briefbound-test-strategy SKILL.md skillA
briefbound-test-strategy from ccdawn/codex-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ccdawn/codex-skills/briefbound-test-strategy@git:20260920.280b6d2Pins git:20260920.280b6d2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ccdawn/codex-skills
- Path
skills/engineering/briefbound-test-strategy/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260920.280b6d2, committed Sep 20, 2026
- First version recorded
- Sep 20, 2026
- Size
- 4,309 bytes
- Repository stars
- 6
- License
- MIT
Use when tests or coverage are the primary unknown: backfilling tests for untested code, coverage gap analysis, choosing test levels, or selecting regression tests after a change; do not use for TDD of newly defined behavior, bug-fix verification anchors, or benchmark work.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Briefbound Test Strategy ## 目标 回答“测什么、测到什么程度、用什么层级”，用最小决定性测试挡住真实风险。它负责测试策略与存量补测，不负责新行为的 TDD 流程、bug 修复验证或性能基准。 ## Briefbound task contract - Context Boundary: 被测对象与关键路径、现有测试体系与 runner、已知风险区、变更范围和允许写入面。 - Output Contract: 风险排序、层级选择、每条测试挡住的具体风险、覆盖缺口结论和最小补测集。 - Allowed Action: 在授权范围内编写并运行测试；不静默修改被测实现、mock 语义或 CI 阈值。 - Success Evidence: 每条测试与其防御的风险一一对应；失败注入或等价证据证明测试真的会失败；命令与结果可复现。 - Stop Condition: 被测行为未定义、关键依赖无法隔离、测试基建缺失且引入需授权，或测试目标与业务目标冲突。 - Route Out: 新行为 RED 流程 `briefbound-bdd-tdd-development`；bug 修复验证 `briefbound-bug-review`；性能基准 `briefbound-performance-engineering`；契约设计 `briefbound-api-contract`；已验证残留 `briefbound-development-cleanup`；`briefbound-router` 或 BLOCKED。 ## 统一调用契约 - 只处理 Briefbound task contract 范围；不匹配时回 `briefbound-router` 或更具体 owner，复合任务不吞其他 owner。 - 用户可见内容默认中文，先说结论与覆盖判断，不贴大段测试代码；Route Out 仅以 Briefbound task contract 为准，有自然闸门时末行 `下一步建议: <一个具体动作>`，否则继续已授权工作。 ## 激活闸门 只有测试或覆盖是主要未知量，或用户明确要求补测、测试计划、覆盖分析、回归选择时进入。已定义清楚的新行为走 BDD/TDD owner；修 bug 的验证锚点留在 bug-review 内部，不转移到本 skill。 ## 层级选择 按风险选层级，不按覆盖率数字凑数： - 单元：纯逻辑、状态机、边界与错误分支；依赖少、失败定位快。 - 集成：跨模块协作、持久化、队列与外部服务的契约适配。 - E2E/浏览器：只有信任边界、关键用户旅程或回归高发路径值得；慢且脆，不用于堆数量。 框架中立：优先用仓库现有 runner 与断言风格；没有测试体系时提议最小引入并等待授权，不静默搭建全套基建。 …
Read the whole file at its exact version.
How to install
mdr add ccdawn/codex-skills/briefbound-test-strategy@sha256:0b2d2cee5dc71ad2The line at the top of this page pins the label git:20260920.280b6d2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_7vob3xrm7tm65udj)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 20, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260920.280b6d2 latest | 2026-09-20 | 280b6d2 | 4,309 B | A | view · diff |
| git:20260920.2c24d66 | 2026-09-20 | 2c24d66 | 4,268 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4309 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ccdawn/codex-skills · 6 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7vob3xrm7tm65udj GET https://markdownregistry.com/api/v1/resolve?ref=ccdawn/codex-skills/briefbound-test-strategy GET https://markdownregistry.com/api/v1/blob/0b2d2cee5dc71ad29678023e568100b828588f1ea7b64a188e3f22c08e000bf5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.