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/hachej/boring-ui/documentation-website-for-software-projectnpx skills add hachej/boring-ui --skill documentation-website-for-software-projectgit clone --depth 1 https://github.com/hachej/boring-uiWrote 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/hachej/boring-ui/documentation-website-for-software-project)<a href="https://agentmods.dev/skills/hachej/boring-ui/documentation-website-for-software-project"><img src="https://agentmods.dev/badge/skills/hachej/boring-ui/documentation-website-for-software-project.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 | $0.00046 | $0.05517 |
| Opus 5 | $0.00023 | $0.02759 |
| Sonnet 5 | $0.00009 | $0.01103 |
| Haiku 4.5 | $0.00005 | $0.00552 |
Grade C, and why
documentation-website-for-software-project scanned grade C with 2 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 6d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
4. **Package manager?** Prefer `bun` if available. If missing, offer to install via `curl -fsSL https://bun.sh/install | bash` (ask first). Fall back to `pnpm` or `npm`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **Package manager?** Prefer `bun` if available. If missing, offer to install via `curl -fsSL https://bun.sh/install | bash` (ask first). Fall back to `pnpm` or `npm`. How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Website For Software Project
The One Rule: Documentation is narrative plus reference, not a method dump. Before typing any MDX, build a mental model of the codebase; write prose that explains why and how it fits; only then drop into parameter tables.
What This Skill Produces
A deployable Nextra 4 (App Router) documentation site in a sibling directory <project>__nextra_documentation_site/, optionally deployed to Vercel. Drafted by parallel subagents across 10 phases, polished until agents stop making substantive changes.
Inputs
- Source repo path (e.g.
/data/projects/frankensqlite), or - Git URL (clone into
/tmp/first, then treat as path), or - Current working directory if nothing specified.
Outputs
<repo>__nextra_documentation_site/— initialized Nextra projectcontent/tree populated with narrative MDX (App Routercontent/convention)- Theme-polished Navbar / Footer / Banner, working search, mermaid + KaTeX, dark mode, edit link, OG image generation
- Vercel deploy with
ghintegration, or self-host viabun start/next start - Playwright smoke-test run against the deployed URL
Up-Front User Confirmations (Ask Before Starting)
- Target project path? Confirm absolute path or clone URL.
- Site directory name? Default:
<basename>__nextra_documentation_siteas a sibling. Confirm OK to create &git init. - Deploy target? Vercel (recommended; works on free tier for internal docs) or self-hosted via bun. If Vercel — do they have an account + CLI? If not, walk them through setup (see DEPLOY.md).
- Package manager? Prefer
bunif available. If missing, offer to install viacurl -fsSL https://bun.sh/install | bash(ask first). Fall back topnpmornpm. - Fresh run or resuming? If the site directory already exists, confirm whether to re-enter the phase loop (idempotent) or treat as new.
What ships with it
59 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- bundle-manifest.json 20 KB
- LICENSE.txt 340 B
- references/ADR-PATTERNS.md 13 KB
- references/ADVANCED-NEXTRA.md 25 KB
- references/AGENT-PROMPTS.md 24 KB
- references/AI-SEARCH.md 15 KB
- references/AUDIENCE.md 14 KB
- references/CONTENT-TEMPLATES.md 27 KB
- references/CORPUS-EXPORT.md 11 KB
- references/DEPLOY.md 14 KB
- references/DIAGRAMS.md 14 KB
- references/DIATAXIS.md 10.0 KB
- references/EXEMPLARS.md 33 KB
- references/EXTENDED-PROJECT-TYPES.md 16 KB
- references/FEEDBACK-PIPELINE.md 14 KB
- references/GLOSSARY-CRAFT.md 12 KB
- references/INTERACTIVE.md 17 KB
- references/LIFECYCLE.md 12 KB
- references/MEASUREMENT.md 11 KB
- references/MIGRATION.md 12 KB
- references/NEXTRA.md 17 KB
- references/OPERATOR-LIBRARY.md 22 KB
- references/ORCHESTRATION.md 18 KB
- references/PHASES.md 25 KB
- references/PROJECT-TYPES.md 14 KB
- references/QUALITY-METRICS.md 9.2 KB
- references/SHOWCASE-GALLERY.md 14 KB
- references/SKILL-INSTALLATION.md 11 KB
- references/TEAM-WORKFLOWS.md 14 KB
- references/TESTING-DOCS.md 15 KB
- references/TROUBLESHOOTING.md 12 KB
- references/WRITING-CRAFT.md 16 KB
- scripts/a11y-check.sh 1.5 KB runs code
- scripts/audit-content.mjs 10 KB runs code
- scripts/check-skills.sh 3.6 KB runs code
- scripts/content-lint.mjs 4.0 KB runs code
- scripts/corpus-export.mjs 3.6 KB runs code
- scripts/docs-freshness.mjs 3.5 KB runs code
- scripts/generate-meta.mjs 4.2 KB runs code
- scripts/install-referenced-skills.sh 2.9 KB runs code
- scripts/link-check.mjs 4.9 KB runs code
- scripts/scaffold-nextra.sh 6.7 KB runs code
- scripts/seo-check.sh 2.3 KB runs code
- scripts/triangulate.sh 1.7 KB runs code
- SELF-TEST.md 2.8 KB
- subagents/a11y-auditor.md 3.0 KB
- subagents/api-reference-writer.md 2.7 KB
- subagents/changelog-writer.md 2.8 KB
- subagents/fresh-eyes.md 1.8 KB
- subagents/freshness-scanner.md 2.2 KB
- subagents/migration-agent.md 3.1 KB
- subagents/orchestrator.md 2.2 KB
- subagents/performance-auditor.md 3.4 KB
- subagents/polisher.md 1.6 KB
- subagents/section-writer.md 2.2 KB
- subagents/security-reviewer.md 3.7 KB
- subagents/synthesizer.md 1.5 KB
- subagents/triangulator.md 2.8 KB
- subagents/tutorial-writer.md 3.6 KB
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.
- 6d ago First seen · 377 lines · 46 tokens per session scan C 6f73f6188b10
documentation-website-for-software-project is a skill published in the GitHub repository hachej/boring-ui (46 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 5,517 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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-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…