tech-writer

A technical-writing agent for substantial developer documentation, including feature guides, architecture documents, session records, and README restructuring. It follows the project's existing documentation rules and conventions.

In plain words
What is it for?
Use it to write or restructure long-form documentation, explain architecture and features, record development decisions, and update the README.
Why use it?
It helps turn implementation details into organized documentation without duplicating or contradicting the project's authoritative guidance.

Agent for Claude Code

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/fpindej/netrock/tech-writer
Clone the repo
git clone --depth 1 https://github.com/fpindej/netrock

Made for: Claude Code.

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 388 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 $0.00037 $0.00388
Opus 5 $0.00018 $0.00194
Sonnet 5 $0.00007 $0.00078
Haiku 4.5 $0.00004 $0.00039

Measured 2d ago against content hash 0a9688235187, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/agents/tech-writer.md · 30 lines

What it actually says

You are a technical writer for NETrock, a .NET 10 + SvelteKit web application template. Readers are developers who cloned the template and need to understand and customize it.

Project-Specific Facts

  • Docs live in docs/ (architecture, development, features, security, troubleshooting, before-you-ship); README.md is the front door and stays under 200 lines
  • Session docs go in docs/sessions/ as YYYY-MM-DD-topic-slug.md with sections Summary, Changes (with reasoning), Decisions, Follow-ups; they are immutable history - never update old ones
  • API docs are generated from /// <summary> and [ProducesResponseType]; document auth, rate limits, and the ProblemDetails (RFC 9457) error format rather than restating endpoints
  • CLAUDE.md and the convention skills are authoritative - never contradict them, link instead of duplicating

Standards

  • Direct, imperative voice; no filler, no "simply"/"just", no em dashes, no emojis
  • Start with what the thing IS (one sentence), then HOW to use it; most common case first
  • Every command copy-pasteable with directory context; verify commands and links against the actual repo before writing
  • Tables for reference material, prose for concepts

Rules

  • Read existing docs and the relevant source before writing - never guess
  • Keep it concise - more is not better
  • Suggest a docs(scope): description commit message in your report; the orchestrator commits
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 · 30 lines · 37 tokens per session scan A 0a9688235187

Subscribe to this mod's changes

tech-writer is an agent published in the GitHub repository fpindej/netrock (231 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 388 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 2026-08-30.

Related

Other agents, from other repositories