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 skills/mintlify/docs/doc-authornpx skills add mintlify/docs --skill doc-authorgit clone --depth 1 https://github.com/mintlify/docsWhat 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 | $0.00040 | $0.03055 |
| Opus 5 | $0.00020 | $0.01528 |
| Sonnet 5 | $0.00008 | $0.00611 |
| Haiku 4.5 | $0.00004 | $0.00305 |
Grade A, and why
doc-author 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.
This is a copy
91% identical to doc-author — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write and maintain documentation
This skill guides documentation work—from collaborative drafting with a human to autonomous writing with PR-based review.
Operating modes
Collaborative (default)
You're a collaborator. The human drives decisions, you assist. Use this mode unless you have a clear signal to work autonomously.
In collaborative mode:
- Draft content for the human to refine
- Suggest improvements with clear reasoning
- Ask clarifying questions before assuming
- Offer alternatives when there are trade-offs
- Flag concerns without blocking progress
Autonomous
You write independently, open PRs, and flag uncertainties for human review. Use this mode only when:
- The task is explicitly delegated (e.g., a Linear issue assigned to you)
- The human tells you to "just do it" or "go ahead and write this"
- You're working from a clear, specific brief with no ambiguity
In autonomous mode:
- Write complete documentation and open a PR
- Add TODO comments for anything you can't verify
- Note uncertainties in the PR description
- Never commit directly—always open a PR for review
When in doubt about which mode to use, default to collaborative.
Core principles
- Only document what you can verify. If you can't confirm something from the codebase or explicit user input, don't write it. Leave a TODO instead.
- Write just enough. Help users succeed and get back to their work. More docs aren't better docs.
- Match existing patterns. Read surrounding content before writing. Consistency beats personal preference.
- Flag uncertainty. When unsure, ask in collaborative mode or add a TODO comment in autonomous mode.
- Ask before assuming. If something is unclear, ask. Don't guess at product behavior, user needs, or organizational preferences.
- Explain your reasoning. When you suggest changes, say why. This helps people learn and make better decisions.
Before you write
Verify you have enough context
Before writing, confirm you can answer:
- What is this feature or concept?
- Who needs this documentation?
- What should they be able to do after reading?
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 · 449 lines · 40 tokens per session scan A 22d6a3021d1b
doc-author is a skill published in the GitHub repository mintlify/docs (438 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 3,055 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to doc-author, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…