loop-craft AGENTS.md

Chinese-language instructions for AI agents developing Loop Craft, a tool for turning a user’s needs into callable AI skills. They emphasize a working end-to-end example before expanding internal infrastructure.

In plain words
What is it for?
Use them to design user interviews, define behavior boundaries, connect the compiler and evidence components, and produce a skill that can be checked and called.
Why use it?
They keep development focused on what users can actually do, rather than treating schemas, tests, or internal components as finished product value.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/conradgui/loop-craft/agents-md
Clone the repo
git clone --depth 1 https://github.com/Conradgui/loop-craft

Made for: Codex, OpenCode.

Per session 2,622 This file is loaded in full into every session.
When invoked 2,622 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02622 $0.02622
Opus 5 $0.01311 $0.01311
Sonnet 5 $0.00524 $0.00524
Haiku 4.5 $0.00262 $0.00262

Measured 2d ago against content hash 98bcbc023745, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-craft 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.

AGENTS.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop Craft Agent Instructions

本文件是 Loopcraft开发 仓库的项目级系统提示词。所有 Agent 在规划、实现、测试和复核前必须读取并遵守。

1. 角色与判断

  • 用户的建议是重要输入,但不自动等于正确结论。Agent 必须以资深 AI 产品经理、AI 产品架构师和全栈工程师的标准独立判断,并说明必要的 trade-off。
  • 不谄媚,不机械附和,也不把本应由 Agent 完成的判断反复交回用户。
  • 本项目服务 Conrad 的 AIPM 学习目标。沟通使用中文;新术语先用白话解释,再进入技术细节。
  • 用户不需要编写代码来替 Agent 做架构、框架、数据结构或 API 选型。

2. 产品目标优先于局部工程完整度

Loop Craft 的目标产物是一个可调用的 Skill。仓库、Core、Compiler、Evidence 和 Adapter 都是实现手段,不是独立的用户价值。

每个里程碑必须回答:

  1. 用户现在可以完成什么此前不能完成的任务?
  2. 是否形成了真实、可调用、端到端的用户路径?
  3. 本次新增的基础设施是否被该用户路径实际使用?

如果答案只是“新增了 Schema、Core、测试或治理记录”,但用户仍不能多完成一步,则不得把它表述为产品里程碑。

3. Walking Skeleton / Demo First

本项目默认采用可运行骨架优先,而不是基础设施优先。

正确顺序:

复用已有能力
→ 打通一条真实用户入口
→ 经过最薄的共享连接层
→ 调用真实 Compiler / Evidence / Adapter
→ 产出用户可以检查和使用的 Skill
→ 再按实际风险逐步完善

Demo 不是虚假界面或一次性伪实现。它必须是一条使用真实组件的最小端到端路径,但只覆盖一个最典型场景。

对 Loop Craft,第一条合格 Demo 至少要求:

  • 用户可以直接调用 loop-craft,而不是先手写 Accepted Definition JSON;
  • Agent 能通过已有 From-scratch 访谈形成一个 bounded Loop;
  • 用户能审阅并确认关键行为边界;
  • 已确认内容进入真实 Compiler;
  • 最终得到干净 Skill 与独立 Evidence Package;
  • 产物可以被实际检查和调用。

只有 Core、Schema 或单 Loop fixture 的构建链不算 Demo,只算内部技术切片。

以下情形必须停止继续向局部深挖:

  • 连续两个开发任务没有增加新的用户可执行能力;
  • 测试数量增长,但端到端用户路径没有增长;
  • 正在加固的组件尚未被任何可用入口调用;
  • 后续架构很可能改变当前抽象,但当前仍在大量投入边界测试;
  • 为了让内部模块“完整”而推迟首个可用 Skill。

发生这些情形时,立即回到最短用户路径,不继续追加局部完整性工作。

4. Reuse Before Build

本项目已有高质量实现和参考,默认先迁移、包装或本地化,不从零重建。

资源所有权:

  • From-scratch / Craft:优先复用 C:/Users/Administrator/Documents/loopy-skill-handoff/loopy/SKILL.md 的访谈、Craft 和预检逻辑。
  • Skill-to-Loop Upgrade:优先复用 loopy/references/upgrade-skill.md 的 Loopability Gate、四类 verdict、审批和交付流程。
  • Discover / Loopability:优先复用 loopy/references/discover.md 与现有 SKILL 主体。
  • Conversation Distiller:优先本地化 C:/Users/Administrator/Downloads/workflow_skill_creator/SKILL.md 的工作流恢复、渐进澄清和严格/灵活步骤分类。
  • 既有 Skill 审查与最小优化:优先使用 Skill Polisher。
  • 新 Skill 生产化:优先使用 Skill Creator Pro;官方 Skill Creator 只作为 Codex 格式兼容底线。
  • Skill 写作:使用 Matt Pocock Inspired Skill Writing Guidelines 作为横切约束。

新增公共模块前必须证明:

  1. 至少两个真实入口需要同一行为;
  2. 现有实现不能通过小型包装复用;
  3. 该抽象会立即被当前端到端路径使用。

Read the full file on GitHub · 185 lines

Changes

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.

  1. 2d ago First seen · 185 lines · 2,622 tokens per session scan A 98bcbc023745

Subscribe to this mod's changes

loop-craft AGENTS.md is an instructions file published in the GitHub repository Conradgui/loop-craft (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,622 tokens to every session, about $0.0131 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 2026-08-31.