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/fit-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 | $0.00012 | $0.00869 |
| Opus 5 | $0.00006 | $0.00434 |
| Sonnet 5 | $0.00002 | $0.00174 |
| Haiku 4.5 | $0.00001 | $0.00087 |
Grade A, and why
fit-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 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.
What it actually says
根据用户的自然语言描述创建任务并执行需求分析。
🔴 行为边界(必须遵守):
- 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
- 用户描述的内容是"待办事项",不是"立即执行的指令"
用户描述: $ARGUMENTS
执行以下步骤:
-
获取当前时间:
date '+%Y-%m-%d %H:%M:%S' date +%Y%m%d-%H%M%S -
解析用户描述: 从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)
- 包含"添加"、"新增"、"支持" → feature
- 包含"修复"、"解决"、"Bug" → bugfix
- 包含"重构"、"优化"、"改进" → refactor
- 包含"文档"、"Javadoc"、"注释" → docs
- 其他 → chore
- 工作流: feature/docs/chore → feature-development, bugfix → bug-fix, refactor → refactoring
如果描述不够清晰,先向用户确认关键信息后再继续。
-
创建任务目录:
mkdir -p .ai-workspace/active/TASK-<timestamp>/使用 Write 工具基于 .agents/templates/task.md 模板创建 task.md 文件:
- 填写任务元数据: id, type, workflow, status, created_at, updated_at 等
- created_by: human(任务来源于用户的自然语言描述)
- current_step: requirement-analysis
- assigned_to: codex
- 相关Issue: 无
-
执行需求分析(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,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
-
输出分析文档到 analysis.md,包含:
- 需求来源(用户自然语言描述,引用原始描述)
- 需求理解(重新描述需求)
- 相关文件列表(带文件路径和行号)
- 影响范围评估(直接影响和间接影响)
- 技术风险
- 依赖关系
- 工作量和复杂度评估
-
更新任务状态:
- current_step: requirement-analysis
- updated_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 ✅
-
告知用户:
- 输出任务ID、标题、类型、工作流
- 显示输出文件路径
- 提示下一步设计技术方案:
- Claude Code / OpenCode: /plan-task
- Gemini CLI: /fit:plan-task
- Codex CLI: /prompts:fit-plan-task
注意事项:
- 与 analyze-issue 的区别: create-task 从用户自然语言描述创建,相关Issue标记为"无"
- 如果用户描述模糊或缺少关键信息,先向用户确认
🛑 STOP: 完成上述步骤后立即停止。不要继续执行 plan、implement 或任何后续步骤。
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 · 84 lines · 12 tokens per session scan A 2accbdd8e3fa
fit-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 12 tokens to every session and 869 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.