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/teamniteo/hakuto/section-docsnpx skills add teamniteo/hakuto --skill section-docsgit clone --depth 1 https://github.com/teamniteo/hakutoWhat 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 | $0.00126 | $0.02973 |
| Opus 5 | $0.00063 | $0.01486 |
| Sonnet 5 | $0.00025 | $0.00595 |
| Haiku 4.5 | $0.00013 | $0.00297 |
Grade A, and why
section-docs 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Section
Adds technical documentation with sidebar navigation to existing websites. Uses minimal content-focused design regardless of main site aesthetic. Complex multi-page system requiring existing site with site-specification.md.
Integration Workflow
Copy this checklist and track progress:
Documentation Integration:
- [ ] Step 1: Read site-specification.md
- [ ] Step 2: Determine documentation structure
- [ ] Step 3: Apply minimal design system
- [ ] Step 4: Create documentation pages
- [ ] Step 5: Use technical placeholders
- [ ] Step 6: Update site-specification.md and AGENTS.md
Step 1: Read Site Specification
Read site-specification.md (project root) to extract:
- Site type (SaaS or General)
- Theme (light or dark - docs will match)
- Existing navigation structure
- User customizations
Step 2: Determine Documentation Structure
Ask user: "What docs sections do you need? (Getting Started, API Reference, Guides, etc.)"
If no answer provided, create default structure:
For SaaS sites:
- Getting Started (Installation, Authentication, Quick Start)
- Guides (Basic Concepts, Best Practices)
- API Reference (Endpoints, Parameters, Examples)
- FAQ / Troubleshooting
For General sites:
- Getting Started (Account Setup, Walkthrough)
- How-To Guides (Task-focused)
- Features (Explanations, Use Cases)
- FAQ / Support
Step 3: Apply Minimal Design System
Docs prioritize legibility for long-form technical reading, so all design languages (Minimalist, Technology, Dark, Corporate, Brutalist, Colorful, Elegant) converge to the same minimal system. Brand color and decoration belong on marketing pages, not in reference material.
Design Principles:
- NO brand colors: No gradients, accent colors, colorful badges, category colors
- Blue links as ONLY color accent
- Generous whitespace (2-3x more than main site)
- Flat design throughout
Color Palette (CSS custom properties):
Define docs colors as CSS custom properties in index.css so themes can override them. Hardcoding hex values inline locks the docs to a single appearance and breaks dark-mode toggles.
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 · 346 lines · 126 tokens per session scan A d9b90d97c293
section-docs is a skill published in the GitHub repository teamniteo/hakuto (5 stars, last pushed 7d ago), licensed MIT. It adds 126 tokens to every session and 2,973 once invoked, about $0.0006 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
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…