fit-framework: Command for Claude Code

.codex/commands/fit-refine-title.md

fit-refine-title is a command for Claude Code, Codex from ModelEngine-Group/fit-framework. It costs 17 tokens per session (418 once invoked), scanned A, original, MIT.

A command that reads a GitHub issue or pull request and proposes a title in Conventional Commits format, such as type(scope): subject. It can then rename the issue or pull request after asking for confirmation.

In plain words
What is it for?
It is for retitling GitHub issues and pull requests after examining their descriptions, labels, and changed files.
Why use it?
It replaces vague or misleading titles with short titles that describe the change and its area of the codebase. Conventional Commits is a shared title style using types such as feat and fix.

Command for Claude CodeCodex

Written for Claude Code and Codex: argument-hint in frontmatter, but also installed under .codex/. Also seen: positional $N argument.

This is ModelEngine-Group/fit-framework's own configuration. It tells Claude Code and Codex how to work on fit-framework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fit-framework configures →

About the project

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.

ModelEngine-Group/fit-framework · 2,115 stars · on GitHub · modelengine-ai.net

Reuse

Borrowing it

Nothing to install: this file belongs to ModelEngine-Group/fit-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ModelEngine-Group/fit-framework/main/.codex/commands/fit-refine-title.md
Clone the repo
git clone --depth 1 https://github.com/ModelEngine-Group/fit-framework

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for fit-refine-title

README.md
[![agentmods](https://agentmods.dev/badge/commands/modelengine-group/fit-framework/fit-refine-title.svg)](https://agentmods.dev/commands/modelengine-group/fit-framework/fit-refine-title)
Your own site
<a href="https://agentmods.dev/commands/modelengine-group/fit-framework/fit-refine-title"><img src="https://agentmods.dev/badge/commands/modelengine-group/fit-framework/fit-refine-title.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 418 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 5.1 $0.00017 $0.00418
Opus 5 $0.00009 $0.00209
Sonnet 5 $0.00003 $0.00084
Haiku 4.5 $0.00002 $0.00042

Measured 3d ago against content hash f1975753af84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fit-refine-title 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 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.

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.

.codex/commands/fit-refine-title.md · 48 lines

What it actually says

针对 GitHub Issue 或 PR #$1,读取其详细描述、标签和代码变更,深度理解其意图,然后生成符合 type(scope): subject 规范的新标题并执行修改。

执行以下步骤:

  1. 识别对象与获取信息: 先尝试获取 Issue:

    gh issue view $1 --json number,title,body,labels,state
    

    如果失败,尝试获取 PR:

    gh pr view $1 --json number,title,body,labels,state,files
    
  2. 智能分析: 2.1 确定 Type: 阅读 body、检查 labels(bug→fix, feature→feat)、分析 files 2.2 确定 Scope: 分析涉及的模块(fit/waterflow/fel) 2.3 生成 Subject: 从 body 中提炼核心意图(忽略原标题),20字以内中文

  3. 生成建议与交互:

    🔍 分析对象: Issue/PR #$1
    当前标题: <原标题>
    🧠 分析依据: <推断类型和范围的依据>
    ✨ 建议标题: <type>(<scope>): <subject>
    

    询问用户: "是否确认修改?(y/n)"

  4. 执行修改: Issue: gh issue edit $1 --title "<new-title>" PR: gh pr edit $1 --title "<new-title>"

  5. 告知用户:

    ✅ 标题已更新
    原标题: <old>
    新标题: <new>
    

注意事项:

  • 必须先分析内容,不要直接使用原标题
  • 确保用户确认后再执行修改
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 · 48 lines · 17 tokens per session scan A f1975753af84

Subscribe to this mod's changes

fit-refine-title is a command published in the GitHub repository ModelEngine-Group/fit-framework (2,115 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 418 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.