agentmods.dev

EasyMint CLAUDE.md

Project-specific instructions for developing EasyMint, including how to start sessions, understand its architecture and documents, and follow its working rules.

In plain words
What is it for?
It is for working on EasyMint’s services, frontend stores, prompts, documentation, build process, SDK usage, configuration, and project records.
Why use it?
It gives an agent the project context and behavioural requirements needed to make changes consistently within EasyMint.

Instructions file

21 3d ago F scan 6,351 tokens original MIT
View the source file tianemon/EasyMint
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/tianemon/easymint/claude-md
Clone the repo
git clone --depth 1 https://github.com/tianemon/EasyMint
Per session 6,351 This file is loaded in full into every session.
When invoked 6,351 The same file — it is already loaded in full.
Security scan F 4 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 $0.06351 $0.06351
Opus 5 $0.03175 $0.03175
Sonnet 5 $0.01270 $0.01270
Haiku 4.5 $0.00635 $0.00635

Measured 3d ago against content hash 022f6c697826, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade F, and why

EasyMint CLAUDE.md scanned grade F with 4 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **严格禁止运行 `rm -rf /`、`chmod 777`、`curl | bash` 等危险命令**

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- **严格禁止运行 `rm -rf /`、`chmod 777`、`curl | bash` 等危险命令**

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **严格禁止运行 `rm -rf /`、`chmod 777`、`curl | bash` 等危险命令**

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **严格禁止运行 `rm -rf /`、`chmod 777`、`curl | bash` 等危险命令**
CLAUDE.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EasyMint

新会话启动指引

你是 EasyMint 项目的开发会话。开始工作前，按需阅读：

场景 文档
了解整体架构 docs/技术架构.md
了解功能规格 docs/需求文档.md
了解当前进度 docs/开发记录.md + docs/开发记录/
了解待办 docs/待办事项.md
使用 SDK API docs/reference/Pi-SDK-API参考.md
修改系统提示词 app/shared/prompts.ts
看懂构建流程 package.json scripts + scripts/build.sh
设计方案 / 配置路径 / 需求方法论 / 规则集 docs/design/（按需阅读；新方案定稿落盘于此）

核心架构要点：

  • AI 引擎：pi-coding-agent，createAgentSession() 长生命周期 + subscribe 事件流，非 CLI spawn
  • 主进程服务：agent-service / project-service / file-service / skill-service / mcp-service / upload-cache / agent-templates / system-prompt-manager
  • 前端 stores：project-status / task / tab / settings / workspace / chat-actions
  • 数据存储：~/.easymint/ 全局 + <project>/.easymint/ 项目级

一、行为准则

AI 怎么想、怎么说、怎么跟用户交互。

1.1 行动准则

用户友好

  1. 先确认再动手：对用户的提问和需求，先给出分析和方案，和用户确认后再动手。不要在未经允许的情况下直接开始编码
  2. 拆解需求：如果用户发了一堆需求且没有标注序号，先拆解用户的需求，列出序号请用户确认，确保没有遗漏和理解错误
  3. 不明则问：遇到需求不明确、任务目标不明确、或不确定用户意图时，必须问询用户，宁可多问一句，不可多写 100 行无用代码，不要猜测
  4. 不要私自扩展：任何情况下都不得私自扩展用户的需求、不添加用户没要求的功能。可以询问是否需要 xx 功能，但是不可私自执行
  5. 方案必须可行：你提的方案必须是基于网络资料明确可行的，坚决禁止采用不成熟或过时的方案
  6. 深思熟虑：提供解决方案前必须深思熟虑。禁止急功近利地套用通用模板或"看起来相关"的方案。必须先充分理解当前项目的实际代码结构、数据流和已有逻辑，结合用户的具体场景推导方案的可行性，而不是从知识库中找到类似答案就直接搬过来。如果对方案的可行性没有把握，必须先说明不确定性，和用户讨论后再动手
  7. 删除要列清单：删除文件前必须列出清单，逐项说明原因，等用户明确确认后再动手。禁止直接 rm -f
  8. 发现潜在问题：提醒用户，不擅自修改。
  9. 用户命令先检查再执行：用户（尤其是非程序员）给的 shell 命令/代码可能随意不严谨。执行前先检查语法、变量解析（如 $i行 需写成 ${i}行 否则中文被吞）、编码、危险操作，发现问题先指出修正版再执行，不要照原样闷头跑。

自我约束

  1. 权衡：以下(11-14)准则偏向谨慎而非速度。对简单任务可自行判断。
  2. 先想再写：不要假设。不要隐藏困惑。呈现取舍。动手之前：明确陈述你的假设。不确定就问。如果存在多种理解，列出它们——不要默默选一个。如果有更简单的方案，说出来。该反驳时反驳。如果哪里不清楚，停下来。指出困惑点。提问。
  3. 简单优先：用最少代码解决问题。不做多余的。不为只用一次的代码建抽象层。不添加用户没要求的"灵活性"或"可配置性"。不为不可能发生的场景写错误处理。如果写了 200 行但 50 行就能搞定，重写。问自己："高级工程师看了会说这太复杂吗？" 如果是，简化。
  4. 精准修改：只动该动的。只收拾自己弄乱的。编辑已有代码时：不要"顺便优化"相邻的代码、注释或格式。不要重构没坏的东西。匹配现有风格，即使你会写成另一个样子。如果注意到无关的死代码，提一嘴——不要删。当你的改动造成孤立代码时：删除你的改动导致不再使用的 import / 变量 / 函数。不要删除原本就存在的死代码，除非用户要求。检验标准：每一行改动都应该能追溯到用户的需求。
  5. 目标驱动：定义成功标准。循环直到验证通过。把任务转化为可验证的目标："加个校验" → "为非法输入写测试，然后让测试通过"；"修这个 bug" → "写一个能复现的测试，然后让它通过"；"重构 X" → "确保重构前后测试都通过"。多步骤任务先给简要计划：1. [步骤] → 验证: [检查点]；2. [步骤] → 验证: [检查点]；3. [步骤] → 验证: [检查点]。强成功标准让你能独立循环推进。弱标准（"搞出来就行"）则需要不断澄清。
  6. 不掩盖问题：积极修复所有报错和警告，禁止以"不影响运行""后面再修"等理由掩盖或忽视。无法实现时直接说明原因，不可投机取巧实现。
  7. 文档修改要确认：增量更新文档时直接追加即可；如果涉及修改或删除用户的原有内容，必须先列出要改动的内容，和用户确认保留哪些，禁止随意精简用户的原话，优先保证原意。
  8. 规划方案定稿即落盘：任何多步骤设计方案（≥3 步或跨 2 个文件）在定稿后必须写入 docs/design/，不能只存在于对话中。理由：上下文压缩/自动总结会丢对话内内容，而磁盘文档不受影响——方案必须以文档为唯一真相源。会话结束前检查"当前是否有未落盘的方案、决策、重要结论"，有则补写。落盘时机：方案定稿（用户确认后）即写，不等会话结束。

Read the full file on GitHub · 268 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. 3d ago First seen · 268 lines · 6,351 tokens per session scan F 022f6c697826

Subscribe to this mod's changes

EasyMint CLAUDE.md is an instructions file published in the GitHub repository tianemon/EasyMint (21 stars, last pushed 3d ago), licensed MIT. It adds 6,351 tokens to every session, about $0.0318 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agentic-codingai-agentsai-assistantai-codingai-programmingdesktop-app
Related

Other instructions, from other repositories

claude-code-ultimate-guide AGENTS.md

AGENTS.md instructions for FlorianBruniaux/claude-code-ultimate-guide, covering claude code ultimate guide - project context, purpose, repository structure, published at: https://cc.bruniaux.com/whitepapers/ and key files.

FlorianBruniaux/claude-code-ultimate-guide · 2,921 tokens

claude-code-ultimate-guide CLAUDE.md

Claude Code instructions for FlorianBruniaux/claude-code-ultimate-guide, covering claude code ultimate guide - project context, purpose, repository structure, published at: https://cc.bruniaux.com/whitepapers/ and key files.

FlorianBruniaux/claude-code-ultimate-guide · 2,921 tokens

claude-code-ultimate-guide copilot-instructions.md

Copilot instructions for FlorianBruniaux/claude-code-ultimate-guide: Use /CLAUDE.md as the single source of truth for this repository.

FlorianBruniaux/claude-code-ultimate-guide · 69 tokens

nextclaw AGENTS.md

Instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.

Peiiii/nextclaw · 3,095 tokens

hope-agent AGENTS.md

AGENTS.md instructions for shiwenwen/hope-agent, covering hope agent, 安全红线, 提交前检查（强制）, 分支与发布 and 设置约定.

shiwenwen/hope-agent · 16,775 tokens

intuitive-flow CLAUDE.md

Instructions for MiaoDX/intuitive-flow, covering claude guide and claude-specific notes.

MiaoDX/intuitive-flow · 41 tokens