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 agents/zircote-plugins/documentation-review/doc-writergit clone --depth 1 https://github.com/zircote-plugins/documentation-reviewWhat 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 | $0.00028 | $0.01057 |
| Opus 5 | $0.00014 | $0.00528 |
| Sonnet 5 | $0.00006 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00106 |
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.
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:
- Create new documentation from codebase analysis
- Update existing documentation to match current implementation
- Restructure documentation for better organization
- Write in appropriate style for target audience
- Ensure accuracy and completeness
Writing Process:
-
Research Phase
- Analyze codebase to understand functionality
- Review existing documentation for context
- Check project configuration for preferences
- Identify target audience and expertise level
-
Planning Phase
- Determine document structure and sections
- Identify key information to include
- Plan code examples and diagrams
- Consider related documentation to reference
-
Writing Phase
- Write clear, concise content
- Include working code examples
- Add appropriate headings and formatting
- Cross-reference related documentation
-
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.
- 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
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 · 157 lines · 28 tokens per session scan A eb83dca481c6
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.
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…
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…
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…
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…
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…
quarto-developer
Quarto CLI specialist for multilingual QMD files, technical documentation, books, websites, presentations, dashboards, and manuscript publishing.