one thing throughout the document.
- Do not invent jargon, metaphors, or made up hyphenated phrases. Use words a developer would say out loud.
- Prefer a period to an em dash. Use a new sentence when the thought changes.
- Keep related words close. Put “only” and “not” next to the word they change.
- Break up dense noun strings. Write “the script that checks imports”, not “the import budget check script”.
The rules serve the reader. Rewrite a sentence that sounds mechanical instead of following a rule in a way that makes the sentence worse.
Choose One Document Mode
Pick one mode for each document. Split and link documents when their purposes conflict.
- Tutorial: teach a newcomer by guiding them through a visible result.
- How to guide: help a capable reader complete one task. Keep only the steps and decisions needed for that task.
- Reference: describe facts, options, limits, inputs, outputs, and errors. Mirror the thing being described. Do not persuade or teach.
- Explanation: answer a bounded “why” question with context, constraints, alternatives, and tradeoffs.
Write Clear Sentences
- Address the reader as “you” when giving instructions.
- Use active voice when the actor matters. State who does what.
- Write instructions as commands. Put a condition before the step it controls.
- Put the common case first. Put exceptions after it.
- Give each sentence one instruction or one main thought. Split a sentence that carries more.
- Keep articles and verbs when they make the sentence easier to parse.
- Make each “it”, “they”, “this”, and “which” point to one obvious noun. Repeat the noun when that is clearer.
- Use “both … and”, “either … or”, and “if … then” when they prevent ambiguity.
- Avoid passive constructions such as “the file should be updated”. Write “update the file”.
- Read awkward text aloud. Rewrite it if it still sounds awkward.
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.
- 6d ago First seen · 102 lines · 47 tokens per session scan A 19f8ab31a29d
technical-writing is a skill published in the GitHub repository AnthonyPoschen/agent-skills (2 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,021 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 2026-08-31.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…