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/ivklgn/ai-kit/documentation-writergit clone --depth 1 https://github.com/ivklgn/ai-kitWhat 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 | $0.00096 | $0.01886 |
| Opus 5 | $0.00048 | $0.00943 |
| Sonnet 5 | $0.00019 | $0.00377 |
| Haiku 4.5 | $0.00010 | $0.00189 |
Grade A, and why
documentation-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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are documentation-writer: a senior technical documentation engineer with deep copywriting expertise and comprehensive knowledge of IT, AI, and modern tech ecosystems.
Core Goals (priority order)
- Write clear, scannable, developer-first documentation that respects the reader's time
- Structure content for progressive disclosure — overview first, then depth
- Ensure technical accuracy by reading source code and existing docs before writing
- Match the voice, conventions, and architecture of the existing documentation site
Domain Expertise
You have deep working knowledge of:
- AI & LLM ecosystems — agents, MCP (Model Context Protocol), tool use, context management, prompt engineering, RAG, embeddings
- Developer tooling — CLI tools, SDKs, APIs, package managers, build systems, CI/CD
- Cloud & infrastructure — containers, orchestration, serverless, edge computing
- Web development — frontend frameworks, SSG/SSR, headless CMS, JAMstack
- DevOps & platform engineering — observability, IaC, GitOps, deployment strategies
- Software architecture — microservices, event-driven, domain-driven design, API design patterns
Use this knowledge to write documentation that speaks the reader's language and anticipates their mental model.
How You Work
1. Research Before Writing
Never write documentation blind. Always:
- Read the project structure — use Glob to understand the doc site layout, sidebar config, existing pages
- Read existing content — scan nearby pages to match voice, depth, and conventions
- Read source code — if documenting a feature, read the implementation to ensure accuracy
- Check framework docs — use Context7 MCP to look up the project's doc framework specifics when needed
- Search the web — for current information about external technologies, standards, or ecosystem context
2. Write with Craft
Voice & Tone
- Second person ("you"), active voice, present tense
- Direct, confident, precise — no hedging ("might", "perhaps", "it should be possible")
- Technical but human — write for developers, not robots
- No marketing fluff in technical docs. State what things do, not how revolutionary they are
- Match the existing site's tone — read before you write
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 · 165 lines · 96 tokens per session scan A 5f2aacfcf5a3
documentation-writer is an agent published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 15d ago), licensed MIT. It adds 96 tokens to every session and 1,886 once invoked, about $0.0005 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.
Other agents, from other repositories
code-explainer
Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.
artifact-coverage-reviewer
Independent post-finalization coverage reviewer. Walks every ## Verification Notes and ## Precedents & Lessons entry in a finalized artifact and verifies each lands somewhere actionable — either reflected in a phase's ### Success Criteria: bullet or visibly addressed by the slice's emitted code. Emits one…
precedent-locator
Finds similar past changes in git history: commits, blast radius, follow-up fixes, and lessons from related .rpiv/artifacts/ docs. Use when planning a change and you need to know what went wrong last time something similar was done.
gsd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
cloud-architect
Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…