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/modelengine-group/fit-framework/agents-mdgit clone --depth 1 https://github.com/ModelEngine-Group/fit-frameworkWrote 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/modelengine-group/fit-framework/agents-md)<a href="https://agentmods.dev/instructions/modelengine-group/fit-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/modelengine-group/fit-framework/agents-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 | $0.00819 | $0.00819 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
fit-framework 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 today.
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.
What it actually says
FIT Framework - AI 开发指南
本仓库包含 FIT 框架及相关引擎（framework/fit/java、framework/fit/python、framework/waterflow、framework/fel）。
快速开始命令
# 构建全部模块（包含测试）
mvn clean install
# 仅构建 Java FIT 框架
cd framework/fit/java && mvn clean install
# 启动 FIT 运行时（依赖 Node.js，默认端口 8080）
./build/bin/fit start
# 完整验证流程（构建 + 启动 + 健康检查）
./.agents/scripts/run-test.sh
编码规范（必须遵守）
Java 代码风格
- 使用 IntelliJ 配置
CodeFormatterFromIdea.xml格式化代码 - 公共/受保护的 API 必须有 Javadoc，包含
@param/@return - 类头必须包含
@author和@since yyyy-MM-dd
版权头更新规则
修改任意带版权头的文件时，必须更新版权年份：
- 先运行
date +%Y获取当前年份（不要硬编码） - 更新格式示例（假设当前年份为 2026）：
2024-2025→2024-20262024→2024-2026
分支命名
使用模块前缀：fit-feature-xxx、waterflow-bugfix-yyy
测试要求
- 基线命令：
mvn clean install（自动运行所有测试） - 测试命名：
*Test.java - 测试文件与源码同模块放置
- 模块级测试：在模块目录下运行
mvn test
提交与 PR 规范
提交信息格式（Conventional Commits）
<type>(<scope>): <subject>
示例：
feat(fit): 添加新的数据验证功能
fix(waterflow): 修复空指针异常
docs(fel): 更新表达式语言文档
- type:
feat,fix,docs,refactor,test,chore - scope:
fit,waterflow,fel（可省略） - subject: 中文，20 字以内
PR 检查清单
提交 PR 前必须确保：
- 所有测试通过（
mvn clean install） - 代码已格式化
- 公共 API 有 Javadoc
- 版权头年份已更新
安全注意事项
- ❌ 不要提交敏感文件：
.env,credentials.json, 密钥等 - ⚠️ 安全问题请按
SECURITY.md指引私下提交（不要公开 Issue） - 启用 git hooks：
git-hooks/check-utf8-encoding.sh
多 AI 协作支持
本项目支持 Claude、ChatGPT、Gemini、Cursor 等多个 AI 工具协同工作。
协作配置目录：
.agents/- AI 配置和工作流定义（版本控制）.ai-workspace/- 协作工作区（临时文件，已被 git ignore）
详细协作指南：.agents/README.md
语言规范：
- AI 回复语言与用户输入保持一致（中文问→中文答，英文问→英文答）
- 项目文档默认语言：中文
- 代码注释默认语言：中文
基于标准: AGENTS.md (Linux Foundation AAIF)
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.
- today First seen · 92 lines · 819 tokens per session scan A 412060d96b85
fit-framework AGENTS.md is an instructions file published in the GitHub repository ModelEngine-Group/fit-framework (2,116 stars, last pushed 5mo ago), licensed MIT. It adds 819 tokens to every session, about $0.0041 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 2026-09-03.
Other instructions, from other repositories
agent-framework python.instructions.md
Instructions for microsoft/agent-framework: See AGENTS.md for project structure and package documentation. Detailed conventions are in the agent skills under .github/skills/.
mini-swe-agent copilot-instructions.md
Copilot instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.
innovation-lab-examples python.instructions.md
Instructions for fetchai/innovation-lab-examples, a project described as: 80+ production-ready AI agent examples in Python — build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.
valuecell AGENTS.md
Instructions for ValueCell-ai/valuecell, covering guidelines, python programming, python environment, imports and runtime checks.
agentscope-java code-review.instructions.md
Instructions for agentscope-ai/agentscope-java, covering java code standards, security check, performance check, documentation sync check and pr title check.
Agentflow CLAUDE.md
Instructions for 10xHub/Agentflow, covering agentflow (core python library) — engineering guide, what this package is, working principles for this codebase, package layout (real, current) and import map (verified) — this is the part that bites people.