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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/mouse-lin/finesse-brief/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mouse-lin/finesse-brief/copilot-instructions.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 | $0.06505 | $0.06505 |
| Opus 5 | $0.03252 | $0.03252 |
| Sonnet 5 | $0.01301 | $0.01301 |
| Haiku 4.5 | $0.00651 | $0.00651 |
Grade A, and why
finesse-brief copilot-instructions.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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions: finesse-brief
GitHub Copilot reads this file automatically. These rules apply when defining a workbench — a web page someone returns to on a rhythm. Two kinds: personal (one person, one life domain — 「小暖的姨妈工作台」「毛孩子工作台」「摆摊工作台」) and system (built around a business object, with modules, page depth and a data model — CRM · ERP · AI Agent 控制台 · 数据看板 · 智慧工厂 · 电商后台 · 教务 · 医疗). They govern the definition, not the interface.
Core Directive
Decide what the thing is before anything renders. The output is .workbench/spec.md, not a page — a self-contained brief finesse-ui reads mechanically and any other builder can read too, because the spec carries its own decoder (see the closing section). If the user needs the interface built, finish the spec first and hand it over.
What gets built is a web page — H5 in a phone browser or a console in a desktop one. Never a native app: no push, no badges. That's load-bearing — nothing rescues a weak hook, so the line at the top of the first screen is the entire retention mechanism.
Decide the domain first, silently, and never ask him: can you say 「一共有 N 个 X」 about this thing? N customers / orders / agents / devices / students → system. Only his own entries → personal. Ambiguous → is any data written by something other than him? Yes → system. Borderline resolves toward system when there's a page tree: 「个人知识库」 is system (registry) despite one user; 「摆摊工作台」 is personal despite being a business. Count the objects and the levels, not the users.
Two failures own this category and they are not symmetric. The visible one is never starting — he wants a workbench and can't name one. The expensive one is building the wrong one beautifully: a page whose hook reads 今天是黄体期第 3 天 forever because nobody asked where the 3 comes from, or an admin console whose twelve tables render empty the day it meets a real database. Everything below exists to kill the second.
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 · 72 lines · 6,505 tokens per session scan A bc6e82a053eb
finesse-brief copilot-instructions.md is an instructions file published in the GitHub repository mouse-lin/finesse-brief (44 stars, last pushed 1mo ago), licensed MIT. It adds 6,505 tokens to every session, about $0.0325 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-stable apis and released session data, repository layout, commands and host sandbox failures.