Borrowing it
Nothing to install: this file belongs to zvzuola/acp-components. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zvzuola/acp-components/main/CLAUDE.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/claude-md)<a href="https://agentmods.dev/instructions/zvzuola/acp-components/claude-md"><img src="https://agentmods.dev/badge/instructions/zvzuola/acp-components/claude-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 5.1 | $0.02789 | $0.02789 |
| Opus 5 | $0.01394 | $0.01394 |
| Sonnet 5 | $0.00558 | $0.00558 |
| Haiku 4.5 | $0.00279 | $0.00279 |
Grade A, and why
acp-components CLAUDE.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 7d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & Development
pnpm install # Install all deps
pnpm build # Build both packages (core → react)
pnpm build:core # Build only @acp-components/core
pnpm build:react # Build only @acp-components/react
pnpm lint # Lint all TypeScript in packages/*/src
Web Demo
pnpm dev:server # Terminal 1 — WebSocket ↔ stdio bridge
pnpm dev # Terminal 2 — Vite dev server at localhost:5173
pnpm dev:tauri # Tauri desktop dev (stdio transport)
pnpm build:tauri # Tauri production build
Running a single test
pnpm --filter @acp-components/core test -- -t "test name pattern"
pnpm --filter @acp-components/react test -- -t "test name pattern"
Bridge server env vars
| Variable | Default | Description |
|---|---|---|
ACP_PORT |
3100 |
WebSocket port |
ACP_HOST |
127.0.0.1 |
WebSocket host |
ACP_AGENT |
opencode |
Agent binary |
ACP_AGENT_ARGS |
acp |
Agent arguments |
Architecture
Package Layering
Application Layer (Vite Demo / Tauri / Custom Apps)
└─ @acp-components/react (UI Layer)
Components (15+) + Hooks (useSyncExternalStore) + AcpContext + PlatformContext + Theme + i18n
depends on ↓
@acp-components/core (Data Layer)
createAcpProvider (multi-agent lifecycle) + AcpClient (per-agent, wraps ACP SDK)
+ Transport (Stdio/WebSocket/HTTP/Custom) + acpStore + sessionStore + fileTreeStore (vanilla Zustand)
+ Actions (sessions/prompt/permission/fileTree/extensions, agent-aware)
built on ↓
@agentclientprotocol/sdk (ACP protocol types + ClientSideConnection)
Platform Layer (orthogonal to the above): a `Platform` interface (defined in `@acp-components/react`) + `PlatformContext`/`usePlatform()` provide host-native capabilities to the UI. The interface is **sharded** into cohesive slices — `fs?` (readDirectory/readFileContent/writeFileContent?/watchFileTree?), `dialogs?` (openLink/openFilePicker/notify), `storage` (always required), `openExternalEditor?` (host takes over file opening, bypassing built-in FileViewer), `updater?`, `system?` (restart?/exportLogs?) — capability is expressed by slice / method presence; callers guard with `?.` at the use site. Each host (web demo, Tauri template) implements its own `Platform` (`createWebPlatform` / `createTauriPlatform`). Workspace load/save is NOT on `Platform` — it lives in the `useWorkspacesPersistence` hook, backed by `storage('workspaces')`. core does NOT implement `Platform` — it only owns the shared primitive types (`PlatformKind`, `PlatformStorage`, `UpdaterState`, …).
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.
- 7d ago First seen · 160 lines · 2,789 tokens per session scan A 9e9ace28ec92
acp-components CLAUDE.md is an instructions file published in the GitHub repository zvzuola/acp-components (49 stars, last pushed 1mo ago), licensed MIT. It adds 2,789 tokens to every session, about $0.0139 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
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 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.