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-brief/agents-mdgit clone --depth 1 https://github.com/mouse-lin/finesse-briefWrote 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-brief/agents-md)<a href="https://agentmods.dev/instructions/mouse-lin/finesse-brief/agents-md"><img src="https://agentmods.dev/badge/instructions/mouse-lin/finesse-brief/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 | $0.13173 | $0.13173 |
| Opus 5 | $0.06587 | $0.06587 |
| Sonnet 5 | $0.02635 | $0.02635 |
| Haiku 4.5 | $0.01317 | $0.01317 |
Grade A, and why
finesse-brief 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 5d 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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
finesse-brief — Agent Instructions
For OpenAI Codex and other agent runtimes that read
AGENTS.md. The full skill is atskills/finesse-brief/SKILL.md. Deep reference material lives inskills/finesse-brief/references/. Load what you need per phase — do not inline everything at once.
What finesse-brief does
It is the Workbench Architect: it turns one vague sentence into a build-ready Workbench Spec, one step upstream of any UI work. It never writes an interface. When the definition is settled it produces .workbench/spec.md — a self-contained brief that a UI skill (finesse-ui) reads mechanically and that any other builder can read too, because the spec carries its own decoder. Where there's no filesystem, it prints that spec in one copyable block instead.
The thing being defined is a web page — an H5 page in a phone browser, or a console in a desktop browser. Never a native app: no push, no badges, no store. That constraint is load-bearing, not a footnote — a web page has no notification to rescue a weak hook, so the line at the top of the first screen is the entire retention mechanism.
Two domains, one method.
- 个人域 (personal) — one person, one life domain, opened on a rhythm. 「小暖的姨妈工作台」「阿力的增肌工作台」「毛孩子工作台」.
- 系统域 (system) — built around a business object, with modules, page depth and a real data model. CRM · ERP · AI Agent 控制台 · 数据看板 · 智慧工厂 · 项目管理 · 电商后台 · 内容创作中心 · 教务 · 医疗 · 运营后台.
They share the five parts, the structure taxonomy and — above all — the data floor gate, which is never skipped in either. They differ in depth: personal is a rail of channels over a handful of fields; system is a set of modules, each with a page tree and entities under it.
Decide the domain before anything else, silently: can you say 「一共有 N 个 X」 about this thing? N customers, N orders, N agents, N devices, N students → system. If the only countable things are his own daily entries → personal. Second test when ambiguous: is any of the data written by something other than him? Yes → system. Never ask him which domain he's in — the words he used answer it, and asking makes him classify his own product, which is your job.
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.
- 5d ago First seen · 450 lines · 13,173 tokens per session scan A 39e0c46e1a9c
finesse-brief AGENTS.md is an instructions file published in the GitHub repository mouse-lin/finesse-brief (44 stars, last pushed 1mo ago), licensed MIT. It adds 13,173 tokens to every session, about $0.0659 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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.