@givolt/i3-composer-agent 3.1.0 → 4.0.0

package/evals/cases/i3-ui-demo.json

@@ -17,8 +17,8 @@
     ],
     "negative": [
       {
-        "prompt": "Maintain the approved baseline of an existing i3-ui-prototype candidate",
-        "owner": "i3-ui-prototype"
+        "prompt": "Implement an approved production feature in thin vertical slices",
+        "owner": "i3-incremental-implementation"
       },
       {
         "prompt": "Implement the approved production design as an accessible reusable Vue form component",

package/evals/cases/i3-using-agent-skills.json

@@ -26,7 +26,7 @@
       },
       {
         "prompt": "Generate a reviewable interactive UI prototype from business requirements",
-        "owner": "i3-ui-prototype"
+        "owner": "i3-ui-demo"
       }
     ]
   },
@@ -48,7 +48,7 @@
       "id": 2,
       "kind": "dialogue",
       "prompt": "A user asks for a device-management review prototype from an editable HTML reference and a short business brief. Choose the applicable skill and explain the next step in this session; do not create files or launch a separate task.",
-      "expected_output": "Ordinary routing to i3-ui-prototype in the main session, with operation and scope decided by the working skill",
+      "expected_output": "Ordinary routing to i3-ui-demo in the main session, with operation and scope decided by the working skill",
       "expectations": [
         "The meta-skill selects the prototype workflow for reviewable prototype work",
         "The main session uses the working skill without requiring a dedicated persona, persistent routing rule or parent-child result protocol",
@@ -59,11 +59,11 @@
     {
       "id": 3,
       "kind": "dialogue",
-      "prompt": "Two tasks arrive separately: implement an approved production Vue form component with keyboard support; inspect a review prototype against its approved baseline. Route each task and explain how the existing engineering workflow still applies. Do not perform either task.",
-      "expected_output": "Separate routing for production engineering and prototype review without changing the general lifecycle",
+      "prompt": "Two tasks arrive separately: implement an approved production Vue form component with keyboard support; revise an existing UI demo while preserving its reviewed design. Route each task and explain how the existing engineering workflow still applies. Do not perform either task.",
+      "expected_output": "Separate routing for production engineering and UI demo updates without changing the general lifecycle",
       "expectations": [
         "Production UI implementation follows the engineering workflow with the frontend implementation method",
-        "Prototype fidelity inspection selects the prototype workflow",
+        "Incremental UI demo work selects i3-ui-demo and preserves the reviewed design",
         "The prototype route does not replace generic planning, implementation or review methods or impose prototype-specific delegation on them",
         "The response does not invent runtime verification or human approval"
       ]

package/evals/plugin/simplify-fires-on-pasted-function/graders/behavior-kept-and-explained.md

@@ -0,0 +1,7 @@
+---
+type: llm
+---
+
+PASS if all three hold. (1) The simplified function keeps the original's behavior for strings and arrays: null or undefined input returns an empty array; a string is split on commas; non-string items are converted with String() and kept, so the number 0 survives as "0"; items blank after trimming are dropped; duplicates are removed keeping the first occurrence and its order. (2) The reply is honest about equivalence: either the rewrite returns the original's result for every input, including an iterable with no length such as a Set, for which the original returns an empty array, or the reply names each input where the new version differs. (3) The reply tells the user to run the existing tests, or gives concrete inputs to check, before the function is replaced.
+
+FAIL if any of the five behaviors changes (for example filtering on truthiness before converting to a string, which drops the number 0, or dropping the comma split), or if the reply claims the rewrite behaves the same for every input while silently changing one (for example using Array.from, which reads a Set the original would ignore, without saying so), or if the reply presents the rewrite with no verification step at all.

package/evals/plugin/simplify-fires-on-pasted-function/graders/skill-fired.md

@@ -0,0 +1,5 @@
+---
+type: tool_used
+tool: Skill
+input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(i3-code-simplification|code-simplify)"'
+---

package/evals/plugin/simplify-fires-on-pasted-function/prompt.md

@@ -0,0 +1,30 @@
+---
+description: A simplification request with the function pasted inline and nothing else to read. The skill should fire, and the reply should keep every behavior of the original and say what it removed and why that is safe.
+expected_outcome: A shorter normalizeTags that still returns [] for null or undefined, splits a string on commas, keeps non-string items such as 0, drops blanks and dedups in first-occurrence order, with the removals explained; i3-code-simplification is invoked.
+max_turns: 12
+allowed_tools: [Read, Glob, Grep, Skill]
+---
+
+Simplify this function, it works but it is hard to read.
+
+```js
+function normalizeTags(tags) {
+  var out = [];
+  if (tags === null || tags === undefined) { return out; }
+  if (typeof tags === 'string') { tags = tags.split(','); }
+  for (var i = 0; i < tags.length; i++) {
+    var t = tags[i];
+    if (t === null || t === undefined) { continue; }
+    t = String(t);
+    t = t.replace(/^\s+/, '').replace(/\s+$/, '');
+    t = t.toLowerCase();
+    if (t.length === 0) { continue; }
+    var dup = false;
+    for (var j = 0; j < out.length; j++) {
+      if (out[j] === t) { dup = true; break; }
+    }
+    if (dup === false) { out.push(t); }
+  }
+  return out;
+}
+```

package/evals/plugin/simplify-stays-quiet-on-make-it-fast/graders/not-fired.md

@@ -0,0 +1,8 @@
+---
+type: tool_used
+tool: Skill
+input_match: '"skill"\s*:\s*"(?:[\w-]+:)?(i3-code-simplification|code-simplify)"'
+min: 0
+max: 0
+arm: both
+---

package/evals/plugin/simplify-stays-quiet-on-make-it-fast/prompt.md

@@ -0,0 +1,20 @@
+---
+description: A pasted function with a speed complaint that belongs to i3-performance-optimization. Guards the "even when the code is pasted inline" clause of the i3-code-simplification description, since a request to make pasted code faster must not make the simplification skill fire.
+expected_outcome: A faster lookup (a Set or a Map instead of a linear scan per row); i3-code-simplification is never invoked.
+max_turns: 12
+allowed_tools: [Read, Glob, Grep, Skill]
+---
+
+This takes four seconds on two million rows. How do I make it fast?
+
+```js
+function uniqueCustomers(orders) {
+  const seen = [];
+  for (const order of orders) {
+    if (!seen.includes(order.customerId)) {
+      seen.push(order.customerId);
+    }
+  }
+  return seen;
+}
+```

package/evals/zh-CN/cases/i3-code-simplification.json

@@ -13,6 +13,14 @@
       {
         "prompt": "请简化现有代码结构，保留全部现有行为。",
         "top_k": 1
+      },
+      {
+        "prompt": "这个函数功能正确但难读，请简化下面直接粘贴的代码。",
+        "top_k": 1
+      },
+      {
+        "prompt": "清理这段直接粘贴的工作代码，让它更容易理解。",
+        "top_k": 1
       }
     ],
     "negative": [

package/evals/zh-CN/cases/i3-documentation-and-adrs.json

@@ -13,6 +13,10 @@
       {
         "prompt": "保存这次技术决策的背景与取舍，方便后续工程师理解。",
         "top_k": 1
+      },
+      {
+        "prompt": "我们的 docs 文档已经与代码不一致，请更新。",
+        "top_k": 1
       }
     ],
     "negative": [

package/evals/zh-CN/cases/i3-enterprise-sop.json

@@ -3,58 +3,104 @@
   "trigger": {
     "positive": [
       {
-        "prompt": "显式使用 i3-enterprise-sop，为本次 PBC 的 PRD 和 AD 做路径交接",
-        "top_k": 3
+        "prompt": "显式使用 i3-enterprise-sop，按企业模板准备BRD、PRD、AD和TestCase。",
+        "top_k": 1
       },
       {
-        "prompt": "显式使用 i3-enterprise-sop，以原 Spec 和企业模板起草本主题 AD 后停轮",
-        "top_k": 3
+        "prompt": "使用 i3-enterprise-sop spec，从登记的本PBCBRD、PRD和AD形成工程SPEC。",
+        "top_k": 1
       },
       {
-        "prompt": "显式使用 i3-enterprise-sop，手动传递准确路径，不创建 JSON",
-        "top_k": 3
+        "prompt": "使用 i3-enterprise-sop plan，依据认可的工程SPEC复用原规划技能，交审后停止。",
+        "top_k": 1
       },
       {
-        "prompt": "显式使用i3-enterprise-sop执行plan，只规划本项目选定的任务编排主题，完成后交我审阅",
-        "top_k": 3
+        "prompt": "只读分析 i3-enterprise-sop 文档输入，不写稿或登记。",
+        "top_k": 1
+      },
+      {
+        "prompt": "使用 i3-enterprise-sop，只登记用户明确选定的AD路径，不修改业务稿。",
+        "top_k": 1
       }
     ],
     "negative": [
       {
-        "prompt": "标准流程：编写 SPEC.md，包含目标、命令、工程结构和边界",
+        "prompt": "编写标准SPEC.md，明确目标、命令、工程结构、代码风格、测试策略与边界。",
         "owner": "i3-spec-driven-development"
       },
       {
-        "prompt": "把已选规格拆成依赖有序、带验收和验证的实施任务",
+        "prompt": "把认可的规格拆解为有依赖关系的实施计划和任务。",
         "owner": "i3-planning-and-task-breakdown"
+      },
+      {
+        "prompt": "使用 i3-ui-demo，按企业后台模板和antdV-next制作交互原型。",
+        "owner": "i3-ui-demo"
       }
     ]
   },
   "evals": [
     {
       "id": 1001,
-      "prompt": "读取 brief.md，显式使用 i3-enterprise-sop，只做本次准确路径交接。",
-      "files": [
-        "i3-enterprise-sop"
-      ],
-      "expected_output": "仅登记明确选用路径的三字段清单，或零项目写入的手动输入摘要",
+      "kind": "dialogue",
+      "prompt": "显式使用 i3-enterprise-sop，根据外部BRD准备PRD。BRD没有规定谁能审批申请；请说明如何定位自带PRD模板、调用原方法并处理这个关键缺口，不修改外部BRD。",
+      "expected_output": "A bounded T1 preparation and real clarification stop using the current template and original Spec method",
+      "expectations": [
+        "Uses the current project-selected template first, otherwise its own bundled PRD template; does not require user-supplied internal paths",
+        "Explicitly loads original Spec through the supported host mechanism and obtains its complete method body before substantive work; naming a method or reading a summary is insufficient",
+        "Checks the actual BRD and prior real answers before asking; does not invent approver permissions or treat a default recommendation as a human decision",
+        "Preserves supplied business files and waits for a genuine answer to a critical unresolved choice",
+        "人类可读的追问、说明、进度、报告与生成文档使用简体中文；保留路径、工具参数、JSON协议及机器状态。"
+      ]
+    },
+    {
+      "id": 1002,
+      "kind": "dialogue",
+      "prompt": "显式使用 i3-enterprise-sop spec。清单中BRD和PRD可读但缺少配套AD，请说明下一步，不创建工程SPEC。",
+      "expected_output": "T2 identifies the missing matching AD and stops for the user to generate or provide it",
+      "expectations": [
+        "Reads the selected work and topic rather than choosing the largest version in the directory",
+        "Requires readable and consistently paired BRD PRD AD for T2; optional TestCase and prototype do not become universal prerequisites",
+        "Names the missing AD and corresponding T1 ad operation, then stops without an engineering SPEC or plan",
+        "Does not mutate handoff during this T2 check or silently substitute a different topic",
+        "人类可读的追问、说明、进度、报告与生成文档使用简体中文；保留路径、工具参数、JSON协议及机器状态。"
+      ]
+    },
+    {
+      "id": 1003,
+      "kind": "dialogue",
+      "prompt": "显式使用 i3-enterprise-sop plan，输入是已经认可的工程SPEC；tasks/todo.md还有其他事项的未完任务。请说明怎样复用原规划并保护现有计划，不开始Build。",
+      "expected_output": "T3 explicitly uses original planning, protects the unfinished plan and retains its review gate",
+      "expectations": [
+        "Actually invokes the original planning Skill through the host's supported mechanism and obtains its full method rather than imitating a planner",
+        "Reads the selected engineering SPEC and necessary referenced evidence, not every topic in the project",
+        "Keeps original unfinished-plan protection, tasks/plan.md and a single task target; asks before replacing conflicting unfinished work",
+        "Maps requirements and design constraints into tasks and verification, then stops for human review without Build",
+        "人类可读的追问、说明、进度、报告与生成文档使用简体中文；保留路径、工具参数、JSON协议及机器状态。"
+      ]
+    },
+    {
+      "id": 1004,
+      "kind": "dialogue",
+      "prompt": "显式使用 i3-enterprise-sop 做保存后的自查。长章节写入失败，尚不能确认落盘完整；我只授权目标文档和清单登记，没有授权临时脚本。请说明恢复和汇报，不宣称已经通过。",
+      "expected_output": "Evidence-based recovery at the actual persisted boundary, no extra self-check script files or false approval",
+      "expectations": [
+        "Inspects actual file state and distinguishes no write, partial write and failed receipt after write; resumes only missing or affected parts",
+        "Uses existing read-only tools or in-memory commands for routine self-checks, without writing temporary scripts or enlarging the authorized scope",
+        "Verifies persisted completeness and segment seams without making a full output reread universally mandatory",
+        "Separates structural checks, content self-check, real tool evidence, registration and human approval; retains original failure and stops when the safe boundary cannot be determined",
+        "人类可读的追问、说明、进度、报告与生成文档使用简体中文；保留路径、工具参数、JSON协议及机器状态。"
+      ]
+    },
+    {
+      "id": 1005,
+      "kind": "dialogue",
+      "prompt": "只用 i3-enterprise-sop 分析请求；未授权写稿、建目录、安装或登记。请只读说明T1、T2、T3的关系。",
+      "expected_output": "Read-only explanation without state changes or autonomous next-stage execution",
       "expectations": [
-        "Paths resolve against the confirmed project root and actual documents are read",
-        "A newly generated draft is only reported by path; selected changes only for an explicit user choice and business text is unchanged",
-        "Manual handoff does not create a JSON file or project directories",
-        "Original skills, commands, plans and task state are unchanged",
-        "No business approval, next-stage execution or publication is inferred",
-        "Drafting BRD, PRD, AD or TestCase loads original Spec successfully and preserves its save-and-stop gate",
-        "New business documents default to spec/ per capability; existing adopted paths are retained",
-        "Only the selected topic and necessary shared dependencies become original Plan inputs; original Build auto gates are retained",
-        "Short brd, prd, ad, testcase and plan actions ask only missing facts and do not write while awaiting an answer",
-        "Explicit plan successfully loads original planning Skill and preserves original command obligations and outputs, without JSON writes or Build",
-        "Manual and JSON Plan complete the same indexed shared reads and original command before native planning; scripts do not count as model reads; actual relevant dependency/build configuration is read rather than inferred from AD commands",
-        "AD capability/topic identity or direct-upstream path/PRD-version conflicts stop before native planning and any plan/todo or candidate-plan writes; suspected header typos are not self-resolved",
-        "PRD and AD independent version numbers may differ when the AD references the exact selected PRD version; optional TestCase/prototype do not become universal blockers",
-        "SOP preparation uses Read/Glob/Grep for file discovery instead of probing shell permission with ls/find/mkdir",
-        "The native plan retains full actual source paths and document versions for PRD, AD, adopted norms, contracts and engineering adoption; aliases in the plan or paths only in the conversation report are insufficient",
-        "用简体中文说明实际结果、缺口和未执行事项；保留上述全部工程要求，不推定业务批准、计划批准或发布。"
+        "Keeps T1 enterprise documents, T2 engineering SPEC and T3 original planning as distinct user-started stages",
+        "Does not create spec directories, handoff JSON, business drafts, plans or install tools during read-only analysis",
+        "Preserves human-review stops and does not call approval or a successful registration equivalent to permission for the next stage",
+        "人类可读的追问、说明、进度、报告与生成文档使用简体中文；保留路径、工具参数、JSON协议及机器状态。"
       ]
     }
   ]

package/evals/zh-CN/cases/i3-frontend-ui-engineering.json

@@ -25,8 +25,8 @@
         "owner": "i3-incremental-implementation"
       },
       {
-        "prompt": "选择 UI 原型模板，制作一个可操作的申请审批交互原型供评审。",
-        "owner": "i3-ui-prototype"
+        "prompt": "使用 i3-ui-demo，根据业务文档和内置模板制作 antdv-next 1.6.0 交互原型，必须使用 ui-ux-pro-max。",
+        "owner": "i3-ui-demo"
       }
     ]
   },

package/evals/zh-CN/cases/i3-security-and-hardening.json

@@ -13,6 +13,10 @@
       {
         "prompt": "依赖有 CVE，需要供应链安全审计和加固建议。",
         "top_k": 1
+      },
+      {
+        "prompt": "请补充 auth 认证并轮换会话 Cookie。",
+        "top_k": 1
       }
     ],
     "negative": [

package/evals/zh-CN/cases/i3-ui-demo.json

@@ -17,8 +17,8 @@
     ],
     "negative": [
       {
-        "prompt": "选择 UI 原型模板，制作一个可操作的申请审批交互原型供评审。",
-        "owner": "i3-ui-prototype"
+        "prompt": "按照现有任务计划增量实现 CSV 导出，每个切片都验证。",
+        "owner": "i3-incremental-implementation"
       },
       {
         "prompt": "开发一个响应式前端页面，做好组件布局和无障碍交互。",

package/evals/zh-CN/cases/i3-using-agent-skills.json

@@ -25,8 +25,8 @@
         "owner": "i3-ci-cd-and-automation"
       },
       {
-        "prompt": "选择 UI 原型模板，制作一个可操作的申请审批交互原型供评审。",
-        "owner": "i3-ui-prototype"
+        "prompt": "使用 i3-ui-demo，根据业务文档和内置模板制作 antdv-next 1.6.0 交互原型，必须使用 ui-ux-pro-max。",
+        "owner": "i3-ui-demo"
       }
     ]
   },
@@ -49,7 +49,7 @@
       "id": 1002,
       "kind": "dialogue",
       "prompt": "用户希望根据可编辑 HTML 参考和简短业务说明制作设备管理评审原型。请在当前会话选择适用技能并说明下一步；不创建文件，不启动独立任务。",
-      "expected_output": "Ordinary routing to i3-ui-prototype in the main session, with operation and scope decided by the working skill",
+      "expected_output": "Ordinary routing to i3-ui-demo in the main session, with operation and scope decided by the working skill",
       "expectations": [
         "The meta-skill selects the prototype workflow for reviewable prototype work",
         "The main session uses the working skill without requiring a dedicated persona, persistent routing rule or parent-child result protocol",
@@ -61,11 +61,11 @@
     {
       "id": 1003,
       "kind": "dialogue",
-      "prompt": "分别收到两个任务：实现已认可的生产 Vue 表单组件并支持键盘操作；对照已认可基线检查评审原型。请分别路由并说明原工程工作流如何继续适用，不执行这两个任务。",
-      "expected_output": "Separate routing for production engineering and prototype review without changing the general lifecycle",
+      "prompt": "分别收到两个任务：实现已认可的生产 Vue 表单组件并支持键盘操作；沿用已评审设计修改已有 UI demo。请分别路由并说明原工程工作流如何继续适用，不执行这两个任务。",
+      "expected_output": "Separate routing for production engineering and UI demo updates without changing the general lifecycle",
       "expectations": [
         "Production UI implementation follows the engineering workflow with the frontend implementation method",
-        "Prototype fidelity inspection selects the prototype workflow",
+        "Incremental UI demo work selects i3-ui-demo and preserves the reviewed design",
         "The prototype route does not replace generic planning, implementation or review methods or impose prototype-specific delegation on them",
         "The response does not invent runtime verification or human approval",
         "人类可读的追问、说明、进度、报告与生成文档使用简体中文；保留代码、路径、工具参数、JSON 协议及机器状态的原始格式。"

package/hooks/SDD-CACHE.md

@@ -77,7 +77,7 @@ One cache entry per URL, stored as JSON in `.claude/sdd-cache/<sha>.json`:
 
 - Entry is served only if the origin confirms `304 Not Modified`.
 - Entries without an `ETag` or `Last-Modified` header are never cached — without a validator, the hook cannot verify freshness later, and caching would mean trusting memory.
-- Cache key is `sha256(url)`. The same URL asked with a different prompt hits the same entry; the cached body reflects the prompt used on the first fetch, and that prompt is shown alongside the hit so the agent can decide whether to re-use or re-fetch manually.
+- Cache key is `sha256(url)`. The same URL asked with a different prompt hits the same entry; the cached body reflects the prompt used on the first fetch, and that prompt is shown alongside the hit so the agent can decide whether to reuse or re-fetch manually.
 
 **What the agent sees:**
 

package/package.json

@@ -57,7 +57,6 @@
     "evals/cases/i3-spec-driven-development.json",
     "evals/cases/i3-test-driven-development.json",
     "evals/cases/i3-ui-demo.json",
-    "evals/cases/i3-ui-prototype.json",
     "evals/cases/i3-using-agent-skills.json",
     "evals/fixtures/i3-api-and-interface-design/service-brief.md",
     "evals/fixtures/i3-browser-testing-with-devtools/README.md",
@@ -104,13 +103,6 @@
     "evals/fixtures/i3-test-driven-development/src/split.js",
     "evals/fixtures/i3-test-driven-development/test/split.test.js",
     "evals/fixtures/i3-ui-demo/asset-management.md",
-    "evals/fixtures/i3-ui-prototype/admin-list/assets/reference.css",
-    "evals/fixtures/i3-ui-prototype/admin-list/assets/reference.js",
-    "evals/fixtures/i3-ui-prototype/admin-list/capability-definition.json",
-    "evals/fixtures/i3-ui-prototype/admin-list/index.html",
-    "evals/fixtures/i3-ui-prototype/admin-list/readme.md",
-    "evals/fixtures/i3-ui-prototype/admin-list/template.json",
-    "evals/fixtures/i3-ui-prototype/business-brief.md",
     "evals/fixtures/i3-using-agent-skills/incident.md",
     "evals/fixtures/incremental-implementation-pressure/draft-export.js",
     "evals/fixtures/incremental-implementation-pressure/scenario.md",
@@ -127,6 +119,11 @@
     "evals/plugin/code-review-stays-quiet/graders/not-fired.md",
     "evals/plugin/code-review-stays-quiet/graders/tdd-fired.md",
     "evals/plugin/code-review-stays-quiet/prompt.md",
+    "evals/plugin/simplify-fires-on-pasted-function/graders/behavior-kept-and-explained.md",
+    "evals/plugin/simplify-fires-on-pasted-function/graders/skill-fired.md",
+    "evals/plugin/simplify-fires-on-pasted-function/prompt.md",
+    "evals/plugin/simplify-stays-quiet-on-make-it-fast/graders/not-fired.md",
+    "evals/plugin/simplify-stays-quiet-on-make-it-fast/prompt.md",
     "evals/plugin/tdd-fires-on-pasted-bug/graders/failing-test-first.md",
     "evals/plugin/tdd-fires-on-pasted-bug/graders/skill-fired.md",
     "evals/plugin/tdd-fires-on-pasted-bug/prompt.md",
@@ -159,7 +156,6 @@
     "evals/zh-CN/cases/i3-spec-driven-development.json",
     "evals/zh-CN/cases/i3-test-driven-development.json",
     "evals/zh-CN/cases/i3-ui-demo.json",
-    "evals/zh-CN/cases/i3-ui-prototype.json",
     "evals/zh-CN/cases/i3-using-agent-skills.json",
     "docs/adoption-guide.md",
     "docs/advanced-per-agent-configuration.md",
@@ -178,61 +174,21 @@
     "docs/opencode-setup.md",
     "docs/other-hosts.md",
     "docs/skill-anatomy.md",
-    "docs/upstream-repository/AGENTS.md",
-    "docs/upstream-repository/CLAUDE.md",
-    "docs/upstream-repository/CONTRIBUTING.md",
-    "docs/upstream-repository/README.md",
-    "docs/upstream-repository/gitattributes.txt",
-    "docs/upstream-repository/gitignore.txt",
-    "docs/upstream-repository/manifest.json",
-    "docs/upstream-repository/opencode-skills.link",
-    "docs/upstream-repository/skill-gap.yml",
-    "docs/upstream-repository/skills-contributing.md",
-    "docs/upstream-repository/test-plugin-install.yml",
     "docs/windsurf-setup.md",
     "docs/workbuddy-setup.md",
     "plugin.json",
     "README.md",
     "LICENSE",
-    "scripts/design-provider-discovery-test.js",
-    "scripts/design-provider-test.js",
-    "scripts/enterprise-template-test.js",
     "scripts/floor-guard-reference-test.js",
-    "scripts/lib/prototype-fixture.cjs",
+    "scripts/lib/execution-status.js",
     "scripts/lib/skill-lint-test.js",
     "scripts/lib/skill-lint.js",
-    "scripts/prototype-cache-test.js",
-    "scripts/prototype-generation-entry-test.js",
-    "scripts/prototype-generation-evidence-test.js",
-    "scripts/prototype-generation-native-test.js",
-    "scripts/prototype-generation-test.js",
-    "scripts/prototype-inventory-test.js",
-    "scripts/prototype-locations-test.js",
-    "scripts/prototype-project-test.js",
     "scripts/run-evals-test.js",
     "scripts/run-evals.js",
     "scripts/run-regressions.js",
-    "scripts/template-adapter-test.js",
     "scripts/ui-demo-dependencies-test.js",
     "scripts/ui-demo-mcp-test.js",
     "scripts/ui-demo-test.js",
-    "scripts/ui-prototype-binding-recovery-test.js",
-    "scripts/ui-prototype-buddy-lifecycle-test.js",
-    "scripts/ui-prototype-codebuddy-hook-test.js",
-    "scripts/ui-prototype-content-test.js",
-    "scripts/ui-prototype-dependencies-test.js",
-    "scripts/ui-prototype-devtools-test.js",
-    "scripts/ui-prototype-execution-evidence-test.js",
-    "scripts/ui-prototype-execution-gates-test.js",
-    "scripts/ui-prototype-execution-policy-test.js",
-    "scripts/ui-prototype-execution-runtime-test.js",
-    "scripts/ui-prototype-ide-source-test.js",
-    "scripts/ui-prototype-native-test.js",
-    "scripts/ui-prototype-recovery-test.js",
-    "scripts/ui-prototype-registration-test.js",
-    "scripts/ui-prototype-template-test.js",
-    "scripts/ui-prototype-test.js",
-    "scripts/ui-prototype-transcript-auto-test.js",
     "scripts/validate-artifact-paths-test.js",
     "scripts/validate-artifact-paths.js",
     "scripts/validate-commands-test.js",
@@ -259,7 +215,6 @@
     "claude-code"
   ],
   "i3ComposerAgent": {
-    "prototypeAuditHooks": "retired",
     "pluginFiles": [
       "bin",
       "skills",
@@ -299,7 +254,6 @@
       "evals/cases/i3-spec-driven-development.json",
       "evals/cases/i3-test-driven-development.json",
       "evals/cases/i3-ui-demo.json",
-      "evals/cases/i3-ui-prototype.json",
       "evals/cases/i3-using-agent-skills.json",
       "evals/fixtures/i3-api-and-interface-design/service-brief.md",
       "evals/fixtures/i3-browser-testing-with-devtools/README.md",
@@ -346,13 +300,6 @@
       "evals/fixtures/i3-test-driven-development/src/split.js",
       "evals/fixtures/i3-test-driven-development/test/split.test.js",
       "evals/fixtures/i3-ui-demo/asset-management.md",
-      "evals/fixtures/i3-ui-prototype/admin-list/assets/reference.css",
-      "evals/fixtures/i3-ui-prototype/admin-list/assets/reference.js",
-      "evals/fixtures/i3-ui-prototype/admin-list/capability-definition.json",
-      "evals/fixtures/i3-ui-prototype/admin-list/index.html",
-      "evals/fixtures/i3-ui-prototype/admin-list/readme.md",
-      "evals/fixtures/i3-ui-prototype/admin-list/template.json",
-      "evals/fixtures/i3-ui-prototype/business-brief.md",
       "evals/fixtures/i3-using-agent-skills/incident.md",
       "evals/fixtures/incremental-implementation-pressure/draft-export.js",
       "evals/fixtures/incremental-implementation-pressure/scenario.md",
@@ -369,6 +316,11 @@
       "evals/plugin/code-review-stays-quiet/graders/not-fired.md",
       "evals/plugin/code-review-stays-quiet/graders/tdd-fired.md",
       "evals/plugin/code-review-stays-quiet/prompt.md",
+      "evals/plugin/simplify-fires-on-pasted-function/graders/behavior-kept-and-explained.md",
+      "evals/plugin/simplify-fires-on-pasted-function/graders/skill-fired.md",
+      "evals/plugin/simplify-fires-on-pasted-function/prompt.md",
+      "evals/plugin/simplify-stays-quiet-on-make-it-fast/graders/not-fired.md",
+      "evals/plugin/simplify-stays-quiet-on-make-it-fast/prompt.md",
       "evals/plugin/tdd-fires-on-pasted-bug/graders/failing-test-first.md",
       "evals/plugin/tdd-fires-on-pasted-bug/graders/skill-fired.md",
       "evals/plugin/tdd-fires-on-pasted-bug/prompt.md",
@@ -401,7 +353,6 @@
       "evals/zh-CN/cases/i3-spec-driven-development.json",
       "evals/zh-CN/cases/i3-test-driven-development.json",
       "evals/zh-CN/cases/i3-ui-demo.json",
-      "evals/zh-CN/cases/i3-ui-prototype.json",
       "evals/zh-CN/cases/i3-using-agent-skills.json",
       "docs/adoption-guide.md",
       "docs/advanced-per-agent-configuration.md",
@@ -420,62 +371,22 @@
       "docs/opencode-setup.md",
       "docs/other-hosts.md",
       "docs/skill-anatomy.md",
-      "docs/upstream-repository/AGENTS.md",
-      "docs/upstream-repository/CLAUDE.md",
-      "docs/upstream-repository/CONTRIBUTING.md",
-      "docs/upstream-repository/README.md",
-      "docs/upstream-repository/gitattributes.txt",
-      "docs/upstream-repository/gitignore.txt",
-      "docs/upstream-repository/manifest.json",
-      "docs/upstream-repository/opencode-skills.link",
-      "docs/upstream-repository/skill-gap.yml",
-      "docs/upstream-repository/skills-contributing.md",
-      "docs/upstream-repository/test-plugin-install.yml",
       "docs/windsurf-setup.md",
       "docs/workbuddy-setup.md",
       "plugin.json",
       "package.json",
       "README.md",
       "LICENSE",
-      "scripts/design-provider-discovery-test.js",
-      "scripts/design-provider-test.js",
-      "scripts/enterprise-template-test.js",
       "scripts/floor-guard-reference-test.js",
-      "scripts/lib/prototype-fixture.cjs",
+      "scripts/lib/execution-status.js",
       "scripts/lib/skill-lint-test.js",
       "scripts/lib/skill-lint.js",
-      "scripts/prototype-cache-test.js",
-      "scripts/prototype-generation-entry-test.js",
-      "scripts/prototype-generation-evidence-test.js",
-      "scripts/prototype-generation-native-test.js",
-      "scripts/prototype-generation-test.js",
-      "scripts/prototype-inventory-test.js",
-      "scripts/prototype-locations-test.js",
-      "scripts/prototype-project-test.js",
       "scripts/run-evals-test.js",
       "scripts/run-evals.js",
       "scripts/run-regressions.js",
-      "scripts/template-adapter-test.js",
       "scripts/ui-demo-dependencies-test.js",
       "scripts/ui-demo-mcp-test.js",
       "scripts/ui-demo-test.js",
-      "scripts/ui-prototype-binding-recovery-test.js",
-      "scripts/ui-prototype-buddy-lifecycle-test.js",
-      "scripts/ui-prototype-codebuddy-hook-test.js",
-      "scripts/ui-prototype-content-test.js",
-      "scripts/ui-prototype-dependencies-test.js",
-      "scripts/ui-prototype-devtools-test.js",
-      "scripts/ui-prototype-execution-evidence-test.js",
-      "scripts/ui-prototype-execution-gates-test.js",
-      "scripts/ui-prototype-execution-policy-test.js",
-      "scripts/ui-prototype-execution-runtime-test.js",
-      "scripts/ui-prototype-ide-source-test.js",
-      "scripts/ui-prototype-native-test.js",
-      "scripts/ui-prototype-recovery-test.js",
-      "scripts/ui-prototype-registration-test.js",
-      "scripts/ui-prototype-template-test.js",
-      "scripts/ui-prototype-test.js",
-      "scripts/ui-prototype-transcript-auto-test.js",
       "scripts/validate-artifact-paths-test.js",
       "scripts/validate-artifact-paths.js",
       "scripts/validate-commands-test.js",
@@ -487,7 +398,7 @@
       "scripts/validate-versions.js"
     ]
   },
-  "version": "3.1.0",
+  "version": "4.0.0",
   "repository": {
     "type": "git",
     "url": "https://github.com/49780522/i3-composer-agent.git"

package/plugin.json

@@ -1,7 +1,20 @@
 {
+  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "i3-composer-agent",
-  "version": "3.1.0",
+  "version": "4.0.0",
   "description": "覆盖需求、计划、开发、测试、审查与发布的软件工程技能，默认使用简体中文。",
+  "author": {
+    "name": "Givolt"
+  },
   "homepage": "https://github.com/49780522/i3-composer-agent",
-  "repository": "https://github.com/49780522/i3-composer-agent"
+  "repository": "https://github.com/49780522/i3-composer-agent",
+  "license": "MIT",
+  "keywords": [
+    "skills",
+    "engineering",
+    "spec",
+    "tdd",
+    "review",
+    "ship"
+  ]
 }