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 instructions/mouse-lin/finesse-skill/agents-mdgit clone --depth 1 https://github.com/mouse-lin/finesse-skillWrote 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/instructions/mouse-lin/finesse-skill/agents-md)<a href="https://agentmods.dev/instructions/mouse-lin/finesse-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/mouse-lin/finesse-skill/agents-md.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 | $0.03332 | $0.03332 |
| Opus 5 | $0.01666 | $0.01666 |
| Sonnet 5 | $0.00666 | $0.00666 |
| Haiku 4.5 | $0.00333 | $0.00333 |
Grade A, and why
finesse-skill AGENTS.md 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 4d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
finesse — Agent Instructions
For OpenAI Codex and other agent runtimes that read
AGENTS.md. The full skill is atskills/finesse-ui/SKILL.md. Deep reference material lives inskills/finesse-ui/references/. Load what you need per phase — do not inline everything at once.
What finesse does
finesse builds interfaces routed by register:
- brand — landing pages, brand sites, launches, portfolios, hero pages. Design IS the product. Optimize for spectacle + soul + first impression. Uses a real visual engine (Three.js / Canvas / GLSL / GSAP).
- product — dashboards, admin panels, analytics, data tables, app shells, settings. Design SERVES the product. Optimize for clarity + density + usability.
- commerce — PDP, PLP, cart, checkout. A hybrid: route to brand or product by what the specific page is doing.
- h5 — pages that only ever live on a phone: H5 / 移动端页面 / 活动页 / mini-program screens / app prototypes / mobile PDPs. A container register — it fixes the phone frame, safe areas, thumb zone and native furniture, then wraps one of the three above for content. A mobile PDP is
h5+commerce.
All share the same premium substrate and anti-slop blacklist. None is allowed to look cheap.
Commands (targeted iteration)
A full build runs the whole workflow below. For iterating on an existing page, route the request through one verb instead of rebuilding — Codex has no slash commands, so map the user's intent to the verb and load only that reference.
| Verb | Intent it matches | Load |
|---|---|---|
craft |
"build me a landing page / dashboard" (default) | full workflow |
init |
"set up finesse / new project" → write PRODUCT.md brief |
references/init.md |
document |
"capture / document the design system" → extract design-model.yaml |
references/document.md |
audit |
"is this any good?", "review it" — read-only, never edits | references/audit.md (runs scripts/detect.mjs) |
bolder |
"too plain / boring" → SPECTACLE +2, engine up a tier | references/hero-engines.md |
quieter |
"too flashy / janky" → SPECTACLE −2, engine down a tier | references/hero-engines.md |
soul |
"wrong vibe for this page" → re-compose the soul, re-lock color | references/style-personas.md |
diverge |
"every page looks the same / feels generic / 每次都差不多" → systemic anti-sameness: recompose from 5 orthogonal axes, two-altitude anti-default, break the argmax, check the used-list | references/divergence.md |
animate |
"make it move / different animation" → add/swap engine only | references/hero-engines.md |
depth |
"add depth / make it 3D / tilt / parallax" → add one 3D moment (CSS pseudo-3D, or Three.js for a real object) | references/3d-effects.md |
densify |
"too sparse / too dense" → DENSITY ± | references/product-ui.md |
redesign |
"improve / fix this page" → audit-first, never full-rebuild | references/redesign-mode.md |
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.
- 4d ago First seen · 157 lines · 3,332 tokens per session scan A 59b5fad741dc
finesse-skill AGENTS.md is an instructions file published in the GitHub repository mouse-lin/finesse-skill (532 stars, last pushed 1mo ago), licensed MIT. It adds 3,332 tokens to every session, about $0.0167 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.