ZCF is a command-line setup tool for configuring Claude Code and Codex with agents, instructions, skills, hooks, commands, and settings. It is for developers who want to install and personalize these coding-agent workflows through an interactive setup.
Borrowing it
Nothing to install: this file belongs to UfoMiao/zcf. 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/UfoMiao/zcf/main/AGENTS.mdgit clone --depth 1 https://github.com/UfoMiao/zcfWrote 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/ufomiao/zcf/agents-md)<a href="https://agentmods.dev/instructions/ufomiao/zcf/agents-md"><img src="https://agentmods.dev/badge/instructions/ufomiao/zcf/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.
<a href="https://agentmods.dev/instructions/ufomiao/zcf/agents-md"><img src="https://agentmods.dev/badge/instructions/ufomiao/zcf/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01905 | $0.01905 |
| Opus 5.5 | $0.00762 | $0.00762 |
| Sonnet 5.5 | $0.00381 | $0.00381 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
zcf 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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Working guide for AI agents and people changing this repository. Claude Code loads it through CLAUDE.md; Codex and other agents read it directly. Read the sections your task needs, then use the trigger table to find what else applies.
What ZCF is
ZCF v5 is a ground-up rewrite (v3 is frozen at the [email protected] tag; there was no v4). The user keeps one ZCF config, picks AI coding tools, and ZCF installs the tools that are missing and writes each tool's own native config. It configures the tools; it is not a gateway or proxy.
Priorities, in order: speed (startup and apply), development speed, and user experience. No backward compatibility with v3 config or commands.
Prefer each tool's own commands and mainstream CLIs over reimplementing them: claude update, claude mcp add-json, npx skills add, and so on. Edit config files only for settings no command covers.
Layout
| Path | What lives there |
|---|---|
packages/core (@zcf/core, private) |
Headless engine: schema/ (valibot config schema), adapters/ (one per tool), plan/ (plan types, diff preview, apply), io/ (format-preserving JSON/TOML edits, atomic writes, backups), exec/ (command runner) |
packages/ui-kit (@zcf/ui-kit, private) |
Shared by the terminal and web UIs, no rendering: draft model and validation, page and field definitions, useConfigEditor, the ZcfService interface |
packages/cli (zcf, private until v5 ships) |
cli.ts (entry with the fast --version path), main.ts (cac commands), render.ts (terminal output, secret masking), i18n.ts (en and zh-CN strings), service.ts (ZcfService backed by core), tui/ (Ink app, loaded lazily) |
packages/*/test |
Vitest suites for that package |
presets/providers.json |
Provider presets, fetched at runtime so they change without a release; validated by packages/core/test/presets.test.ts |
scripts/bench-startup.mjs |
Startup benchmark that CI enforces |
docs/ |
VitePress site. Pages are docs/{en,zh-CN,ja-JP}/ (home page and guide/); v3's docs live at the [email protected] tag. Deployed by hand (docs-deploy.yml) |
docs/adr/ |
Architecture decisions; read 002-v5-architecture.md before changing the engine |
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.
- 2d ago Changed · +60 lines · +1,272 tokens per session 8ec9c04d08ad
- 1mo ago First seen · 25 lines · 633 tokens per session scan A 8e95d6955969
zcf AGENTS.md is an instructions file published in the GitHub repository UfoMiao/zcf (6,079 stars, last pushed yesterday), licensed MIT. It adds 1,905 tokens to every session, about $0.0076 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.