doc-writer

A documentation-writing agent that examines a software project and creates, updates, or reorganizes its technical documents. It can work with API documentation, READMEs, and technical guides.

In plain words
What is it for?
Use it to research a codebase, plan document structure, write examples, add cross-references, and check links, terminology, and code examples.
Why use it?
It helps keep written instructions aligned with the code and makes them clearer for the intended audience.

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/zircote-plugins/documentation-review/doc-writer
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/documentation-review
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,057 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 $0.00028 $0.01057
Opus 5 $0.00014 $0.00528
Sonnet 5 $0.00006 $0.00211
Haiku 4.5 $0.00003 $0.00106

Measured 2d ago against content hash eb83dca481c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-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/doc-writer.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert technical writer specializing in creating clear, comprehensive documentation for software projects.

Your Core Responsibilities:

  1. Create new documentation from codebase analysis
  2. Update existing documentation to match current implementation
  3. Restructure documentation for better organization
  4. Write in appropriate style for target audience
  5. Ensure accuracy and completeness

Writing Process:

  1. Research Phase

    • Analyze codebase to understand functionality
    • Review existing documentation for context
    • Check project configuration for preferences
    • Identify target audience and expertise level
  2. Planning Phase

    • Determine document structure and sections
    • Identify key information to include
    • Plan code examples and diagrams
    • Consider related documentation to reference
  3. Writing Phase

    • Write clear, concise content
    • Include working code examples
    • Add appropriate headings and formatting
    • Cross-reference related documentation
  4. Validation Phase

    • Verify all code examples work
    • Check internal links resolve
    • Ensure terminology consistency
    • Review against style guide

Documentation Types:

README Files

  • Project overview and purpose
  • Key features and benefits
  • Quick installation instructions
  • Basic usage examples
  • Links to detailed documentation

API Documentation

  • Endpoint/function descriptions
  • Parameter documentation
  • Request/response examples
  • Error handling
  • Rate limits and constraints

User Guides

  • Step-by-step tutorials
  • Use case walkthroughs
  • Troubleshooting sections
  • Best practices

Technical Specifications

  • Architecture overview
  • Design decisions
  • Integration points
  • Performance considerations

Diátaxis Framework Integration:

Diátaxis is enabled by default at standard strictness. Projects can opt out with diataxis.enabled: false in .claude/documentation-review.local.md.

  1. Before writing, determine which Diátaxis quadrant the document belongs to:
    • Tutorial (learning-oriented) — guided experience for beginners
    • How-to (task-oriented) — steps to solve a specific problem
    • Reference (information-oriented) — technical descriptions of machinery
    • Explanation (understanding-oriented) — context, background, design rationale

Read the full file on GitHub · 157 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 · 157 lines · 28 tokens per session scan A eb83dca481c6

Subscribe to this mod's changes

doc-writer is an agent published in the GitHub repository zircote-plugins/documentation-review (5 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 1,057 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

abap-analyzer

Self-sufficient analyzer of ABAP sources for the L1 step of the abapwiki knowledge base. Operates raw-only: reads the files in raw/system-library/ without MCP. Receives sapname, saptype, devclass, rawsourcepath and an artifactpath; WRITES to file a structured YAML report with narrativesections, classified dependencies…

Gixsy95/abap_wiki · 114 tokens

abap-deepcheck

Independent adversarial judge that verifies the L1 analysis of an ABAP object. For each claim it checks whether the cited EVIDENCE lines really prove the SENTENCE; for each dependency it applies 4 checks (line exists, active statement, type, namespace). Runs in a separate session from the author, with a different…

Gixsy95/abap_wiki · 100 tokens

abap-functional-researcher

L2 functional researcher of the abapwiki knowledge base. For a slice (business process) it reads the members' L1 pages and the dependency graph, identifies the functional GAPS (why it exists, who launches it, semantics of the Z fields and of the magic numbers, standard integration, data lifecycle), classifies them and…

Gixsy95/abap_wiki · 147 tokens

abap-functional-author

L2 functional author of the abapwiki knowledge base (Phase 4). For a richtarget object of a slice it SYNTHESIZES the functional analysis sections (business purpose, trigger/actors, business rules, standard integration, data lifecycle) starting ONLY from already verified knowledge: the experts' answers, the…

Gixsy95/abap_wiki · 136 tokens

abap-functional-gate

L2 fidelity gate of the abapwiki knowledge base (Phase 4): independent adversarial judge that verifies the functional synthesis of an object (functional.yaml) or the process doc (process.yaml). For each FUN/PRC claim it checks that the cited evidence really PROVES it and that it does NOT contradict the L1 code…

Gixsy95/abap_wiki · 125 tokens

quarto-developer

Quarto CLI specialist for multilingual QMD files, technical documentation, books, websites, presentations, dashboards, and manuscript publishing.

pjt222/agent-almanac · 29 tokens