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.
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 skills/ufomiao/zcf/featnpx skills add UfoMiao/zcf --skill featgit 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/skills/ufomiao/zcf/feat)<a href="https://agentmods.dev/skills/ufomiao/zcf/feat"><img src="https://agentmods.dev/badge/skills/ufomiao/zcf/feat.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 | $0.00005 | $0.00611 |
| Opus 5 | $0.00003 | $0.00305 |
| Sonnet 5 | $0.00001 | $0.00122 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
feat 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ARGUMENTS
Core Workflow
1. Input Analysis and Type Determination
When receiving user input, first perform type determination and clearly inform the user:
Determination Criteria:
-
Requirement Planning Type: User proposes new feature requirements, project ideas, or needs to formulate plans
-
Discussion Iteration Type: User requests to continue discussion, modify, or refine existing planning
-
Execution Implementation Type: User confirms planning is complete and requests to start specific implementation work
2. Classification Processing Mechanism
A. Requirement Planning Processing
Trigger Condition: Identified as functional requirement input
Execution Actions:
-
Enable Planner Agent
-
Generate detailed markdown planning document
-
Store document in
./.claude/plandirectory, named in plan/xxx.md format -
Include: objective definition, feature breakdown, implementation steps, acceptance criteria
B. Discussion Iteration Processing
Trigger Condition: User requests to continue discussion or modify planning
Execution Actions:
-
Retrieve and analyze previously generated planning files
-
Identify user feedback and confirmation content
-
Enable Planner Agent
-
Generate detailed markdown planning document
-
Create a new document, for example, if the last one was plan/xxx.md, then this time it's plan/xxx-1.md, if the last one was plan/xxx-1.md, then this time it's plan/xxx-2.md, and so on
-
Reorganize pending implementation task priorities
C. Execution Implementation Processing
Trigger Condition: User confirms planning is complete and requests to start execution
Execution Actions:
-
Start task execution in the order of planning documents
-
Perform task type identification before each subtask begins
-
Frontend Task Special Processing:
-
Check if available UI design exists
-
If no design solution exists, must use UI-UX-Designer Agent
-
Complete UI design before proceeding with development implementation
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 · 108 lines · 5 tokens per session scan A 9677c96e9527
feat is a skill published in the GitHub repository UfoMiao/zcf (6,085 stars, last pushed 4d ago), licensed MIT. It adds 5 tokens to every session and 611 once invoked, about $0.0000 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 skills, from other repositories
r3f-animation
React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
golden-rss
Use when testing the rss golden build.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.