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/zvzuola/acp-components/agents-mdgit clone --depth 1 https://github.com/zvzuola/acp-componentsWrote 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/zvzuola/acp-components/agents-md)<a href="https://agentmods.dev/instructions/zvzuola/acp-components/agents-md"><img src="https://agentmods.dev/badge/instructions/zvzuola/acp-components/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 | $0.00760 | $0.00760 |
| Opus 5 | $0.00380 | $0.00380 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
acp-components 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
A pnpm monorepo for Agent Client Protocol (ACP) React components and a framework-agnostic core.
Project Structure & Module Organization
packages/core(@acp-components/core): provider,AcpClient, vanilla Zustand stores (acpStore,sessionStore,fileTreeStore), transports (Stdio/Http/WebSocket/custom), actions, and shared types. Zero React dependency.packages/react(@acp-components/react): UI layer withcomponents/(each component in its own subdirectory),context/(AcpContext,PlatformContext),hooks/,i18n/, andstyles/.examples/:demo(Vite web app),server(WebSocket-to-stdio bridge),tauri(desktop shell).assets/,design-system/,docs/: shared resources and documentation.
Tests are co-located next to source as *.test.ts or *.test.tsx.
Build, Test, and Development Commands
pnpm install # install all workspace deps
pnpm build # build core, then react
pnpm build:core # build @acp-components/core only
pnpm build:react # build @acp-components/react only
pnpm test # run vitest across both packages
pnpm lint # eslint packages/*/src/**/*.{ts,tsx}
pnpm dev # Vite demo at localhost:5173 (run pnpm dev:server first)
pnpm dev:server # WebSocket -> stdio bridge on ACP_PORT (default 3100)
pnpm dev:tauri # Tauri desktop dev
Run a single package or filter by test name:
pnpm --filter @acp-components/core test
pnpm --filter @acp-components/core test -- -t "pattern"
Each package also exposes test:watch for interactive vitest.
Coding Style & Naming Conventions
- TypeScript strict mode; ES2022 target, ESNext modules, bundler resolution.
- ESLint flat config (
eslint.config.js): typescript-eslint recommended plus react-hooks rules. - Prefix unused vars, args, and caught errors with
_. - Styles: SCSS Modules with
camelCaseOnlylocals; theme viadata-acp-theme("dark"default,"light"). - Use
--acp-*CSS custom properties and never hardcode hex colors. Avoid inline styles unless the value is dynamic. - React components live in
packages/react/src/components/<name>/, one per directory.
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 · 58 lines · 760 tokens per session scan A 24f4f0e2946a
acp-components AGENTS.md is an instructions file published in the GitHub repository zvzuola/acp-components (47 stars, last pushed 1mo ago), licensed MIT. It adds 760 tokens to every session, about $0.0038 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
intelligent-terminal agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
intelligent-terminal rust-localization.instructions.md
Instructions for microsoft/intelligent-terminal, covering localization instructions for rust wta (yaml locale files), file structure, file format, the en-us.yml source file and non-translatable token rules.
intelligent-terminal localization.instructions.md
Instructions for microsoft/intelligent-terminal, covering localization instructions for .resw resource files, components with localized resources, locale categories, authoritative locale list (from terminalapp) and adding or updating localized strings.
intelligent-terminal copilot-instructions.md
Copilot instructions for microsoft/intelligent-terminal, covering copilot instructions for windows terminal, build, running, test and code formatting.
intelligent-terminal instructions.instructions.md
Guidelines for creating high-quality custom instruction files for GitHub Copilot.
intelligent-terminal AGENTS.md
AGENTS.md instructions for microsoft/intelligent-terminal, covering intelligent terminal, architecture, supported agents and settings, user-facing behavior and key files.