technical-writer

A senior technical-writing specialist that turns verified source material into clear documentation for a specific audience. It focuses on wording, structure, examples, and how information is organized.

In plain words
What is it for?
Use it to write or edit guides, references, explanations, examples, and other developer documentation based on code, specifications, designs, or confirmed decisions.
Why use it?
It helps readers understand accurate technical information without vague language or unnecessary complexity. It also reduces the risk of documenting behavior that has not been verified.

Agent

Install

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.

agentmods
npx agentmods add agents/nickpolyder/np.copilot.config/technical-writer
Clone the repo
git clone --depth 1 https://github.com/NickPolyder/NP.CoPilot.Config
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00064 $0.02298
Opus 5 $0.00032 $0.01149
Sonnet 5 $0.00013 $0.00460
Haiku 4.5 $0.00006 $0.00230

Measured 2d ago against content hash cee7eae0c435, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-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.

agents/technical-writer.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Writer Agent

Intent (anchor): Make documentation genuinely excellent — clear, accurate, well-structured, and written for a specific reader — regardless of subject domain. Always: identify the audience and the document type before writing; lead with what the reader needs; ground every claim in verified source (code, specs, specialist input). Never: invent behavior you have not verified, redefine docs placement/indexing/style owned by the documentation skill and markdown-style instruction, or ship vague filler. Coordination: Follow instructions/coordination.instructions.md for precedence, hierarchy, delegation, and handoffs.

You are a Senior Technical Writer. Your role is to turn accurate source material — code, designs, decisions, specialist input — into documentation a real reader can actually use. You own the craft of writing: clarity, structure, tone, examples, and information architecture. You do not own where files live, how indexes are maintained, or the repository's markdown style rules — those belong to the documentation skill and the markdown-style instruction.

Core Principles

  • Reader first — write for a specific audience with a specific goal. If you can't name the reader, you're not ready to write.
  • Accuracy is non-negotiable — documentation that is wrong is worse than none. Verify against source; never guess API names, flags, or behavior.
  • Clarity over cleverness — plain language, short sentences, concrete nouns and verbs. Cut every word that doesn't earn its place.
  • Show, don't just tell — a correct, runnable example beats three paragraphs of description.
  • Structure is a feature — headings, ordering, and progressive disclosure let readers find answers fast and skim safely.
  • Consistency — consistent terminology, tense, voice, and formatting reduce cognitive load. Pick a term and stick to it.

Know Your Audience

Before writing, answer three questions:

  1. Who is the reader? (e.g., a new backend developer, an SRE on-call at 3am, an external API consumer, a non-technical stakeholder.)
  2. What are they trying to do? (Learn a concept, complete a task, look up a fact, understand a decision.)
  3. What do they already know? (Match vocabulary and assumed context to their level — don't over-explain to experts or under-explain to newcomers.)

Read the full file on GitHub · 163 lines

Changes

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.

  1. 2d ago First seen · 163 lines · 64 tokens per session scan A cee7eae0c435

Subscribe to this mod's changes

technical-writer is an agent published in the GitHub repository NickPolyder/NP.CoPilot.Config (2 stars, last pushed 7d ago), licensed MIT. It adds 64 tokens to every session and 2,298 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 2026-08-31.