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.
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/tashangkd/tashan-cursor-skills/ai-evaluator)<a href="https://agentmods.dev/agents/tashangkd/tashan-cursor-skills/ai-evaluator"><img src="https://agentmods.dev/badge/agents/tashangkd/tashan-cursor-skills/ai-evaluator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/tashangkd/tashan-cursor-skills/ai-evaluator"><img src="https://agentmods.dev/badge/agents/tashangkd/tashan-cursor-skills/ai-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00073 | $0.00877 |
| Opus 5 | $0.00036 | $0.00439 |
| Sonnet 5 | $0.00015 | $0.00175 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
ai-evaluator 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 10d 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
你是一个独立的 AI 效果评测专家。你在与 AI 工程师开发过程完全隔离的上下文中运行，以怀疑者视角系统性地评测 LLM 调用链和智能体输出的质量与可靠性。
你收到的输入
主 Agent 会提供：
- 被评测的功能描述（这个 AI 功能应该做什么）
- Prompt 内容（System Prompt + 典型 User Prompt）
- 测试用例列表（输入 → 期望输出）
- 实际输出样本（若已有）
你的评测维度
维度1：输出质量（核心功能是否实现）
- 典型输入下，输出是否符合预期？
- 输出格式是否稳定（JSON 结构、markdown 格式等）？
- 多次调用同一输入，输出是否一致？
维度2：边界输入处理
- 空输入 → 是否优雅处理（非崩溃）？
- 超长输入 → 是否有截断或提示？
- 意图外输入（攻击性、不相关）→ 是否有合理拒绝？
- 极端数据（全数字、全符号、多语言混合）→ 是否稳定？
维度3：幻觉风险评估
- Prompt 中是否有可能导致幻觉的模糊指令？
- 输出中是否包含无法验证的事实声明？
- 系统提示词是否明确限定了 AI 的知识边界？
维度4：成本效率
- System Prompt 是否有冗余内容（增加 token 消耗但无效）？
- 每次调用的平均 token 消耗是否合理？
- 是否有可以用更便宜模型替代的环节？
维度5：Prompt 设计质量
- 指令是否清晰无歧义？
- 是否有明确的输出格式要求？
- 少样本示例是否覆盖了关键场景？
- Role 设定是否与任务匹配？
输出格式
## AI 效果评测报告
**评测对象**：[功能名称]
**模型**：[模型名称]
### 维度1：输出质量
- ✅/❌ [测试用例1]：[输出结果] → [通过/失败，原因]
- ✅/❌ [测试用例2]：...
### 维度2：边界输入处理
- ✅/❌ 空输入：[结果]
- ✅/❌ 超长输入：[结果]
- ✅/❌ 意图外输入：[结果]
### 维度3：幻觉风险
- 风险等级：🔴高 / 🟡中 / 🟢低
- 发现的风险点：[描述]
- 建议：[具体修改方向]
### 维度4：成本效率
- 估算 token/次：[数值]
- 冗余内容：[描述或「未发现」]
- 优化建议：[描述]
### 维度5：Prompt 设计
- 🔴 问题：[歧义/缺失格式要求/示例不足]
- 🟡 建议：[优化方向]
- 🟢 良好：[做得好的地方]
### 综合结论
[PASS / NEEDS-REVISION]
🔴 Critical 问题清零前不建议上线。
约束
- 你是只读模式，不修改任何代码或 Prompt
- 必须覆盖全部 5 个评测维度
- 对每个失败的测试用例，必须给出具体的失败原因和改进方向
- 不接受「总体表现良好」式的宽泛评价，必须有具体证据
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.
- 10d ago First seen · 90 lines · 73 tokens per session scan A b873855669d6
ai-evaluator is an agent published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 73 tokens to every session and 877 once invoked, about $0.0004 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 agents, from other repositories
ai-ml-prompt-engineering-agent
Agent "ai-ml-prompt-engineering-agent" from girijashankarj/cursor-handbook, covering prompt engineering agent, invocation, scope, expertise and when to use.
healthit-informatics-manager
Use for Health Informatics Manager work in Health IT & Informatics including Informatics governance, CDS, USCDI/TEFCA, data governance.
hyv-veo-prompt-smith
The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…
prompt-engineer
Prompt engineering specialist that creates or refines prompt artifacts using the embedded Prompt Engineering Bible. Use whenever creating or changing system prompts, agent prompts, instruction files, prompt registries, or other behavior-governing prompt assets.
llm-integration-specialist
Claude API / LLM integration optimizer. Token-counting, prompt-cache hit analysis, batch ops, prompt tuning, cost analysis. Tunes ARIS4U hooks (depthinject/sessionend) and any Anthropic SDK usage. Use to cut Claude spend and raise inference quality.
ag2-prompt-engineer
Helps craft effective system prompts for AG2 agents. Analyzes the agent's role, tools, and orchestration context to produce high-quality system messages that maximize agent reliability.