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/monadworks/agentify/claude-mdgit clone --depth 1 https://github.com/MonadWorks/agentifyWhat 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 | $0.02108 | $0.02108 |
| Opus 5 | $0.01054 | $0.01054 |
| Sonnet 5 | $0.00422 | $0.00422 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
agentify 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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agentify CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentify - The Meta-Tool for Agent-Native Product Transformation
Project Vision
Agentify 是一个 Agent Interface Compiler——从一个 source of truth 编译出产品在 Agent 时代需要的所有接口格式（MCP Server, Skills, CLI, CLAUDE.md, .cursorrules, A2A Card 等）。
Tagline: "One command. Every agent speaks your product."
核心体验: npx agentify transform <openapi-url> → 完整的 Agent 接口套件
产品成熟度目标: 让任何 L1+ 产品一键升级到 L4（Agent-Native 全接口套件）
Project Status
- 项目初始化
- 调研阶段（4 份报告）→
research/ - 产品规划 v1 →
docs/product-plan.md - 七人专家评审 →
research/reviews/ - 计划修订 v1 →
research/reviews/SYNTHESIS.md - 愿景 v2 探索（2 份 UX 研究 + 7 份愿景探索）
- Vision v2 定稿 →
docs/vision-v2.md - Milestone 0: Foundation（第 1 周） ✅ 核心完成
- Milestone 1: Multi-Format MVP（第 2-3 周） ← 当前
- Milestone 2: Intelligence Layer（第 4-5 周）
- Milestone 3: Self-Serve & Ecosystem（第 6-8 周）
- Milestone 4: Scale & Enterprise（第 9-14 周）
Key Decisions
| Date | Decision | Rationale |
|---|---|---|
| 2026-03-02 | 项目启动，代号 Agentify | 产品核心是将传统产品 "Agent化" |
| 2026-03-02 | 定位：端到端 Agent 化转型平台 | 市场空白点，无竞品覆盖全链路 |
| 2026-03-02 | GTM：开源核心 + 付费增值 | 建立 developer mindshare |
| 2026-03-02 | [修订] 单包结构，砍掉 monorepo | 7 人评审一致认为 monorepo 过早 |
| 2026-03-02 | [修订] 扁平 IR 替代 Capability Graph | Graph 推迟到 Phase 2，Phase 0.5 用 ParsedCapability[] |
| 2026-03-02 | [修订] 安全是 Day 1，不是 Phase 3 | Hacker 发现 3 个 CRITICAL 安全威胁 |
| 2026-03-02 | [修订] 分层生成策略 | Agent 科学家发现 context window 灾难 |
| 2026-03-02 | [修订] 移除 ts-morph | 老派开发者：15MB 依赖，Handlebars 足够 |
| 2026-03-02 | [修订] 窗口期 6-9 月（非 12-18） | 创业者调研发现云厂商已在行动 |
| 2026-03-02 | [v2] 定位升级：Agent Interface Compiler | 不只是 MCP，而是全格式输出 |
| 2026-03-02 | [v2] 多格式输出（MCP+Skills+Docs+IDE rules） | MCP+Skill 协同 +25% 任务完成率 |
| 2026-03-02 | [v2] 5 级产品成熟度模型（L0-L4） | L4 目前不存在，Agentify 填补空白 |
| 2026-03-02 | [v2] Milestone 路线图（M0-M4，14 周） | M0:MCP → M1:多格式 → M2:智能 → M3:自举 → M4:规模 |
| 2026-03-03 | M0 核心实现完成 | Parser+Emitter+Scanner+CLI, 21 tests pass, Petstore demo verified |
| 2026-03-03 | 发现新竞品 openapi-to-skills | 165 stars, 588 API 转换, Skills 不再是蓝海但我们做多格式统一 |
| 2026-03-03 | 时间窗口收窄至 4-7 个月 | 市场情报研究员更新：Speakeasy $37.5M 融资 |
| 2026-03-03 | 营销策略三份报告 | GTM 冷启动、增长飞轮、市场情报 → research/marketing/ |
| 2026-03-06 | 竞品形势加剧 | Speakeasy 21 Skills, Stainless 免费层扩大, 窗口收窄至 3-5 月 |
| 2026-03-06 | npm 包名: @agentify/cli | agentify 被占, 用 scoped 包 (@agentify org 已拥有) |
| 2026-03-06 | AGENTS.md 为必生成格式 | 60K+ 采纳, Linux Foundation 标准, AI 编码工具自动读取 |
| 2026-03-06 | GEO 策略: 内容 > 文件 | llms.txt 无 AI 引用相关性, 权威内容才是 LLM 引用来源 |
| 2026-03-06 | 社区: 低维护开源 | GitHub Issues+Discussions only, 不开 Discord, 自动化管理 |
| 2026-03-06 | Pre-launch 分析完成 | 4 agent 团队调研 → research/strategy/ |
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 First seen · 128 lines · 2,108 tokens per session scan A db0b3ddcfeae
agentify CLAUDE.md is an instructions file published in the GitHub repository MonadWorks/agentify (37 stars, last pushed 5mo ago), licensed MIT. It adds 2,108 tokens to every session, about $0.0105 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 instructions, from other repositories
CopilotKit AGENTS.md
AGENTS.md instructions for CopilotKit/CopilotKit, covering general guidelines for working with nx, copilotkit, essentials, private agent instructions and internal skills.
CopilotKit CLAUDE.md
Claude Code instructions for CopilotKit/CopilotKit, covering general guidelines for working with nx, copilotkit, essentials and reference (read when relevant to your task).
trpc-agent-go AGENTS.md
AGENTS.md instructions for trpc-group/trpc-agent-go, covering agents.md, project overview, engineering principles, go design conventions and implementation workflow.
nuwax AGENTS.md
Instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.
nuwax CLAUDE.md
Instructions for nuwax-ai/nuwax, covering claude ai agent platform frontend, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.
ovo AGENTS.md
AGENTS.md instructions for qntx/ovo, a project described as: Agent behavior that compiles.