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 agentmods add skills/docs-plus/docs.plus/tech-writernpx skills add docs-plus/docs.plus --skill tech-writergit clone --depth 1 https://github.com/docs-plus/docs.plusWhat 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 | $0.00090 | $0.03593 |
| Opus 5 | $0.00045 | $0.01796 |
| Sonnet 5 | $0.00018 | $0.00719 |
| Haiku 4.5 | $0.00009 | $0.00359 |
Grade A, and why
tech-writer 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 2d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Writer ✍️
Senior-tech-writer voice, ready to use. The job: simple, straightforward, cohesive prose that respects the reader's time. No throat-clearing, no marketing voice, no structure for its own sake.
Default mode. Short over long, concrete over abstract, active over passive, present-tense over conditional. Cut, then cut again. The first draft is always too long.
Constraints (override everything)
- Lead with the answer, not the journey. If a TL;DR exists, it goes first. Conclusion before rationale.
- Active voice, present tense, verb-first. Name the actor. "Returns the URL" — not "Will return…" or "This function returns…". Use the passive only when no actor exists, or when the actor does not matter.
- Cut throat-clearing. Strike "In order to…", "It should be noted that…", "Please find below…". Start with what matters.
- Cut hedges. Strike
just,simply,basically,very,really,quite,essentially. Length without signal. - No marketing voice. Strike
robust,seamless,powerful,cutting-edge,world-class,enterprise-grade. Show capability with concrete behavior. - Single source of truth. Cross-link instead of duplicating. Two copies of the same fact = one is wrong.
- No structure for its own sake. No FAQ unless 3+ real questions exist. No glossary unless 5+ unique terms. No "Background" section just because templates have one.
- No emojis unless the doc's existing style already uses them.
- Don't restate the heading in the first sentence. Heading "Configuration" → don't open with "This section describes how to configure X."
- No plan or brainstorm labels (
v1,v2,phase 1,MVP, "green doc") in durable docs, memory, or commit copy — describe shipped behavior in plain terms. Real API/schema version strings (/rest/v1/,CommentAnchorV1) stay when they are the actual contract. - Never invent claims. If a fact about behavior, performance, or compatibility isn't in the source, ask — don't write.
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.
- 2d ago First seen · 253 lines · 90 tokens per session scan A a8f178a0de68
tech-writer is a skill published in the GitHub repository docs-plus/docs.plus (88 stars, last pushed 4d ago), licensed MIT. It adds 90 tokens to every session and 3,593 once invoked, about $0.0005 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
docx
Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.
document-converter
Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown. Provides the agent with conversion strategies for academic and research workflows.
docx-manipulation
Create, edit, and manipulate Word documents programmatically using python-docx.
add-format
End-to-end checklist for adding a new input or output format to AILANG Parse (docparse). Use when the user says 'add support for X format', 'wire up a new parser', 'add .foo format', 'add a parser for .bar', 'support .baz files', 'ship format X', 'can we parse .qux', 'new format rollout', or mentions a file extension…
landing-page
Create a new AILANG Parse documentation/landing page targeting a specific keyword or topic. Use when user says 'new landing page', 'new page for X', 'create a page about X', 'landing page for keyword X', or wants to add a documentation page to the docs/ site. Also use when the user references long-tail keywords, SEO…
benchmark
Run OfficeDocBench evaluation and refresh benchmark scores across the AILANG Parse website. Use when the user says 'run benchmarks', 'rerun the benchmark', 'refresh benchmark numbers', 'update bench scores', 'regenerate summary.json', mentions OfficeDocBench, asks to evaluate parsers, asks why scores are out of sync…