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 boparaiamrit/skills-by-amrit --skill writing-documentationgit clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/writing-documentation)<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/writing-documentation"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/writing-documentation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/writing-documentation"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/writing-documentation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.02748 |
| Opus 5 | $0.00015 | $0.01374 |
| Sonnet 5 | $0.00006 | $0.00550 |
| Haiku 4.5 | $0.00003 | $0.00275 |
Grade A, and why
writing-documentation scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://api.example.com/users \ How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Documentation
Overview
Documentation is code for humans. If humans can't understand your system, it might as well not exist. Bad documentation is worse than no documentation — it actively misleads.
Core principle: Write for the reader who has zero context, is in a hurry, and will judge your entire project in 30 seconds.
The Iron Law
NO PUBLIC API WITHOUT DOCUMENTATION. NO COMPLEX LOGIC WITHOUT COMMENTS. NO DOCUMENTATION THAT DOESN'T MATCH THE CODE.
When to Use
- Creating a new project or module
- Adding public APIs or exported functions
- After major architectural changes
- Before onboarding new team members
- When someone asks "how does this work?" (a documentation failure signal)
- When you struggle to explain something (sign it needs better docs)
- Before launching or publishing
When NOT to Use
- Auto-generated API reference from types (tools like TypeDoc handle this)
- Comments that restate what the code does (
// increment i by 1) - Documentation for internal implementation details that change frequently
Anti-Shortcut Rules
YOU CANNOT:
- Say "documentation is done" — verify every code example runs, every link works, every setup step succeeds
- Copy-paste code examples without testing them — stale examples are worse than no examples
- Document what you PLAN to build — only document what EXISTS and WORKS
- Write "see code for details" — if the reader needs code, the documentation failed
- Skip the Quick Start — the first 60 seconds determines if anyone reads further
- Leave TODO or "Coming soon" in documentation — remove it or write it now
- Document for yourself — document for someone who joins tomorrow
- Skip testing setup instructions — run them from scratch in a clean environment
Common Rationalizations (Don't Accept These)
| Rationalization | Reality |
|---|---|
| "The code is self-documenting" | Code explains WHAT and HOW. It never explains WHY, trade-offs, or business rules. |
| "Nobody reads documentation" | Nobody reads BAD documentation. Good docs with a Quick Start get read. |
| "We'll document it later" | Later = never. Document as you build. |
| "It's an internal project" | Internal projects have the highest onboarding cost. Your future self is "internal." |
| "The types are the documentation" | Types tell you the shape of data. They don't tell you when to use it, what happens on error, or why this API exists. |
| "Just ask the team" | That person will leave, be on vacation, or be too busy. Docs scale, people don't. |
| "Too many changes to keep docs updated" | Then automate what you can and document stable interfaces, not implementation details. |
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.
- 8d ago First seen · 354 lines · 29 tokens per session scan A 24680f85fb23
writing-documentation is a skill published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 2,748 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…