universal-dev-standards 6.7.4 → 6.7.5

package/bundled/locales/zh-CN/CHANGELOG.md

@@ -1,7 +1,7 @@
 ---
 source: ../../CHANGELOG.md
-source_version: 6.7.4
-translation_version: 6.7.4
+source_version: 6.7.5
+translation_version: 6.7.5
 last_synced: 2026-08-18
 status: current
 ---
@@ -17,6 +17,17 @@ status: current
 
 ## [Unreleased]
 
+## [6.7.5] - 2026-08-18
+
+### 变更
+
+- **八个 skill 重新可以被模型选中。** `audit-assistant`、`changelog-guide`、`commit-standards`、`docs-generator`、`project-discovery`、`release-standards`、`reverse-engineer` 与 `spec-derivation` 都带着 `disable-model-invocation: true`，那是 `d415937e` 在改写描述时一并加上的，**没有遵循任何说得出口的规则**。2026-08-17 刻意没有动它们，而那个理由在当时是对的：当时定下的规则是「reference 是可以被模型调用的」，而这些**一个都没有 `status` 字段**，解除它们等于用一个没有规则的动作，换掉一个没有规则的状态。此后测量：**八个全都有完整的 `Use when:` 触发条件与 `Not for:` 排除条件、八个描述的都是动作而非参考资料、八个都已经有对应的斜线命令**——这正是 `code-review-assistant` 的形状，而它的 `/code-review` 已被裁定不构成保留该标志的理由。`journey-test-assistant` 是现成的先例：同样的「Generate X」形状、`status: stable`、从未被禁用。每一份现在都记上 `status: stable` 并在文件内写明理由。用 `stable` 而非新值，因为 `skills/` 只用 reference、stable、experimental 三个值，**发明第四个等于换了件衣服的同一个无规则动作**。
+- **模型实际选得到的 skill 数,现在是 55/55。** 此前是 45。
+
+### 修正
+
+- **英文来源移除标志后，locale 版仍然照样出货带着它。** `spec-derivation` 是唯一在 locale 包里自带 `disable-model-invocation` 的 skill，而 frontmatter 合并**只复制英文来源「有」的字段**——所以一个英文已经不再声明的字段，会在 locale 文件里原封不动地留下并照样出货。zh-TW 与 zh-CN 均已更正。以解析 **60 个 skill × 3 个 locale ＝ 165 份安装结果**验证：零个仍被禁用。
+
 ## [6.7.4] - 2026-08-18
 
 ### 修正

package/bundled/locales/zh-CN/README.md

@@ -15,7 +15,7 @@ status: current
 
 > **语言**: [English](../../README.md) | [繁體中文](../zh-TW/README.md) | 简体中文
 
-**版本**: 6.7.4 | **发布日期**: 2026-08-18 | **授权**: [双重授权](../../LICENSE) (CC BY 4.0 + MIT)
+**版本**: 6.7.5 | **发布日期**: 2026-08-18 | **授权**: [双重授权](../../LICENSE) (CC BY 4.0 + MIT)
 
 语言无关、框架无关的软件项目文档标准。通过 AI 原生工作流，确保不同技术栈之间的一致性、质量和可维护性。
 

package/bundled/locales/zh-CN/SECURITY.md

@@ -13,7 +13,7 @@ status: current
 <!-- UDS_SUPPORTED_VERSIONS_START -->
 | 版本 | 支持状态 |
 |------|--------|
-| 6.7.4 | ✅ 最新正式版 |
+| 6.7.5 | ✅ 最新正式版 |
 | < 6.0.0 | ❌ 已终止支持 |
 <!-- UDS_SUPPORTED_VERSIONS_END -->
 

package/bundled/locales/zh-CN/skills/spec-derivation/SKILL.md

@@ -15,7 +15,11 @@ description: |
 allowed-tools: Read, Write, Grep, Glob
 argument-hint: "[all|bdd|tdd|it|e2e|atdd] <spec-file>"
 prerequisites: ["spec-approved"]
-disable-model-invocation: true
+# 2026-08-18: `disable-model-invocation: true` 已移除,與英文來源同步。
+# 這一份是唯一在 locale 包裡自帶該旗標的 skill。
+# 英文來源移除它並不會讓這裡消失——frontmatter 合併只併入「英文有的欄位」,
+# 所以一個英文已經沒有的欄位,在 locale 檔裡會原封不動地留下來並照樣出貨。
+# (XSPEC-378 R5)
 ---
 
 # 正向推演

package/bundled/locales/zh-TW/CHANGELOG.md

@@ -1,7 +1,7 @@
 ---
 source: ../../CHANGELOG.md
-source_version: 6.7.4
-translation_version: 6.7.4
+source_version: 6.7.5
+translation_version: 6.7.5
 last_synced: 2026-08-18
 status: current
 ---
@@ -17,6 +17,17 @@ status: current
 
 ## [Unreleased]
 
+## [6.7.5] - 2026-08-18
+
+### 變更
+
+- **八個 skill 重新可以被模型選中。** `audit-assistant`、`changelog-guide`、`commit-standards`、`docs-generator`、`project-discovery`、`release-standards`、`reverse-engineer` 與 `spec-derivation` 都帶著 `disable-model-invocation: true`，那是 `d415937e` 在改寫描述時一併加上的，**沒有依循任何說得出口的規則**。2026-08-17 刻意沒有動它們，而那個理由在當時是對的：當時定下的規則是「reference 是可以被模型叫用的」，而這些**一個都沒有 `status` 欄位**，解除它們等於用一個沒有規則的動作，換掉一個沒有規則的狀態。此後量測：**八個全都有完整的 `Use when:` 觸發條件與 `Not for:` 排除條件、八個描述的都是動作而非參考資料、八個都已經有對應的斜線指令**——這正是 `code-review-assistant` 的形狀，而它的 `/code-review` 已被裁定不構成保留該旗標的理由。`journey-test-assistant` 是現成的先例：同樣的「Generate X」形狀、`status: stable`、從未被禁用。每一份現在都記上 `status: stable` 並在檔內寫明理由。用 `stable` 而非新值，因為 `skills/` 只用 reference、stable、experimental 三個值，**發明第四個等於換了件衣服的同一個無規則動作**。
+- **模型實際選得到的 skill 數,現在是 55/55。** 先前是 45。
+
+### 修正
+
+- **英文來源移除旗標後，locale 版仍然照樣出貨帶著它。** `spec-derivation` 是唯一在 locale 包裡自帶 `disable-model-invocation` 的 skill，而 frontmatter 合併**只複製英文來源「有」的欄位**——所以一個英文已經不再宣告的欄位，會在 locale 檔裡原封不動地留下並照樣出貨。zh-TW 與 zh-CN 均已更正。以解析 **60 個 skill × 3 個 locale ＝ 165 份安裝結果**驗證：零個仍被禁用。
+
 ## [6.7.4] - 2026-08-18
 
 ### 修正

package/bundled/locales/zh-TW/README.md

@@ -15,7 +15,7 @@ status: current
 
 > **語言**: [English](../../README.md) | 繁體中文 | [简体中文](../zh-CN/README.md)
 
-**版本**: 6.7.4 | **發布日期**: 2026-08-18 | **授權**: [雙重授權](../../LICENSE) (CC BY 4.0 + MIT)
+**版本**: 6.7.5 | **發布日期**: 2026-08-18 | **授權**: [雙重授權](../../LICENSE) (CC BY 4.0 + MIT)
 
 語言無關、框架無關的軟體專案文件標準。透過 AI 原生工作流，確保不同技術堆疊之間的一致性、品質和可維護性。
 

package/bundled/locales/zh-TW/SECURITY.md

@@ -13,7 +13,7 @@ status: current
 <!-- UDS_SUPPORTED_VERSIONS_START -->
 | 版本 | 支援狀態 |
 |------|--------|
-| 6.7.4 | ✅ 最新正式版 |
+| 6.7.5 | ✅ 最新正式版 |
 | < 6.0.0 | ❌ 已終止支援 |
 <!-- UDS_SUPPORTED_VERSIONS_END -->
 

package/bundled/locales/zh-TW/skills/spec-derivation/SKILL.md

@@ -13,7 +13,11 @@ description: |
 allowed-tools: Read, Write, Grep, Glob
 argument-hint: "[all|bdd|tdd|it|e2e|atdd] <spec-file>"
 prerequisites: ["spec-approved"]
-disable-model-invocation: true
+# 2026-08-18: `disable-model-invocation: true` 已移除,與英文來源同步。
+# 這一份是唯一在 locale 包裡自帶該旗標的 skill。
+# 英文來源移除它並不會讓這裡消失——frontmatter 合併只併入「英文有的欄位」,
+# 所以一個英文已經沒有的欄位,在 locale 檔裡會原封不動地留下來並照樣出貨。
+# (XSPEC-378 R5)
 ---
 
 # 正向推演

package/bundled/skills/audit-assistant/SKILL.md

@@ -8,7 +8,30 @@ description: |
   Keywords: UDS audit, health check, manifest integrity, standards feedback, friction, 安裝健康, 標準稽核, 回饋.
 allowed-tools: Read, Grep, Glob, Bash(git log, uds audit)
 argument-hint: "[--health | --patterns | --friction | --report]"
-disable-model-invocation: true
+status: stable
+# 2026-08-18: `disable-model-invocation: true` removed, and a status recorded.
+#
+# The flag was applied by d415937e alongside the description rewrite and, like
+# the two lifted on 2026-08-17, followed no stateable rule. These eight were
+# left alone that day for a reason that was correct at the time: the rule
+# settled on was "a reference is model-invocable", and none of them carried a
+# `status` at all, so lifting them would have replaced one unruled state with
+# one unruled action.
+#
+# Measured 2026-08-18, which is what closed it: all eight carry a full
+# `Use when:` trigger and a `Not for:` exclusion, all eight describe an action
+# rather than reference material, and all eight already have a slash command —
+# which is exactly the shape of `code-review-assistant`, whose paired `/code-review`
+# was ruled not to justify the flag. `journey-test-assistant` is the standing
+# precedent: same "Generate X" shape, `status: stable`, never disabled.
+#
+# `stable` rather than a new value: `skills/` uses reference, stable and
+# experimental, and inventing a fourth would be the same unruled-action mistake
+# in different clothing.
+#
+# The cost of being wrong is asymmetric and observable in only one direction.
+# Over-triggering shows up and is undone by deleting a line; a skill that is
+# structurally unable to fire produces no signal at all. (XSPEC-378 R5)
 ---
 
 # Audit Assistant | 審計助手

package/bundled/skills/changelog-guide/SKILL.md

@@ -7,7 +7,30 @@ description: |
   Not for: choosing the next version number or running the release — use /release; writing the commit messages themselves — use /commit.
   Keywords: changelog, CHANGELOG.md, Keep a Changelog, release notes, unreleased, 變更日誌, 發布說明, 版本紀錄.
 allowed-tools: Read, Write, Grep, Bash(git log:*)
-disable-model-invocation: true
+status: stable
+# 2026-08-18: `disable-model-invocation: true` removed, and a status recorded.
+#
+# The flag was applied by d415937e alongside the description rewrite and, like
+# the two lifted on 2026-08-17, followed no stateable rule. These eight were
+# left alone that day for a reason that was correct at the time: the rule
+# settled on was "a reference is model-invocable", and none of them carried a
+# `status` at all, so lifting them would have replaced one unruled state with
+# one unruled action.
+#
+# Measured 2026-08-18, which is what closed it: all eight carry a full
+# `Use when:` trigger and a `Not for:` exclusion, all eight describe an action
+# rather than reference material, and all eight already have a slash command —
+# which is exactly the shape of `code-review-assistant`, whose paired `/code-review`
+# was ruled not to justify the flag. `journey-test-assistant` is the standing
+# precedent: same "Generate X" shape, `status: stable`, never disabled.
+#
+# `stable` rather than a new value: `skills/` uses reference, stable and
+# experimental, and inventing a fourth would be the same unruled-action mistake
+# in different clothing.
+#
+# The cost of being wrong is asymmetric and observable in only one direction.
+# Over-triggering shows up and is undone by deleting a line; a skill that is
+# structurally unable to fire produces no signal at all. (XSPEC-378 R5)
 ---
 
 # Changelog Assistant | 變更日誌助手

package/bundled/skills/commit-standards/SKILL.md

@@ -8,7 +8,30 @@ description: |
   Keywords: commit message, Conventional Commits, feat, fix, refactor, scope, bilingual, 提交訊息, 雙語 commit, 提交規範.
 allowed-tools: Read, Grep, Bash(git status:*), Bash(git diff:*), Bash(git log:*), Bash(git add:*), Bash(git commit:*)
 argument-hint: "[description of changes | 變更描述]"
-disable-model-invocation: true
+status: stable
+# 2026-08-18: `disable-model-invocation: true` removed, and a status recorded.
+#
+# The flag was applied by d415937e alongside the description rewrite and, like
+# the two lifted on 2026-08-17, followed no stateable rule. These eight were
+# left alone that day for a reason that was correct at the time: the rule
+# settled on was "a reference is model-invocable", and none of them carried a
+# `status` at all, so lifting them would have replaced one unruled state with
+# one unruled action.
+#
+# Measured 2026-08-18, which is what closed it: all eight carry a full
+# `Use when:` trigger and a `Not for:` exclusion, all eight describe an action
+# rather than reference material, and all eight already have a slash command —
+# which is exactly the shape of `code-review-assistant`, whose paired `/code-review`
+# was ruled not to justify the flag. `journey-test-assistant` is the standing
+# precedent: same "Generate X" shape, `status: stable`, never disabled.
+#
+# `stable` rather than a new value: `skills/` uses reference, stable and
+# experimental, and inventing a fourth would be the same unruled-action mistake
+# in different clothing.
+#
+# The cost of being wrong is asymmetric and observable in only one direction.
+# Over-triggering shows up and is undone by deleting a line; a skill that is
+# structurally unable to fire produces no signal at all. (XSPEC-378 R5)
 ---
 
 # Commit Message Assistant | Commit Message 助手

package/bundled/skills/docs-generator/SKILL.md

@@ -8,7 +8,30 @@ description: |
   Keywords: docgen, usage docs, cheatsheet, feature reference, generated documentation, 使用文件, 速查表, 文件產生.
 allowed-tools: Read, Write, Grep, Glob, Bash(*)
 argument-hint: "[config file | 設定檔]"
-disable-model-invocation: true
+status: stable
+# 2026-08-18: `disable-model-invocation: true` removed, and a status recorded.
+#
+# The flag was applied by d415937e alongside the description rewrite and, like
+# the two lifted on 2026-08-17, followed no stateable rule. These eight were
+# left alone that day for a reason that was correct at the time: the rule
+# settled on was "a reference is model-invocable", and none of them carried a
+# `status` at all, so lifting them would have replaced one unruled state with
+# one unruled action.
+#
+# Measured 2026-08-18, which is what closed it: all eight carry a full
+# `Use when:` trigger and a `Not for:` exclusion, all eight describe an action
+# rather than reference material, and all eight already have a slash command —
+# which is exactly the shape of `code-review-assistant`, whose paired `/code-review`
+# was ruled not to justify the flag. `journey-test-assistant` is the standing
+# precedent: same "Generate X" shape, `status: stable`, never disabled.
+#
+# `stable` rather than a new value: `skills/` uses reference, stable and
+# experimental, and inventing a fourth would be the same unruled-action mistake
+# in different clothing.
+#
+# The cost of being wrong is asymmetric and observable in only one direction.
+# Over-triggering shows up and is undone by deleting a line; a skill that is
+# structurally unable to fire produces no signal at all. (XSPEC-378 R5)
 ---
 
 # Documentation Generator | 文件產生器

package/bundled/skills/project-discovery/SKILL.md

@@ -8,7 +8,30 @@ description: |
   Keywords: discovery, project assessment, legacy onboarding, risk register, technical debt, 現況評估, 專案盤點, 風險登記簿.
 allowed-tools: Read, Grep, Glob, Bash(npm test:*), Bash(npm audit:*), Bash(npm outdated:*)
 argument-hint: "[feature area | 功能範圍]"
-disable-model-invocation: true
+status: stable
+# 2026-08-18: `disable-model-invocation: true` removed, and a status recorded.
+#
+# The flag was applied by d415937e alongside the description rewrite and, like
+# the two lifted on 2026-08-17, followed no stateable rule. These eight were
+# left alone that day for a reason that was correct at the time: the rule
+# settled on was "a reference is model-invocable", and none of them carried a
+# `status` at all, so lifting them would have replaced one unruled state with
+# one unruled action.
+#
+# Measured 2026-08-18, which is what closed it: all eight carry a full
+# `Use when:` trigger and a `Not for:` exclusion, all eight describe an action
+# rather than reference material, and all eight already have a slash command —
+# which is exactly the shape of `code-review-assistant`, whose paired `/code-review`
+# was ruled not to justify the flag. `journey-test-assistant` is the standing
+# precedent: same "Generate X" shape, `status: stable`, never disabled.
+#
+# `stable` rather than a new value: `skills/` uses reference, stable and
+# experimental, and inventing a fourth would be the same unruled-action mistake
+# in different clothing.
+#
+# The cost of being wrong is asymmetric and observable in only one direction.
+# Over-triggering shows up and is undone by deleting a line; a skill that is
+# structurally unable to fire produces no signal at all. (XSPEC-378 R5)
 ---
 
 # Project Discovery | 專案現況評估

package/bundled/skills/release-standards/SKILL.md

@@ -9,7 +9,30 @@ description: |
 allowed-tools: Read, Write, Grep, Bash(git:*), Bash(npm version:*)
 argument-hint: "[version]"
 prerequisites: ["release-check"]
-disable-model-invocation: true
+status: stable
+# 2026-08-18: `disable-model-invocation: true` removed, and a status recorded.
+#
+# The flag was applied by d415937e alongside the description rewrite and, like
+# the two lifted on 2026-08-17, followed no stateable rule. These eight were
+# left alone that day for a reason that was correct at the time: the rule
+# settled on was "a reference is model-invocable", and none of them carried a
+# `status` at all, so lifting them would have replaced one unruled state with
+# one unruled action.
+#
+# Measured 2026-08-18, which is what closed it: all eight carry a full
+# `Use when:` trigger and a `Not for:` exclusion, all eight describe an action
+# rather than reference material, and all eight already have a slash command —
+# which is exactly the shape of `code-review-assistant`, whose paired `/code-review`
+# was ruled not to justify the flag. `journey-test-assistant` is the standing
+# precedent: same "Generate X" shape, `status: stable`, never disabled.
+#
+# `stable` rather than a new value: `skills/` uses reference, stable and
+# experimental, and inventing a fourth would be the same unruled-action mistake
+# in different clothing.
+#
+# The cost of being wrong is asymmetric and observable in only one direction.
+# Over-triggering shows up and is undone by deleting a line; a skill that is
+# structurally unable to fire produces no signal at all. (XSPEC-378 R5)
 ---
 
 # Release Assistant | 發布助手

package/bundled/skills/reverse-engineer/SKILL.md

@@ -8,7 +8,30 @@ description: |
   Keywords: reverse engineering, system archeology, legacy code, spec extraction, data model, runtime, 反向工程, 系統考古, 規格提取.
 allowed-tools: Read, Grep, Glob, Bash(pg_dump:*), Bash(mysql:*), Bash(sqlite3:*), Bash(npm run:*), Bash(cat:*), Bash(docker:*)
 argument-hint: "[spec|data|runtime|bdd|tdd] <input>"
-disable-model-invocation: true
+status: stable
+# 2026-08-18: `disable-model-invocation: true` removed, and a status recorded.
+#
+# The flag was applied by d415937e alongside the description rewrite and, like
+# the two lifted on 2026-08-17, followed no stateable rule. These eight were
+# left alone that day for a reason that was correct at the time: the rule
+# settled on was "a reference is model-invocable", and none of them carried a
+# `status` at all, so lifting them would have replaced one unruled state with
+# one unruled action.
+#
+# Measured 2026-08-18, which is what closed it: all eight carry a full
+# `Use when:` trigger and a `Not for:` exclusion, all eight describe an action
+# rather than reference material, and all eight already have a slash command —
+# which is exactly the shape of `code-review-assistant`, whose paired `/code-review`
+# was ruled not to justify the flag. `journey-test-assistant` is the standing
+# precedent: same "Generate X" shape, `status: stable`, never disabled.
+#
+# `stable` rather than a new value: `skills/` uses reference, stable and
+# experimental, and inventing a fourth would be the same unruled-action mistake
+# in different clothing.
+#
+# The cost of being wrong is asymmetric and observable in only one direction.
+# Over-triggering shows up and is undone by deleting a line; a skill that is
+# structurally unable to fire produces no signal at all. (XSPEC-378 R5)
 ---
 
 # Reverse Engineering Assistant | 反向工程助手

package/bundled/skills/spec-derivation/SKILL.md

@@ -9,7 +9,30 @@ description: |
 allowed-tools: Read, Write, Grep, Glob
 argument-hint: "[all|bdd|tdd|it|e2e|atdd] <spec-file>"
 prerequisites: ["spec-approved"]
-disable-model-invocation: true
+status: stable
+# 2026-08-18: `disable-model-invocation: true` removed, and a status recorded.
+#
+# The flag was applied by d415937e alongside the description rewrite and, like
+# the two lifted on 2026-08-17, followed no stateable rule. These eight were
+# left alone that day for a reason that was correct at the time: the rule
+# settled on was "a reference is model-invocable", and none of them carried a
+# `status` at all, so lifting them would have replaced one unruled state with
+# one unruled action.
+#
+# Measured 2026-08-18, which is what closed it: all eight carry a full
+# `Use when:` trigger and a `Not for:` exclusion, all eight describe an action
+# rather than reference material, and all eight already have a slash command —
+# which is exactly the shape of `code-review-assistant`, whose paired `/code-review`
+# was ruled not to justify the flag. `journey-test-assistant` is the standing
+# precedent: same "Generate X" shape, `status: stable`, never disabled.
+#
+# `stable` rather than a new value: `skills/` uses reference, stable and
+# experimental, and inventing a fourth would be the same unruled-action mistake
+# in different clothing.
+#
+# The cost of being wrong is asymmetric and observable in only one direction.
+# Over-triggering shows up and is undone by deleting a line; a skill that is
+# structurally unable to fire produces no signal at all. (XSPEC-378 R5)
 ---
 
 # Forward Derivation | 正向推演

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "universal-dev-standards",
-  "version": "6.7.4",
+  "version": "6.7.5",
   "description": "CLI tool for adopting Universal Development Standards",
   "keywords": [
     "documentation",

package/standards-registry.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "version": "6.7.4",
+  "version": "6.7.5",
   "lastUpdated": "2026-05-13",
   "description": "Standards registry for universal-dev-standards with integrated skills and AI-optimized formats",
   "formats": {
@@ -58,14 +58,14 @@
     "standards": {
       "name": "universal-dev-standards",
       "url": "https://github.com/AsiaOstrich/universal-dev-standards",
-      "version": "6.7.4"
+      "version": "6.7.5"
     },
     "skills": {
       "name": "universal-dev-standards",
       "url": "https://github.com/AsiaOstrich/universal-dev-standards",
       "localPath": "skills",
       "rawUrl": "https://raw.githubusercontent.com/AsiaOstrich/universal-dev-standards/main/skills",
-      "version": "6.7.4",
+      "version": "6.7.5",
       "note": "Skills are now included in the main repository under skills/"
     }
   },
@@ -2260,7 +2260,7 @@
       "id": "license-compliance",
       "name": "License Compliance Standards",
       "nameZh": "授權合規標準",
-      "version": "6.7.4",
+      "version": "6.7.5",
       "source": {
         "human": "core/license-compliance.md",
         "ai": "ai/standards/license-compliance.ai.yaml"
@@ -2272,7 +2272,7 @@
       "id": "verification-oracle",
       "name": "Verification Oracle Standards",
       "nameZh": "驗證 Oracle 標準",
-      "version": "6.7.4",
+      "version": "6.7.5",
       "source": {
         "human": "core/verification-oracle.md",
         "ai": "ai/standards/verification-oracle.ai.yaml"
@@ -2284,7 +2284,7 @@
       "id": "model-provenance",
       "name": "Model Provenance Policy Standards",
       "nameZh": "模型來源政策標準",
-      "version": "6.7.4",
+      "version": "6.7.5",
       "source": {
         "human": "core/model-provenance.md",
         "ai": "ai/standards/model-provenance.ai.yaml"
@@ -2296,7 +2296,7 @@
       "id": "resource-cost-boundary",
       "name": "Resource / Cost Boundary Declaration Standards",
       "nameZh": "資源／成本邊界宣告標準",
-      "version": "6.7.4",
+      "version": "6.7.5",
       "source": {
         "human": "core/resource-cost-boundary.md",
         "ai": "ai/standards/resource-cost-boundary.ai.yaml"