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.
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.
curl -O https://raw.githubusercontent.com/ModelEngine-Group/fit-framework/main/.codex/commands/fit-refine-task.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/commands/modelengine-group/fit-framework/fit-refine-task)<a href="https://agentmods.dev/commands/modelengine-group/fit-framework/fit-refine-task"><img src="https://agentmods.dev/badge/commands/modelengine-group/fit-framework/fit-refine-task.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 | $0.00009 | $0.00538 |
| Opus 5 | $0.00005 | $0.00269 |
| Sonnet 5 | $0.00002 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
fit-refine-task 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.
What it actually says
处理任务 $1 的代码审查反馈,修复审查中发现的问题。
执行以下步骤:
-
验证前置条件: 检查必需文件是否存在:
- .ai-workspace/active/$1/task.md
- .ai-workspace/active/$1/review.md 如果任一文件不存在,提示用户先完成前置步骤。
-
读取审查报告: 仔细阅读 .ai-workspace/active/$1/review.md,整理:
- 🔴 Blocker 问题(必须修复)
- 🟡 Major 问题(建议修复)
- 🟢 Minor 问题(可选修复)
-
逐项修复: 按优先级(Blocker → Major → Minor)逐项修复:
- 对每个问题,理解根因并实施修复
- 修复后运行相关测试验证
- 记录每个问题的修复方式
-
运行测试验证:
mvn test -pl :<module-name>确保所有测试通过,包括新增的回归测试。
-
更新实现报告: 在 .ai-workspace/active/$1/implementation.md 中追加"修复记录"章节:
- 列出每个修复的问题及修复方式
- 新增或修改的文件
- 测试验证结果
-
更新任务状态: 使用 Edit 工具更新 .ai-workspace/active/$1/task.md:
- current_step: refinement
- assigned_to: codex
- updated_at: 当前时间
-
告知用户:
- 输出修复的问题数量(按级别)
- 提示重新审查:
- Claude Code / OpenCode: /review-task $1
- Gemini CLI: /fit:review-task $1
- Codex CLI: /prompts:fit-review-task $1
- 或直接提交:
- Claude Code / OpenCode: /commit
- Gemini CLI: /fit:commit
- Codex CLI: /prompts:fit-commit
注意事项:
- 严格按照审查报告修复,不要添加额外变更
- 每修复一个问题就运行测试
- 不要自动执行 git commit
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.
- 3d ago First seen · 61 lines · 9 tokens per session scan A a04d514ab333
fit-refine-task is a command published in the GitHub repository ModelEngine-Group/fit-framework (2,115 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 538 once invoked, about $0.0000 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
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
me-code-review
Perform a full thermal-fluid research-code review covering architecture, reproducibility, units, physics, interfaces, tests, and released artifacts.
sparc-refinement-optimization-mode
🧹 Optimizer - You refactor, modularize, and improve system performance. You enforce file size limits, dependenc...
unwired
Scans the whole codebase for implementations that exist but are never wired in — and for wired implementations left incomplete — then, per finding and only with explicit user confirmation, wires, transfers, or removes them.
check-pr
Check the current branch's PR for external review feedback, fix errors and warnings, run a final external review, and push.