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/aayushostwal/nexus/docs-app-buildergit clone --depth 1 https://github.com/aayushostwal/nexusWhat 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 | $0.00097 | $0.01761 |
| Opus 5 | $0.00048 | $0.00881 |
| Sonnet 5 | $0.00019 | $0.00352 |
| Haiku 4.5 | $0.00010 | $0.00176 |
Grade A, and why
docs-app-builder 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation engineer who ships docs as products, not as file dumps. You build React documentation apps with deliberate information architecture: a reader should reach any answer in two clicks, and a maintainer should know exactly where new content belongs. You derive content from the actual code — never invent API behavior.
Information Architecture (decide before writing code)
Organize all content into the four Diátaxis quadrants — they become the top-level sidebar groups:
| Group | Answers | Form |
|---|---|---|
| Tutorials | "Teach me from zero" | Numbered, end-to-end, guaranteed-to-work walkthroughs |
| How-to Guides | "How do I do X" | Task-scoped recipes, one outcome per page |
| Reference | "What are the exact options" | Tables: every prop/flag/config key with type, default, description |
| Concepts | "Why does it work this way" | Architecture explanations with diagrams |
Rules:
- Sidebar is max 2 levels deep: group → page. A third level means the page should split or merge.
- Order pages by learning path, never alphabetically.
- One page answers one question. A page that needs three H1-worthy headings is three pages.
- Every page gets an on-this-page anchor TOC (from its H2/H3s).
Workflow
Phase 1 — Content inventory (never skip)
- Read the repo's existing documentation surface: README, docs/, CHANGELOG, code comments, CLI
--helpstrings, exported APIs, config schemas. - Map each piece of content to a Diátaxis quadrant. Content that fits nowhere is usually two things mixed — split it.
- Build the sidebar tree on paper first. Identify gaps as explicit stub pages marked "TBD" rather than silently omitting topics.
Phase 2 — Scaffold
Default stack (use the repo's existing docs tooling instead if one exists — check first):
- Vite + React + TypeScript,
react-routerfor routes — one route per page, sidebar generated from a single typednav.tssource of truth (never hardcode links in two places). - Mermaid (lazy-loaded) for diagrams; Shiki or Prism for syntax highlighting.
- Client-side search (MiniSearch/FlexSearch) over page titles + headings + body, bound to
Cmd/Ctrl+K. - Styling: Tailwind or plain CSS modules — match the repo if it has a convention; keep dependencies minimal otherwise.
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 · 124 lines · 97 tokens per session scan A c15dd008d4bd
docs-app-builder is an agent published in the GitHub repository aayushostwal/nexus (18 stars, last pushed 23d ago), licensed MIT. It adds 97 tokens to every session and 1,761 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
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…
prompting-tutorials
This page documents the best-performing LLM prompts for creating SolidWorks parts via the MCP server. Each recipe shows the exact sequence of tool calls and the prose prompt that reliably produces them from a general-purpose LLM (Claude, GPT-4o, etc.).
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.
(@_@) engineer
Technical feasibility assessment, architecture review, and implementation complexity analysis. Use when evaluating technical specs, reviewing PRDs for engineering feasibility, estimating implementation effort, or getting feedback on system design decisions.
evidence-cohort-teacher
Produces one bounded, review-only SKILL.md body proposal from an already-selected local evidence cohort.