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/plan-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 | $0.00012 | $0.01879 |
| Opus 5 | $0.00006 | $0.00940 |
| Sonnet 5 | $0.00002 | $0.00376 |
| Haiku 4.5 | $0.00001 | $0.00188 |
Grade A, and why
plan-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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Task Command
功能说明
为指定任务设计技术方案,输出详细的实施计划。
⚠️ 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. 查找任务文件
按以下优先级搜索任务:
- 查找
.ai-workspace/active/{task-id}/task.md(优先) - 如果不存在,查找
.ai-workspace/blocked/{task-id}/task.md - 如果不存在,查找
.ai-workspace/completed/{task-id}/task.md - 如果都不存在,提示用户任务不存在
找到后记录任务状态(status)和任务目录路径。
注意:{task-id} 格式为 TASK-{yyyyMMdd-HHmmss},例如 TASK-20260205-202013
2. 读取需求分析
读取 .ai-workspace/{status}/{task-id}/analysis.md:
- 如果不存在,提示用户需要先执行需求分析
- 如果存在,读取并理解需求
3. 理解问题本质和约束条件
- 阅读 analysis.md,理解问题的根本原因和影响范围
- 识别技术约束(从 analysis.md 的"技术依赖和约束"章节获取)
- 识别特殊要求(例如:安全修复需要考虑漏洞修复版本、Bug修复需要防止回归、功能开发需要考虑扩展性)
4. 设计解决方案
按照对应的工作流(如 .agents/workflows/feature-development.yaml)中的 technical-design 步骤:
- 基于 analysis.md 中的信息,提出多个可行方案
- 对比各方案的优劣(效果、成本、风险、可维护性)
- 选择最合适的方案并说明理由
- 制定详细的实施步骤
- 列出需要创建/修改的文件清单
- 设计验证策略(测试、验证、回归检查)
- 评估影响(性能、安全、兼容性)
- 制定风险控制和回滚方案
5. 输出方案文档
创建 .ai-workspace/{status}/{task-id}/plan.md,必须包含以下章节:
# 技术方案和实施计划
## 方案决策
### 问题理解
{基于 analysis.md 的问题理解和根本原因}
### 约束条件
- 技术约束: {技术依赖和限制}
- 业务约束: {业务要求和限制}
- 时间约束: {交付时间要求}
### 备选方案对比分析
{如果有多个方案,详细对比分析各方案的优劣}
### 最终选择
- **方案**:{选择的方案}
- **理由**:{选择理由}
## 技术方案
### 核心解决策略
{详细的解决策略}
### 关键技术点
- {技术点1}
- {技术点2}
### 具体实现细节
{根据问题类型的具体实现,例如:代码实现、依赖升级、配置调整等}
## 实施步骤
### 步骤 1: {步骤名称}
**操作**:{具体操作}
**预期结果**:{预期结果}
### 步骤 2: {步骤名称}
...
## 文件清单
### 需要创建的文件
- `{file-path}` - {说明}
### 需要修改的文件
| 序号 | 文件路径 | 修改内容 | 预计行数 |
|------|----------|----------|----------|
| 1 | {path} | {内容} | {行数} |
## 验证策略
### 功能验证
- 单元测试: {测试范围和验收标准}
- 集成测试: {测试范围和验收标准}
### 问题验证
{确认问题已解决,如:功能正常、Bug不再复现、漏洞已修复}
### 回归验证
{确保没有引入新问题}
## 影响评估
### 性能影响
{性能影响分析和优化建议}
### 安全影响
{安全风险评估和防护措施}
### 兼容性影响
{兼容性分析和注意事项}
## 风险控制
### 潜在风险
| 风险 | 等级 | 应对措施 |
|------|------|----------|
| {风险} | {等级} | {措施} |
### 回滚方案
{如果实施失败,如何回滚}
## 预期产出
- {产出1}
- {产出2}
6. 更新任务状态
更新 .ai-workspace/active/{task-id}/task.md:
current_step: technical-designassigned_to: claudeupdated_at: {当前时间}- 标记 plan.md 为已完成
- 在工作流进度中标记技术方案设计为完成
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 · 242 lines · 12 tokens per session scan A 96b27f5d2cbb
plan-task is a command published in the GitHub repository ModelEngine-Group/fit-framework (2,117 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 1,879 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.