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 instructions/fantasieleven-code/callout/claude-mdgit clone --depth 1 https://github.com/fantasieleven-code/calloutWrote 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/fantasieleven-code/callout/claude-md)<a href="https://agentmods.dev/instructions/fantasieleven-code/callout/claude-md"><img src="https://agentmods.dev/badge/instructions/fantasieleven-code/callout/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 | $0.02414 | $0.02414 |
| Opus 5 | $0.01207 | $0.01207 |
| Sonnet 5 | $0.00483 | $0.00483 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
callout 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 4d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Callout — AI Co-founder for 0→1 Builds
What is this
MCP Server，非技术创始人的AI副驾驶。通过多视角审查、阶段引导、产品质疑帮用户发现"不知道该问的问题"。所有发现汇入 todo list 统一管理。
Product Context
目标用户: 用AI代替工程团队的非技术创始人。用Cursor/Claude Code/Kimi Code让AI写代码，但没有CTO/产品经理帮他把关方向。
核心理念:
- 五视角帮用户发现盲区（包括专利/合规/部署这些从没想过的问题）
- 发现必须变成行动 → 所有工具输出汇入todo list
- 不需要主动调用 → CLAUDE.md/.cursorrules规则自动触发
- Callout不调LLM → 只组装prompt，让宿主执行，零API成本
Current Status
V0.5.1: 16 MCP tools, 142 tests, npm published
路线图: 见 TODO.md 和 docs/roadmap.md
技术架构: 见 docs/architecture.md
Quick Start
npm install # 安装依赖
npm run build # tsc → dist/
npm run test # vitest run (134 tests, 14 files)
npm run dev # tsc --watch
Project Structure
src/
├── server.ts # MCP Server入口 (~55行，bootstrap + instructions + 4 register calls)
├── util.ts # 共享工具函数 (resolvePath, withPathHeader)
├── handlers/ # 工具注册模块 (4个文件)
│ ├── analysis.ts # 4工具: review, test_translate, coach, idea_score
│ ├── todo.ts # 4工具: todo_add, todo_update, todo_list, todo_summary
│ ├── recommend.ts # 3工具: recommend, recommend_dismiss, recommend_reset
│ └── meta.ts # 5工具: init, callout_help, save_review_findings, set_target_user, portfolio
├── types.ts # ProjectContext, Perspective, PerspectiveGroup 类型定义
├── context.ts # 项目上下文收集器 (文件树/依赖/技术栈/统计)
├── review.ts # 9视角审查引擎 + Executive Summary (3组: technical/business/founder)
├── coach.ts # AI协作教练 (环境诊断/行为模式/知识盲区)
├── challenge.ts # 产品质疑 prompt builder (被 review focus 复用)
├── guide.ts # 阶段检测器 + 检查清单 (被 coach 复用)
├── todo.ts # Todo核心 (add/update/list/summary)
├── history.ts # 审查历史持久化 (.callout/history.json)
├── config.ts # 项目配置 + 目标用户自动检测
├── git.ts # Git自动收集 (diff/log)
├── portfolio.ts # 多项目扫描 + 汇总 prompt builder
├── recommend.ts # Dismissed场景追踪 (.callout/dismissed.json)
├── setup.ts # CLI: npx callout-dev setup
├── rules-template.ts # CLAUDE.md自动触发规则模板
└── prompts/ # 9个视角prompt模板 + 工具类prompt
├── cto.ts # 过度设计/技术债/扩展瓶颈/砍什么
├── security.ts # OWASP/认证/输入验证/数据隔离
├── product.ts # 用户旅程/缺失功能/定位清晰度
├── devops.ts # 部署/监控/备份/CI
├── customer.ts # 拒绝理由/体验缺口 (支持自定义角色)
├── strategy.ts # 资源分配/商业模式/竞争壁垒/GTM
├── investor.ts # 市场规模/团队匹配/收入模型/护城河/资本效率
├── unicorn-founder.ts # 速度优先/核心功能/规模思维/砍半测试
├── solo-entrepreneur.ts # 单人可行性/时间预算/运维负担/倦怠风险
├── idea-score.ts # 10维度量化评分 (challenge的怀疑论变体)
└── recommend.ts # 场景检测 + 工具推荐prompt builder
test/
├── server.test.ts # 21 tests (集成测试: 16工具注册 + instructions验证)
├── coach.test.ts # 14 tests
├── portfolio.test.ts # 12 tests
├── review.test.ts # 11 tests
├── idea-score.test.ts # 6 tests
├── challenge.test.ts # 7 tests (prompt builder测试，工具已合并入review)
├── guide.test.ts # 10 tests (prompt builder测试，阶段检测被coach复用)
├── todo.test.ts # 9 tests
├── history.test.ts # 6 tests
├── config.test.ts # 10 tests
├── recommend.test.ts # 13 tests
├── spot-check.test.ts # 6 tests (prompt builder测试)
├── cleanup.test.ts # 6 tests (prompt builder测试)
├── validate.test.ts # 6 tests (prompt builder测试)
└── test-translate.test.ts # 5 tests
docs/
├── roadmap.md # 产品路线图
└── architecture.md # 技术架构 + CI/CD + 测试策略
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.
- 4d ago First seen · 161 lines · 2,414 tokens per session scan A 011b123ba51c
callout CLAUDE.md is an instructions file published in the GitHub repository fantasieleven-code/callout (3 stars, last pushed 5mo ago), licensed MIT. It adds 2,414 tokens to every session, about $0.0121 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.
Other instructions, from other repositories
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
tmetric-minimal-mcp CLAUDE.md
Claude Code instructions for guglielmo/tmetric-minimal-mcp, covering claude.md, development commands, project architecture, file structure and core architecture patterns.
shelly-forge CLAUDE.md
Claude Code instructions for mslavov/shelly-forge, covering documentation usage guidelines, critical: framework-first reading order, 📚 mandatory reading order, pre-task protocol and post-task protocol.
vibelive AGENTS.md
AGENTS.md instructions for pooriaarab/vibelive, covering agents.md, repository context, pull requests, cloud agents (cursor) and install & test.
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).