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/haaaiawd/anws/tech-evaluatornpx skills add Haaaiawd/ANWS --skill tech-evaluatorgit clone --depth 1 https://github.com/Haaaiawd/ANWSWrote 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/skills/haaaiawd/anws/tech-evaluator)<a href="https://agentmods.dev/skills/haaaiawd/anws/tech-evaluator"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/tech-evaluator.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.03191 |
| Opus 5 | $0.00041 | $0.01596 |
| Sonnet 5 | $0.00016 | $0.00638 |
| Haiku 4.5 | $0.00008 | $0.00319 |
Grade A, and why
tech-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技术评估师手册 — Genesis Step 3
"没有最好的技术栈,只有最适合的技术栈。" —— ThoughtWorks Technology Radar
本技能基于 SEI 的 ATAM (Architecture Tradeoff Analysis Method) 与 加权决策矩阵。在 /genesis 中与 Step 3 绑定;ADR 的正式写入与编号治理以 Step 5 与 genesis.md 为准。
CRITICAL /genesis 门禁(本线专用收口)
[!IMPORTANT]
/genesisStep 3:只输出评估结果与 Markdown 对比素材,不得在本步创建或修改.anws/v{N}/03_ADR/下任何 ADR 文件。原因见genesis.mdStep 3 / Step 5:ADR 为正式决策记录,须在 Step 5 完整审视后落盘。- Step 5 落盘目标(供下游引用,非 Step 3 执行项):将 Step 3 对比表升格为
.anws/v{N}/03_ADR/ADR_001_TECH_STACK.md(及姊妹 ADR),章节结构以references/ADR_TEMPLATE.md为唯一权威。- 若宿主会话声明 非
/genesis或显式授权「本步即写 ADR」,以当场工作流为准;默认仍按 Step 3 不写 ADR。
[!NOTE] ADR 时序:Step 3 只产出评估与对比素材,不写
03_ADR/;Step 4 产出系统边界与02_*;Step 5 再升格 ADR,使影响范围与真实系统 ID 对齐。阶段表与四点论证见genesis.mdStep 3 的 NOTE。若会话非/genesis或用户授权本步写 ADR,以当场工作流为准。
CRITICAL spec 产出契约(Step 3 交付物)
[!IMPORTANT]
- 可核对:约束块须覆盖功能需求、非功能需求、团队、预算、特殊约束;缺的项写「未提供—评估基于假设 H-…」,不得静默省略。
- 可计算:每个候选栈须有 12 维得分表(1–5)或逐维「不适用 + 原因」;禁止只给总分不给细表。
- 可推演:ATAM 段落须含至少一个质量属性场景、若干权衡点、若干风险点;不得用形容词堆叠代替场景。
- 可升格:最终对比表须能无损映射到
references/ADR_TEMPLATE.md的章节与必填节,供 Step 5 粘贴与润色。- 验证策略显式:须回答或标注待决:单测 / 集成 / E2E 侧重、冒烟 / 回归门禁、质量门禁落在 PR / INT / 预发 / 发布的哪一层(与
genesis.mdStep 3 要求一致)。- 单一真源:数值与结论以 Step 3 产出表为准;Step 5 仅做编辑与状态流转,不得在无新证据时反向改分。
强制深度思考
[!IMPORTANT] 在开始评估前必须调用
sequential-thinkingskill,按复杂度组织 3—7 个 thought,例如:
- 用户核心场景与必须支持的用例边界是什么?
- 团队熟悉度与可接受的学习成本?
- 预算与云 / 许可证 TCO 敏感度?
- 预期规模与并发 / 数据量级?
- 合规(GDPR、等保等)是否一票否决某些栈?
任务目标(Step 3)
在不写 ADR 文件前提下,产出:
- 结构化约束摘要与候选栈列表;
- 12 维打分矩阵与加权汇总说明(权重须声明或采用本文建议并说明);
- ATAM 权衡与风险短文;
- 供 Step 5 直接使用的 Markdown 候选方案对比总表。
评估流程 (The Evaluation)
第一步:收集约束 (Gather Constraints)
必须从用户或已加载工件取得(不足的按 spec 契约标注假设):
- 功能需求:核心能力列表(可引用
01_PRD.md)。 - 非功能需求:性能、可用性、安全等级。
- 团队情况:人数、技能栈、学习意愿。
- 预算:开发、运维、时间。
- 特殊约束:合规、存量系统集成、客户指定技术。
- (如已执行 Step 2.5)
/explore研究结论中的证据与备选方案。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 253 lines · 82 tokens per session scan A 2d5664072ec9
tech-evaluator is a skill published in the GitHub repository Haaaiawd/ANWS (142 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 3,191 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 skills, from other repositories
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
verification-planning
Verification planning for non-trivial coding work. Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change that needs a credible project-specific evidence path.
loop-engineering
Loop engineering runtime Grill + Monitor.
agy-researcher
Delegate a deep research or survey task to Google's Antigravity CLI (agy staffer, fast Gemini). Use when the user says /skill:agy-researcher, "ask agy to research", "have the agy staffer survey X", or wants a second, independent deep-dive on a topic or codebase without spending the host model's quota.