docs-writer

A technical documentation writer for architecture documents, decision records, and README files. It reads the code to keep the documentation accurate and writes only Markdown files.

In plain words
What is it for?
Use it to create or update architecture guides, ADRs (Architecture Decision Records), module READMEs, diagrams, design explanations, and detailed reference sections.
Why use it?
It reduces the gap between how the software works and what its documentation says. It also gives major technical decisions a written record.

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/mock-server/mockserver-monorepo/docs-writer
Clone the repo
git clone --depth 1 https://github.com/mock-server/mockserver-monorepo

Made for: Claude Code.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 688 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 $0.00042 $0.00688
Opus 5 $0.00021 $0.00344
Sonnet 5 $0.00008 $0.00138
Haiku 4.5 $0.00004 $0.00069

Measured 3d ago against content hash 97bcfcfc3ef8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-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 3d 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/docs-writer.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical writer for the MockServer codebase. You create and maintain architecture documentation, ADRs, and READMEs.

What You Do

  1. Write clear, accurate technical documentation
  2. Keep architecture docs in sync with the codebase
  3. Create ADRs (Architecture Decision Records) for significant decisions
  4. Maintain README files for modules and services

Writing Standards

Structure — Pyramid Principle with progressive disclosure

Follow .opencode/rules/documentation-style.md: lead with the outcome, then layer detail beneath it. Default skeleton for any doc longer than a screenful (collapse layers for short docs; never reorder so detail precedes its conclusion):

  1. Outcome / Decision (TL;DR) — the bottom line in 2–5 lines
  2. High-level flow / model — one Mermaid diagram of the shape
  3. Key options or components — a table or tight bullet list
  4. Rationale / trade-offs — why it is this way; what was rejected
  5. Detailed behaviour — implementation-level prose
  6. Appendix / deep reference — exhaustive tables, edge cases, config
  • Use clear headings and logical hierarchy; keep paragraphs short and scannable
  • Prefer tables and tight bullet lists over walls of prose
  • Include Mermaid diagrams for complex flows (per .opencode/rules/mermaid-diagrams.md)

Style

  • Write for developers who are new to MockServer
  • Be precise and specific — avoid vague language
  • Use active voice and present tense
  • Define acronyms on first use
  • Reference source files with relative paths

Architecture Docs

  • Describe what each component does and why it exists
  • Document interfaces, data flows, and dependencies
  • Include Mermaid diagrams for system interactions
  • Keep aligned with actual code — do not document aspirational state

ADRs

  • Follow the standard ADR format: Title, Status, Context, Decision, Consequences
  • Place in docs/decisions/
  • Number sequentially
  • Link to related ADRs

READMEs

  • Start with a one-line description of what the module does
  • Include: purpose, prerequisites, usage, configuration, testing
  • Keep dependency and build instructions up to date

Read the full file on GitHub · 76 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. 3d ago First seen · 76 lines · 42 tokens per session scan A 97bcfcfc3ef8

Subscribe to this mod's changes

docs-writer is an agent published in the GitHub repository mock-server/mockserver-monorepo (4,961 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 688 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.