finesse-brief: Instructions file for Codex

AGENTS.md

finesse-brief AGENTS.md is an instructions file for Codex, OpenCode from mouse-lin/finesse-brief. It costs 13,173 tokens per session, scanned A, original, MIT.

An instruction file for a planning tool that turns a vague idea into a written specification for a web page, rather than building the interface itself.

In plain words
What is it for?
Creating a self-contained workbench specification for a mobile or desktop web page that another builder can follow.
Why use it?
It helps settle the page’s purpose, audience, and constraints before UI work begins.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: names the AskUserQuestion tool; mentions AGENTS.md; mentions Codex.

This is mouse-lin/finesse-brief's own configuration. It tells Codex and OpenCode how to work on finesse-brief itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything finesse-brief configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mouse-lin/finesse-brief. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mouse-lin/finesse-brief/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mouse-lin/finesse-brief

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for finesse-brief AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mouse-lin/finesse-brief/agents-md/github.svg)](https://agentmods.dev/instructions/mouse-lin/finesse-brief/agents-md)
Your own site
<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/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for finesse-brief AGENTS.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 13,173 This file is loaded in full into every session.
When invoked 13,173 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.13173 $0.13173
Opus 5.5 $0.05269 $0.05269
Sonnet 5.5 $0.02635 $0.02635
Haiku 4.5 $0.01317 $0.01317

Measured 2mo ago against content hash 39e0c46e1a9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

AGENTS.md · 450 lines

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 at skills/finesse-brief/SKILL.md. Deep reference material lives in skills/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.

Read the full file on GitHub · 450 lines

Changes

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.

  1. 2mo ago First seen · 450 lines · 13,173 tokens per session scan A 39e0c46e1a9c

Subscribe to this mod's changes

finesse-brief AGENTS.md is an instructions file published in the GitHub repository mouse-lin/finesse-brief (124 stars, last pushed 3mo ago), licensed MIT. It adds 13,173 tokens to every session, about $0.0527 per session on Opus 5.5. 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.

Related

finesse-brief AGENTS.md compared with instructions from other repositories

finesse-brief AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
finesse-brief AGENTS.mdmouse-lin/finesse-briefInstructions file1243mo agoMITA13,173Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode