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 skills add afaraha8403/balakit --skill documentation-writergit clone --depth 1 https://github.com/afaraha8403/balakitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/afaraha8403/balakit/documentation-writer)<a href="https://agentmods.dev/skills/afaraha8403/balakit/documentation-writer"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/documentation-writer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.01382 |
| Opus 5 | $0.00048 | $0.00691 |
| Sonnet 5 | $0.00019 | $0.00276 |
| Haiku 4.5 | $0.00010 | $0.00138 |
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 7d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Writer
Leading words: research-first, evidence-aware, phase separation, scannability, BLUF (Bottom Line Up Front), progressive disclosure.
Research-first technical documentation workflow. Each phase ends with a checkpoint the agent must complete before proceeding — phase separation prevents the agent from drafting prose before the truth is gathered.
How this relates to subagents
Cursor does not expose user-defined nested sub-sub-agents in skill files. What you can do in practice:
- Phased work: Treat each phase below as a distinct pass. That mimics routing without a separate UI.
- Built-in delegation: If the host agent can launch a
Task/exploresubagent, use a read-only explore pass for large or unfamiliar codebases before drafting. Do not assume that tool exists; use it only when present. - Online research: Use web search (and official docs links from results) for anything version-sensitive or external.
Phase 1 — Discover (know what exists in-repo)
Read relevant files. For unfamiliar or large codebases, delegate broad mapping to an explore subagent when available.
Exit criteria: You can list every file/API/feature the docs must cover. 🛑 Checkpoint: Do not proceed to Research until the user confirms the scope (or you are explicitly operating solo and the scope is unambiguous).
Phase 2 — Research (external truth)
Run web research before asserting facts about:
- Library/framework APIs, CLI flags, config keys, breaking changes, deprecations
- Install commands, system requirements, LTS/support timelines
- Security or compliance claims (cite sources; avoid unsourced absolutes)
Process: Form 2-4 precise search queries (product + version + topic). Prefer primary sources (official docs, repo README, standards bodies) over random blogs. Capture citations (link + short note of what it supports). If sources conflict, say what is uncertain and what to verify locally.
Exit criteria: Every claim you will make has a source link. 🛑 Checkpoint: Do not proceed to Outline until Research is complete.
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.
- 7d ago First seen · 153 lines · 95 tokens per session scan A d20a201d20b0
documentation-writer is a skill published in the GitHub repository afaraha8403/balakit (1 stars, last pushed 10d ago), licensed MIT. It adds 95 tokens to every session and 1,382 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 2026-08-31.
Other skills, from other repositories
documentation-standards
Use when writing README files, API documentation, user guides, or technical documentation following industry standards from Google, Microsoft, and GitLab style guides.
diataxis
Classify, create, review, and maintain documentation using the Diátaxis framework — the four-quadrant system (tutorials, how-to guides, reference, explanation) that separates documentation by user need. Use this skill whenever the user wants to classify documentation into quadrants, perform a documentation gap…
changelog
Generate, update, review, and maintain changelogs using Keep a Changelog format, semantic-release, and conventional commits. Use this skill whenever the user wants to add a changelog entry, prepare release notes, document version changes, generate a changelog from git history, configure semantic-release, understand…
api-documentation
Patterns and templates for creating comprehensive API documentation using OpenAPI/Swagger, AsyncAPI, and manual documentation approaches. Use this skill whenever the user wants to document REST endpoints, generate or improve an OpenAPI spec, create Swagger docs, document WebSocket/event-driven APIs with AsyncAPI…
documentation-standards
Standards and patterns for creating, reviewing, and improving technical documentation — covering markdown formatting, heading hierarchy, code blocks, links, writing style, accessibility, and language-native doc toolchains (rustdoc, godoc, Sphinx, TypeDoc, Javadoc, DocC, ExDoc). Use this skill whenever the user wants…
diataxis-docs-framework
Enterprise technical documentation best practices, patterns, and frameworks for developer and partner adoption. Covers content architecture (Diataxis four quadrants), 14 content types (tutorials, how-to guides, API reference, SDK docs, migration guides, changelogs, runbooks, integration guides, troubleshooting…