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 skills add BlueprintOS/analysis-to-delivery --skill test-case-designgit clone --depth 1 https://github.com/BlueprintOS/analysis-to-deliveryWrote 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/blueprintos/analysis-to-delivery/test-case-design)<a href="https://agentmods.dev/skills/blueprintos/analysis-to-delivery/test-case-design"><img src="https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/test-case-design/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/skills/blueprintos/analysis-to-delivery/test-case-design"><img src="https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/test-case-design.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 | $0.00064 | $0.01003 |
| Opus 5 | $0.00032 | $0.00502 |
| Sonnet 5 | $0.00013 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
test-case-design 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 9d 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
Test-Case-Design — 测试用例设计
Contract
- 输入: 已签字的 BRD,可选
04-合规评审.md,业务规则与验收标准 - 输出:
07-测试用例设计.md - 门控: BRD 功能已覆盖;正常/边界/异常/合规 4 大类齐;用户签字
- Required rules:
stage-gate,no-field-guessing,doc-numbering,goal-boundary - Required paths:
knowledge-path,doc-naming-path - 下一步:
/to-prd
适用场景
- BRD 通过,需要明确"什么算成功"
- 开发前需要验收标准
- 测试团队需要用例输入
流程步骤
1. 加载模板
templates/TEST_CASE_DESIGN.md
2. 覆盖范围
按以下 5 大类逐项设计:
| 类别 | 内容 | 占比建议 |
|---|---|---|
| 正常路径 | 主流程 happy path | 30% |
| 边界条件 | 极值、空值、最大/最小 | 20% |
| 异常路径 | 错误输入、超时、外部依赖失败 | 30% |
| 合规校验 | 数据授权、审计、效期锁定 | 10% |
| 性能/安全 | 并发、SQL 注入、XSS | 10% |
3. 用例结构
每条用例至少包含:
| 字段 | 说明 |
|---|---|
| 用例编号 | TC-{模块}-{序号} |
| 关联需求 | BRD §{章节} |
| 前置条件 | 初始数据/状态 |
| 输入 | 测试数据 |
| 操作步骤 | 步骤化 |
| 预期结果 | 精确、可验证 |
| 实际结果 | 测试执行时填 |
| 通过条件 | PASS/FAIL 判定标准 |
4. 业务规则回测(从 BRD §四 提取)
对每条业务规则设计至少 1 个用例:
- 正向:触发条件满足 → 期望行为
- 反向:触发条件不满足 → 期望拦截
- 边界:临界值
输出
07-测试用例设计.md
调用的 rule
rules/stage-gate— 阶段 5 门控
结束条件
- 用例覆盖 BRD §四 全部功能点
- 异常路径 100%(每条主流程至少 1 个异常用例)
- 业务规则正向 + 反向 + 边界 三类齐
- 合规校验用例关联到合规评审条款
- 用户签字进入
/to-prd
反模式
- ❌ 5 大类缺一(正常路径/边界条件/异常路径/合规校验/性能安全) —
testcase-coverage-check.py --strict直接 fail - ❌ TC 编号不规范(TC-001 写成 Test001) — 必须
TC-N-xxx/TC-B-xxx/TC-E-xxx/TC-C-xxx/TC-P-xxx前缀 - ❌ 合规校验用例未关联到合规条款 — 每条 TC-C-* 必须标
GSP-XXX/GDPR-Art-X等条款号 - ❌ 只写正常路径不写异常 — 主流程:异常用例比例 ≥ 1:1,异常路径 ≥ 90% 覆盖
- ❌ 性能测试写"应该很快" — 必须量化(P95 < Xs / 并发 Y 单/秒)
- ❌ 用例步骤空泛("操作直到成功") — 必须分 1/2/3/4 步,每步可复现
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.
- 9d ago First seen · 91 lines · 64 tokens per session scan A 8c8cac13b5c3
test-case-design is a skill published in the GitHub repository BlueprintOS/analysis-to-delivery (26 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,003 once invoked, about $0.0003 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
qa-testing
Run QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to QA a page or site, run a smoke test after a deploy, verify a page before launch, or run a regression sweep. Triggers on QA, QA sweep, smoke test, regression test, post-deploy…
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
senpi-qa
QA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the REAL senpi binary in strict isolation, and write every artifact to the one canonical evidence path .omo/evidence/omo-senpi-adapter/ /. The live drivers under packages/omo-senpi/scripts/qa/ create their own isolated SENPICODINGAGENTDIR and…
suede-ai-eval
Suede Labs AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure scores, and mechanical acceptance gates. Use when a change ships LLM, RAG, agent, classifier, prompt, or generated-media behavior, or when asked to write evals…