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 skills/modelengine-group/fit-framework/review-tasknpx skills add ModelEngine-Group/fit-framework --skill review-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 | $0.00037 | $0.00312 |
| Opus 5 | $0.00018 | $0.00156 |
| Sonnet 5 | $0.00007 | $0.00062 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
review-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
代码审查
执行步骤
-
验证前置条件:
- .ai-workspace/active//task.md 存在
- .ai-workspace/active//implementation.md 存在
-
读取上下文: task.md, plan.md, implementation.md, git diff。
-
执行代码审查:
- 功能正确性: 实现是否符合技术方案
- 代码质量: 编码规范、命名、注释、复杂度
- 测试覆盖: 是否有充分的测试用例
- 安全性: SQL注入、XSS、权限控制
- 性能: 算法复杂度、资源使用
- 边界情况: 空值处理、异常处理
-
输出审查报告到 review.md:
- 审查发现（分级: 🔴 Blocker / 🟡 Major / 🟢 Minor）
- 总结与建议（✅批准 / ⚠️修改后批准 / ❌需要重大修改）
-
更新任务状态，标记 code-review 为完成。
-
如果需要修改，提示使用 refine-task skill；如果批准，提示使用 commit skill。
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 · 31 lines · 37 tokens per session scan A 8634df7b6cf3
review-task is a skill published in the GitHub repository ModelEngine-Group/fit-framework (2,117 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 312 once invoked, about $0.0002 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 skills, from other repositories
mechanical-engineering-research
Apply source-aware mechanical-engineering judgment to research, analysis, coding, writing, teaching, research identity, and release work. Use for thermal-fluid systems, heat transfer, fluid mechanics, thermodynamics, HVAC, energy systems, turbomachinery, piping, multiphase flow, experiments, correlations, CFD…
swarm
Launching multi-agent parallel work with the Agentic SDLC. Use when a task benefits from decomposition into parallel subtasks.
finish
Completing a development branch for merge readiness. Use when implementation and tests pass and the branch needs formal preparation for review and merge.
grill
Interrogating requirements to validate before building. Use before swarm decomposition, design decisions on ambiguous features, or when scope creep risk is high.
team
Referencing the agent roster, roles, coordination model, and dispatch modes. Use when spawning agents or checking permissions.
ticket
Associate every PDS task with a GitHub issue. Orchestrator finds or creates the ticket, posts plan and acceptance criteria as a checkbox list, updates it as work progresses. Use at Phase 1 of every swarm.