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/refine-titlegit clone --depth 1 https://github.com/ModelEngine-Group/fit-frameworkWhat 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 | $0.00023 | $0.00778 |
| Opus 5 | $0.00012 | $0.00389 |
| Sonnet 5 | $0.00005 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
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 yesterday.
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
Refine Title Command
功能说明
针对指定的 GitHub Issue 或 PR,读取其详细描述(Body)、标签(Labels)以及代码变更(如果是 PR),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。
执行流程
1. 识别对象与获取信息
尝试判断 ID 是 Issue 还是 PR,并获取详细信息。
# 尝试获取 Issue 信息
gh issue view <id> --json number,title,body,labels,state
# 如果提示是 PR,或者查不到 Issue 但存在同号 PR,则获取 PR 信息
gh pr view <id> --json number,title,body,labels,state,files
2. 智能分析
根据获取到的 JSON 数据进行分析:
-
确定 Type (类型):
- 阅读
body中的 "变更类型" 或描述。 - 检查
labels(如type: bug->fix,type: feature->feat)。 - 如果是 PR,分析
files(仅文档变动 ->docs,仅测试变动 ->test)。
- 阅读
-
确定 Scope (范围):
- 阅读
body提及的模块。 - 检查
labels(如in: fit->fit)。 - 如果是 PR,分析
files路径 (如framework/fit/java/...->fit)。
- 阅读
-
生成 Subject (摘要):
- 忽略原标题(避免受干扰),直接从
body中提炼核心意图。 - 确保简练(20字以内)、中文描述、无句号。
- 忽略原标题(避免受干扰),直接从
3. 生成建议与交互
输出分析结果供用户确认:
🔍 分析对象: Issue #<id> / PR #<id>
当前标题: [原标题]
--------------------------------------------------
🧠 分析依据:
- 原始意图: (从 Body 提取的一句话摘要)
- 推断类型: Fix (依据: 标签 type:bug, Body 关键词 "修复")
- 推断范围: fit (依据: 涉及文件路径 framework/fit/...)
--------------------------------------------------
✨ 建议标题: fix(fit): 修复并发场景下的空指针异常
询问用户:"是否确认修改?(y/n)"
4. 执行修改
用户确认(y)后,根据对象类型执行命令:
# 如果是 Issue
gh issue edit <id> --title "<new-title>"
# 如果是 PR
gh pr edit <id> --title "<new-title>"
参数说明
<id>: Issue 或 PR 的编号(必需)。
使用示例
# 智能重命名 Issue #1024
/refine-title 1024
优势
相比于批量修改 (/normalize-titles),本命令:
- 修正错误:如果原标题是 "Help me",此命令能读懂内容并改为 "fix(core): 修复启动报错"。
- 更精准的 Scope:通过分析 PR 的文件变动,能自动判断是
fit还是waterflow,无需人工指定。
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.
- yesterday First seen · 92 lines · 23 tokens per session scan A 9343b2f74053
refine-title is a command published in the GitHub repository ModelEngine-Group/fit-framework (2,117 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 778 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 2026-08-30.
Other commands, from other repositories
overview
Codev provides three CLI tools for AI-assisted software development.
me-han-hu-draft
Draft a technical manuscript section in Han Hu manuscript mode using the private calibrated style corpus and evidence-preserving engineering workflow.
me-cfd-review
Review thermal-fluid CFD setup, boundary conditions, mesh, wall treatment, convergence, validation, and whether the claims are supported.
me-code-sanity
Run a fast preflight on thermal-fluid research code for units, baselines, leakage, physics checks, and result traceability.
me-correlation-check
Check thermal-fluid equations, empirical correlations, and dimensionless groups for validity range, assumptions, units, and claim strength.
me-experiment-plan
Plan thermal-fluid experiments with instrumentation, calibration, uncertainty, repeatability, heat-loss correction, operating envelope, and safety checks.