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/analyze-codescangit 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 | $0.00019 | $0.02100 |
| Opus 5 | $0.00010 | $0.01050 |
| Sonnet 5 | $0.00004 | $0.00420 |
| Haiku 4.5 | $0.00002 | $0.00210 |
Grade A, and why
analyze-codescan 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Code Scanning Command
功能说明
分析指定的 Code Scanning(CodeQL)告警,评估安全风险并创建修复任务,输出安全分析文档。
执行流程
1. 获取告警信息
gh api repos/{owner}/{repo}/code-scanning/alerts/<alert-number>
提取关键信息:
number: 告警编号state: 状态(open/dismissed/fixed)rule: 规则信息id: 规则 ID(如java/sql-injection)severity: 严重程度(error/warning/note)description: 规则描述security_severity_level: 安全严重级别(critical/high/medium/low)
tool: 扫描工具信息name: 工具名(如 CodeQL)version: 版本
most_recent_instance: 最近发现的实例location: 文件位置(path/start_line/end_line)message: 告警消息state: 实例状态
html_url: GitHub 上的告警链接
2. 创建任务目录和文件
检查是否已存在该告警的任务:
- 在
.ai-workspace/active/中搜索相关任务 - 如果找到,询问是否重新分析
- 如果没有,创建新任务
任务目录结构:
.ai-workspace/active/TASK-{yyyyMMdd-HHmmss}/
├── task.md ← 使用 .agents/templates/task.md 模板创建
└── analysis.md ← 本命令将创建此文件
⚠️ 重要:
- 任务目录命名:
TASK-{yyyyMMdd-HHmmss}(必须包含TASK-前缀) - 示例:
TASK-20260205-202013 - 任务ID(
{task-id})即为目录名:TASK-{yyyyMMdd-HHmmss}
任务元数据(在 task.md 的 YAML front matter 中)需包含:
id: TASK-{yyyyMMdd-HHmmss}
codescan_alert_number: <alert-number>
severity: <critical/high/medium/low>
rule_id: <rule-id>
tool: <tool-name>
3. 定位和分析源码
必须完成的分析:
- 根据
most_recent_instance.location定位源码文件和行号 - 读取告警所在的源码上下文(前后 20 行)
- 理解 CodeQL 规则的含义和检测逻辑
- 分析代码为什么触发了该规则
- 检查是否有其他位置也存在相同问题(使用 Grep 工具)
- 评估是否为误报(代码逻辑是否确实存在安全隐患)
4. 评估安全风险
必须完成的风险评估:
- 评估漏洞的实际影响(是否可被利用)
- 分析代码路径是否可达(外部输入能否到达漏洞点)
- 评估对系统安全性的影响程度
- 识别潜在的攻击向量
- 确定修复的紧急程度
- 评估修复的复杂度和风险
5. 输出分析文档
创建 .ai-workspace/active/{task-id}/analysis.md,必须包含以下章节:
注意:{task-id} 格式为 TASK-{yyyyMMdd-HHmmss},例如 TASK-20260205-202013
# Code Scanning 告警分析报告
## 告警基本信息
- **告警编号**: #{alert-number}
- **严重程度**: {critical/high/medium/low} 🔴/🟠/🟡/🟢
- **规则 ID**: {rule-id}
- **扫描工具**: {tool-name} {tool-version}
- **告警状态**: {open/dismissed/fixed}
- **规则描述**: {rule-description}
## 告警详情
### 源码位置
- **文件路径**: `{file-path}`
- **行号范围**: L{start-line} - L{end-line}
- **告警消息**: {message}
### 代码上下文
```{language}
// 告警所在的代码片段(包含前后上下文)
{code-snippet}
规则说明
{详细解释 CodeQL 规则检测的安全问题类型}
影响范围评估
直接影响的代码
{file-path}:{line-number}- {说明}
相同模式的其他位置
- {搜索项目中是否有类似的代码模式}
安全风险评估
漏洞可利用性
- 外部输入能否到达该代码路径?
- 是否有输入验证或过滤?
- 当前配置是否暴露了漏洞?
结论: {高/中/低风险 - 说明理由}
攻击向量
{描述可能的攻击方式}
影响程度
{评估对系统安全性、数据完整性、可用性的影响}
紧急程度
{根据严重程度和可利用性确定修复的紧急程度}
修复建议
推荐修复方式
{具体的代码修改建议}
修复复杂度
{评估修复的难度和工作量}
技术依赖和约束
{列出修复时需要考虑的技术依赖和约束条件}
参考链接
- GitHub Alert: {html_url}
- CodeQL Rule: https://codeql.github.com/codeql-query-help/{language}/{rule-id}/
- {其他相关文档}
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 · 254 lines · 19 tokens per session scan A 57f0f4e72ca9
analyze-codescan is a command published in the GitHub repository ModelEngine-Group/fit-framework (2,117 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 2,100 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
me-han-hu-revise
Revise an existing technical manuscript in Han Hu manuscript mode while preserving scientific evidence, figures, values, citations, and claim boundaries.
me-build-slides
Build a graphics-first thermal-fluid research presentation with slide-to-slide logic, visual plans, speaker notes, and backup-slide structure.
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.