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 psd401/psd-claude-plugins --skill tech-writinggit clone --depth 1 https://github.com/psd401/psd-claude-pluginsWrote 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/psd401/psd-claude-plugins/tech-writing)<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/tech-writing"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/tech-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/psd401/psd-claude-plugins/tech-writing"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/tech-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 | $0.00167 | $0.04007 |
| Opus 5.5 | $0.00067 | $0.01603 |
| Sonnet 5.5 | $0.00033 | $0.00801 |
| Haiku 4.5 | $0.00017 | $0.00401 |
Grade A, and why
tech-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 14d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Writing
House style for developer-facing prose, distilled from the complete Google developer documentation style guide. Almost every rule below exists for one of three reasons: accessibility (screen readers, keyboard users), translatability (a global audience with varying English proficiency), or speed (a reader in a hurry, scanning, mid-task). Keep those three reasons in mind and you can resolve cases no rule covers.
Two meta-rules outrank everything else:
- Project style wins. If the repo or team has its own conventions, follow those first.
- Clarity wins. The guide's own advice: break any of these rules sooner than write something unclear or awkward. Consistency within a document beats strict compliance.
How to work
- Establish the mode. Writing new content, editing in place, or reviewing with feedback only. If the user asked for a review, report findings — don't rewrite unasked.
- Identify the doc type — it changes the verb forms and heading style (see the next section).
- Apply the core rules in this file; they fix most drafts.
- Open reference files for depth only as the content demands them (routing table at the end). For any single-word dispute, grep the word list first — most arguments are already settled among its 598 rulings.
Doc types
| Type | Verb form | Heading style |
|---|---|---|
| Task / how-to / tutorial | Imperative: "Click Submit." | Bare infinitive: "Create an instance" (never "Creating an instance") |
| Concept / overview | Declarative, present tense | Noun phrase: "Migration to Google Cloud" (never "-ing" first word) |
| Reference (API, CLI) | Third-person -s openers: "Creates a new task." (never "Create a new task.") | The element name |
Core rules
Voice
- Second person. Address the reader as you. Never "the user" for the reader; never "let's". We only when it unambiguously means the authoring organization.
- Active voice, named actor. "The server sends an acknowledgment," not "an acknowledgment is sent." Passive is fine only when the actor is irrelevant ("The database was purged in January") or to avoid blaming the reader ("Over 50 conflicts were found").
- Present tense. No will for normal behavior; reserve it for genuinely later or asynchronous effects. Never hypothetical would — use "If you X, the server Ys."
- Conversational but precise — a knowledgeable friend, not a robot and not a clown. Use contractions, especially negative ones (don't is harder to misread than not). No humor, idioms, metaphors, pop-culture references, or exclamation points.
- Never promise ease. Delete simply, easily, just, quickly, "it's easy". What's simple for the author isn't simple for the reader.
- No "please" in instructions. "To view the document, click View." Politeness in docs is directness.
- Don't anthropomorphize. Software detects, receives, displays — it doesn't see, think, want, or know.
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.
- 14d ago Changed · -1 lines 896679e2fc41
- 1mo ago Changed 24cb59bb3e21
- 2mo ago First seen · 279 lines · 167 tokens per session scan A 5810279b4213
tech-writing is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 167 tokens to every session and 4,007 once invoked, about $0.0007 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…
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…