FIT is an enterprise AI development framework with a multilingual function engine, a flow orchestration engine, and Java tools for connecting language models, knowledge bases, and external tools. It is for Java-oriented teams building AI applications that can run locally or in distributed deployments with plugins. The catalogue add-ons provide commands, skills, instructions, and settings for working with FIT.
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 commands/modelengine-group/fit-framework/fit-releasegit 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/commands/modelengine-group/fit-framework/fit-release)<a href="https://agentmods.dev/commands/modelengine-group/fit-framework/fit-release"><img src="https://agentmods.dev/badge/commands/modelengine-group/fit-framework/fit-release.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 5.1 | $0.00025 | $0.01805 |
| Opus 5 | $0.00013 | $0.00903 |
| Sonnet 5 | $0.00005 | $0.00361 |
| Haiku 4.5 | $0.00003 | $0.00180 |
Grade A, and why
fit-release 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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Command
执行标准化的版本发布流程。
不含构建验证:仅做版本号替换和 Git 操作。 不含自动推送:仅做本地操作,推送由用户手动完成。
用法:
/prompts:fit-release 1.2.3- 发布 1.2.3 版本
参数说明:
<version>: 发布版本号,格式为X.Y.Z(必需),例如1.2.3
执行步骤
步骤 1:解析并验证参数
从命令参数中提取版本号。
版本号格式验证:
- 必须匹配
X.Y.Z格式(X、Y、Z 均为非负整数) - 如果格式不正确,报错退出:
错误:版本号格式不正确,期望格式为 X.Y.Z(例如 1.2.3)
解析版本组件:
- 主版本号 MAJOR = X
- 次版本号 MINOR = Y
- 修订版本号 PATCH = Z
- 下一修订版本号 NEXT_PATCH = Z + 1
- SNAPSHOT 版本 =
X.Y.Z-SNAPSHOT - 发布版本 =
X.Y.Z - 下一 SNAPSHOT 版本 =
X.Y.(Z+1)-SNAPSHOT
确认 SNAPSHOT 存在:
全局搜索 X.Y.Z-SNAPSHOT:
- 如果没有找到任何匹配,报错退出:
错误:未找到 X.Y.Z-SNAPSHOT,请确认当前代码版本是否正确 - 如果找到匹配,列出所有包含 SNAPSHOT 的文件,告知用户即将替换的范围
步骤 2:确认工作区状态
git status --short
- 如果有未提交的更改,报错退出:
错误:工作区有未提交的更改,请先提交或暂存(git stash)后再执行发布 - 工作区必须是干净的才能继续
步骤 3:全局替换 SNAPSHOT → Release
搜索所有包含 X.Y.Z-SNAPSHOT 的文件,将 X.Y.Z-SNAPSHOT 替换为 X.Y.Z。
覆盖的文件范围(由全局搜索决定,包括但不限于):
**/pom.xml— Maven 版本号和<fit.version>属性README.md— 版本标题docs/**/*.md— 文档中的版本引用*.java— 源码中硬编码的版本字符串*.js— fit.js 中的 VERSION 常量package.json— Node.js 版本号
必须排除的目录(这些目录包含 AI 工具配置、命令模板和示例,不应被版本替换影响):
.agents/.ai-workspace/.claude/.codex/.gemini/.opencode/
替换后验证:
再次搜索 X.Y.Z-SNAPSHOT,确认没有残留。如果仍有残留,继续替换直到全部清除。
步骤 4:创建 Release commit
git add -A && git commit -m "Release X.Y.Z"
步骤 5:创建轻量标签
git tag vX.Y.Z
步骤 6:创建发布分支
git branch release-X.Y.Z
步骤 7:回退当前分支到 Release commit 之前
Release commit 和 tag 已经通过 release-X.Y.Z 分支保留,现在需要将当前开发分支回退到 Release commit 之前的状态,使下一个 SNAPSHOT commit 与 Release commit 成为兄弟关系(共享同一个父节点),而非父子关系。
git reset --hard HEAD~1
执行后,当前分支 HEAD 回到 Release commit 的父节点,而 release-X.Y.Z 分支和 vX.Y.Z tag 仍然指向 Release commit。
步骤 8:全局替换当前 SNAPSHOT → 下一 SNAPSHOT
由于步骤 7 已将工作区回退到 Release commit 之前,文件中的版本号已恢复为 X.Y.Z-SNAPSHOT。
只替换步骤 3 中已知的文件列表(避免误匹配),将 X.Y.Z-SNAPSHOT 替换为 X.Y.(Z+1)-SNAPSHOT。
替换后验证:
抽查几个关键文件(如根 pom.xml),确认版本号已正确更新为 X.Y.(Z+1)-SNAPSHOT。
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 · 210 lines · 25 tokens per session scan A 27818a63b44f
fit-release is a command published in the GitHub repository ModelEngine-Group/fit-framework (2,116 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 1,805 once invoked, about $0.0001 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 commands, from other repositories
promote-public-release
Build, refine, and publish cumulative public release notes, then promote the current alpha prerelease to stable.
android-release
Prepare and execute an Android release (patch/minor/major).
upstream-watch
Review pydantic-ai and pydantic-ai-harness releases published since the last watch entry, and record a verdict in .github/upstream-watch.md.
release-update
(dev-only) release-update maintainer harness — Claude Code upstream change tracker (release-notes version-delta sweep + docs sync). NOT distributed to user projects.
sync-coordinator
Multi-package synchronization and version alignment with ruv-swarm coordination for seamless integration between claude-code-flow and ruv-swarm packages.
github-modes
This document describes all GitHub integration modes available in Claude-Flow with ruv-swarm coordination. Each mode is optimized for specific GitHub workflows and includes batch tool integration for maximum efficiency.