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/create-taskgit 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 | $0.00015 | $0.01975 |
| Opus 5 | $0.00008 | $0.00988 |
| Sonnet 5 | $0.00003 | $0.00395 |
| Haiku 4.5 | $0.00002 | $0.00198 |
Grade A, and why
create-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 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Task Command
功能说明
根据用户的自然语言描述,创建任务并执行需求分析,输出分析文档。适用于没有 GitHub Issue 的场景,用户可以直接用自然语言描述想做的事情。
🔴 CRITICAL: 行为边界
本命令的唯一产出是 task.md 和 analysis.md 两个文件。
- ❌ 禁止编写、修改、创建任何业务代码或配置文件
- ❌ 禁止直接实现用户描述的功能
- ❌ 禁止跳过工作流直接进入 plan/implement 阶段
- ✅ 只做:解析描述 → 创建任务文件 → 需求分析 → 输出分析文档 → 告知用户下一步
用户描述的内容是待办事项,不是立即执行的指令。
⚠️ CRITICAL: 状态更新要求
执行此命令后,你必须立即更新任务状态。参见规则 7。
执行流程
1. 解析用户描述
从用户的自然语言描述中提取以下信息:
- 任务标题:精简的中文标题(20 字以内)
- 任务类型:
feature|bugfix|refactor|docs|chore(根据描述推断) - 工作流:
feature-development|bug-fix|refactoring(根据类型推断) - 详细描述:用户原始描述的整理版本
如果描述不够清晰,先向用户确认关键信息后再继续。
2. 创建任务目录和文件
- 创建任务目录:
.ai-workspace/active/TASK-{yyyyMMdd-HHmmss}/ - 使用
.agents/templates/task.md模板创建任务文件:task.md
⚠️ 重要:
- 任务目录命名:
TASK-{yyyyMMdd-HHmmss}(必须包含TASK-前缀) - 示例:
TASK-20260213-143022 - 任务ID(
{task-id})即为目录名
任务元数据(在 task.md 的 YAML front matter 中):
id: TASK-{yyyyMMdd-HHmmss}
type: feature|bugfix|refactor|docs|chore
workflow: feature-development|bug-fix|refactoring
status: active
created_at: {yyyy-MM-dd HH:mm:ss}
updated_at: {yyyy-MM-dd HH:mm:ss}
created_by: human
current_step: requirement-analysis
assigned_to: claude
注意:created_by 设为 human,因为任务来源于用户的自然语言描述。
3. 执行需求分析
按照 .agents/workflows/feature-development.yaml 中的 requirement-analysis 步骤:
必须完成的任务(仅分析,不编写任何业务代码):
- 理解用户描述的需求
- 搜索相关代码文件(使用 Glob/Grep 工具,只读不改)
- 分析代码结构和影响范围
- 识别潜在的技术风险和依赖
- 评估工作量和复杂度
4. 输出分析文档
创建 .ai-workspace/active/{task-id}/analysis.md,必须包含以下章节:
# 需求分析报告
## 需求来源
**来源类型**: 用户自然语言描述
**原始描述**:
> {用户的原始描述}
## 需求理解
{用自己的话重新描述需求,确保理解正确}
## 相关文件列表
- `{file-path}:{line-number}` - {说明}
## 影响范围评估
**直接影响**:
- {影响的模块和文件}
**间接影响**:
- {可能影响的其他部分}
## 技术风险
- {风险描述和应对思路}
## 依赖关系
- {需要的依赖和其他模块的配合}
## 工作量和复杂度评估
- 复杂度:{高/中/低}
- 风险等级:{高/中/低}
5. 更新任务状态
更新 .ai-workspace/active/{task-id}/task.md:
current_step: requirement-analysisassigned_to: claudeupdated_at: {当前时间}- 标记 analysis.md 为已完成
- 在"工作流进度"中标记 requirement-analysis 为完成 ✅
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 · 221 lines · 15 tokens per session scan A f6b5b0acdecc
create-task is a command published in the GitHub repository ModelEngine-Group/fit-framework (2,117 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 1,975 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-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.
me-lit-matrix
Build a thermal-fluid literature matrix organized by mechanism, method, metric, validity range, benchmark value, and unresolved gap.