@fitlab-ai/agent-infra 0.9.2 → 0.9.4

package/templates/.agents/skills/create-task/reference/context-capture.en.md

@@ -18,6 +18,40 @@ Faithfully condense existing information into task.md under `## Task Input`:
 
 Leave missing categories empty rather than inferring content. Deduplicate repeated information without losing its source or state.
 
+## Observable Acceptance Extraction
+
+The following language-neutral contract is the stable boundary for capturing observable acceptance information:
+
+```text
+# observable-acceptance-contract
+sources: current-request,necessary-prior-discussion
+scan-entire-visible-context: true
+recognize-without-acceptance-label: true
+components: observable-input,action,expected-result
+combine-distributed-evidence: true
+preserve-source-state: true
+missing-components: preserve-as-gaps
+agent-inference-as-confirmed: false
+destination: task-input.acceptance-criteria
+scenario-explicit: capture-supported-components
+scenario-distributed: combine-supported-components
+scenario-insufficient: preserve-supported-components-and-gaps
+```
+
+Execution order:
+
+1. Scan the complete visible context of the current request and necessary prior discussion. Recognize observable information even when the user did not label it as acceptance criteria.
+2. Identify observable inputs, user or system actions, and expected results. These components may be distributed across turns.
+3. Combine supported components that describe the same behavior into a self-contained item, preserving the source and confirmation state of each piece of information.
+4. Preserve unexpressed components as gaps. Do not invent thresholds, scenarios, actions, or results, and do not mark agent inference as user-confirmed information.
+5. Write the items under `## Task Input / ### Acceptance Criteria`. If the context provides no observable criterion, leave that category empty and retain genuine unknowns in the existing categories.
+
+Boundary examples:
+
+- **Single-turn explicit information**: when the current request provides an input, action, and result, capture every supported component and identify the current request as its source.
+- **Distributed information**: when the current request describes an action and necessary prior discussion provides an input or result, combine only components for the same behavior and preserve their source states separately.
+- **Insufficient information**: when the user only says that something "should be faster" without an observable condition or threshold, do not invent a performance target; preserve the stated concern and gaps, leaving the acceptance category empty when no criterion can be formed.
+
 ## Safety and Compression
 
 - Exclude secrets, tokens, credentials, and unrelated personal information.

package/templates/.agents/skills/create-task/reference/context-capture.zh-CN.md

@@ -18,6 +18,40 @@
 
 缺失类别保持为空，不推导补齐。相同信息去重，但不得丢失来源或状态语义。
 
+## 可观察验收提取
+
+以下语言无关契约是可观察验收信息的稳定捕获边界：
+
+```text
+# observable-acceptance-contract
+sources: current-request,necessary-prior-discussion
+scan-entire-visible-context: true
+recognize-without-acceptance-label: true
+components: observable-input,action,expected-result
+combine-distributed-evidence: true
+preserve-source-state: true
+missing-components: preserve-as-gaps
+agent-inference-as-confirmed: false
+destination: task-input.acceptance-criteria
+scenario-explicit: capture-supported-components
+scenario-distributed: combine-supported-components
+scenario-insufficient: preserve-supported-components-and-gaps
+```
+
+执行顺序：
+
+1. 扫描当前请求及必要前序讨论的完整可见上下文；即使用户没有使用“验收标准”标签，也要识别其中的可观察信息。
+2. 找出可观察输入、用户或系统执行的动作以及预期结果。这些组成可以分散在不同轮次。
+3. 将描述同一行为且有上下文证据的组成合并为自足条目，并保留每项信息的来源和确认状态。
+4. 未表达的组成保持为缺口；不得补造阈值、场景、动作或结果，也不得把 Agent 推导标记为用户已确认。
+5. 将条目写入 `## 任务输入 / ### 验收标准`。如果上下文没有提供可观察标准，该分类保持为空，真实的待确认信息继续保留在既有分类中。
+
+边界样例：
+
+- **单轮显式信息**：当前请求同时给出输入、动作和结果时，捕获全部有证据的组成并注明来自当前请求。
+- **跨轮分散信息**：当前请求描述动作、必要前序讨论提供输入或结果时，只合并属于同一行为的组成，并分别保留来源状态。
+- **信息不足**：用户只说“应该更快”但没有可观察条件或阈值时，不得编造性能目标；保留已表达的关注点和缺口，无法形成标准则让验收分类为空。
+
 ## 安全与压缩
 
 - 排除密钥、Token、凭据和与任务无关的个人信息。

package/templates/.agents/skills/import-issue/SKILL.en.md

@@ -6,6 +6,8 @@ description: >
 ---
 
 # Import Issue
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
 
 Import the specified Issue and create a task. Argument: issue number.
 
@@ -145,9 +147,9 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 ### 5. Bind and Sync the Issue
 
 If task.md contains a valid `issue_number`, perform these sync actions (skip and continue on any failure):
-- Run `agent-infra-internal platform-issue bind {task-id} --issue {issue-number} --agent {agent}`
-- Run `agent-infra-internal platform-issue sync {task-id} --agent {agent} --assignees current --milestone initial`
-- After every scenario, run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
+- Run `agent-infra-internal platform-issue bind {task-id} --issue {issue-number} --agent {standard-agent-token}`
+- Run `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --assignees current --milestone initial`
+- After every scenario, run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
 
 ### 6. Verification Gate
 

package/templates/.agents/skills/import-issue/SKILL.zh-CN.md

@@ -6,6 +6,8 @@ description: >
 ---
 
 # 导入 Issue
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
 
 导入指定的 Issue 并创建任务。参数：issue 编号。
 
@@ -145,9 +147,9 @@ date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ### 5. 绑定并同步 Issue
 
 如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（任一失败则跳过并继续）：
-- 调用 `agent-infra-internal platform-issue bind {task-id} --issue {issue-number} --agent {agent}` 校验并原子绑定
-- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {agent} --assignees current --milestone initial`
-- 所有场景结束后，必须调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
+- 调用 `agent-infra-internal platform-issue bind {task-id} --issue {issue-number} --agent {standard-agent-token}` 校验并原子绑定
+- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --assignees current --milestone initial`
+- 所有场景结束后，必须调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
 
 ### 6. 完成校验
 

package/templates/.agents/skills/plan-task/SKILL.en.md

@@ -7,6 +7,9 @@ description: >
 ---
 
 # Design Technical Plan
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
+If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to the completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts.
 
 ## Boundary / Critical Rules
 
@@ -36,7 +39,7 @@ Before the state check is complete, do not make external-state assertions such a
 
 ## Step Start: Write the started Marker
 
-After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} plan.started --agent {agent}` and verify the returned `artifactContext`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} plan.started --agent {standard-agent-token}` and verify the returned `artifactContext`.
 
 ## Steps
 
@@ -110,14 +113,14 @@ Update `.agents/workspace/active/{task-id}/task.md`:
   - Overwrite the `effort` field in frontmatter with the new value
   - Append a `## Effort Re-estimate` section to this round's plan artifact `{plan-artifact}`, recording: `effort {old} → {new} (rationale: {short basis grounded in this plan})`
   If the re-estimated value matches the current value, skip it: do not write the `## Effort Re-estimate` section. The Flow A sync that follows reads the possibly updated frontmatter and propagates the new value to the Issue automatically.
-After the business fields are updated, run `agent-infra-internal task-event {task-id} plan.completed --agent {agent} --artifact {plan-artifact}` so the core atomically records the link, stage, agent, metadata, and Activity Log.
+After the business fields are updated, run `agent-infra-internal task-event {task-id} plan.completed --agent {standard-agent-token} --artifact {plan-artifact} {execution-flag}` so the core atomically records the link, stage, agent, metadata, and Activity Log.
   - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Plan Task (Round {N})** by {agent} — Plan completed, awaiting human review → {artifact-filename}
   ```
 
 If task.md contains a valid `issue_number`, perform these sync actions (skip and continue on any failure):
-- Run `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status pending-design-work --fields`
-- Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
-- Run `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {plan-artifact} --agent {agent}`
+- Run `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status pending-design-work --fields`
+- Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
+- Run `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {plan-artifact} --agent {standard-agent-token}`
 
 ### 8. Verification Gate
 

package/templates/.agents/skills/plan-task/SKILL.zh-CN.md

@@ -7,6 +7,9 @@ description: >
 ---
 
 # 设计技术方案
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
+若入口业务操作数包含 `--orchestrated`，绑定 `{execution-flag}` = `--orchestrated` 并原样转发给 completed 事件；否则绑定为空。不得从 `orchestration.json`、环境变量或历史产物推断该标记。
 
 ## 行为边界 / 关键规则
 
@@ -39,7 +42,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 确认前置条件和轮次后、本轮第一个产出动作之前执行：
 
 ```bash
-agent-infra-internal task-event {task-id} plan.started --agent {agent}
+agent-infra-internal task-event {task-id} plan.started --agent {standard-agent-token}
 ```
 
 ## 执行步骤
@@ -109,12 +112,12 @@ agent-infra-internal task-event {task-id} plan.started --agent {agent}
   - 用新值覆盖 frontmatter 的 `effort` 字段
   - 在本轮方案产物 `{plan-artifact}` 中追加 `## 工作量重估` 段，记录一条：`effort {old} → {new} (rationale: {基于本轮方案的简短依据})`
   若重估值与当前值一致，跳过：不写入 `## 工作量重估` 段。后续 Flow A 同步会读取可能更新过的 frontmatter，并自动把新值同步到 Issue。
-- 完成业务内容更新后执行 `agent-infra-internal task-event {task-id} plan.completed --agent {agent} --artifact {plan-artifact}`，由核心原子登记链接、阶段、代理、时间、版本和 Activity Log。
+- 完成业务内容更新后执行 `agent-infra-internal task-event {task-id} plan.completed --agent {standard-agent-token} --artifact {plan-artifact} {execution-flag}`，由核心原子登记链接、阶段、代理、时间、版本和 Activity Log。
 
 如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（任一失败则跳过并继续）：
-- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status pending-design-work --fields`
-- 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
-- 调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {plan-artifact} --agent {agent}`
+- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status pending-design-work --fields`
+- 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
+- 调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {plan-artifact} --agent {standard-agent-token}`
 
 ### 8. 完成校验
 

package/templates/.agents/skills/post-release/SKILL.en.md

@@ -7,6 +7,8 @@ description: >
 
 # Post-release
 
+Require one explicit canonical SemVer `{version}`. Do not fall back to the latest tag.
+
 ## 1. Inspect Channel Facts
 
 ```bash

package/templates/.agents/skills/post-release/SKILL.zh-CN.md

@@ -7,6 +7,8 @@ description: >
 
 # 发布后处理
 
+要求用户显式提供唯一规范 SemVer `{version}`，不得回退到最新 tag。
+
 ## 1. 检查渠道事实
 
 ```bash

package/templates/.agents/skills/release/SKILL.en.md

@@ -7,36 +7,42 @@ description: >
 
 # Release
 
-Release state is derived from external facts and prepare/publish require separate authorization.
+Prepare, present the latest fact snapshot, and request one remote-publish authorization in a single invocation. External facts remain the source of truth.
 
-## 1. Validate Input and Entropy Report
+## 1. Validate Input and Entropy Checkpoint
 
-Confirm SemVer and the human release checkpoint.
+Require one canonical SemVer `{version}` and a satisfied entropy checkpoint.
 
-## 2. Inspect Facts
+## 2. Prepare and Inspect Facts
 
 ```bash
 agent-infra-internal release-workflow inspect {version}
 ```
 
-## 3. Prepare
+Run prepare and inspect again only when the snapshot is not prepared. Reuse prepared or partially published facts. Unknown state is blocked.
 
 ```bash
 agent-infra-internal release-workflow prepare {version} --entropy-report {path}
 ```
 
-Stop after prepare; never publish implicitly.
+## 3. Present and Confirm
 
-## 4. Publish Separately
+Present the latest snapshot. Only an unambiguous affirmative reply for that snapshot in the current session authorizes publishing. A denial, adjustment, question, ambiguity, interruption, or changed snapshot stops the write and requires a new preview.
 
-Only after explicit user authorization:
+## 4. Publish and Reinspect
 
 ```bash
 agent-infra-internal release-workflow publish {version}
 ```
 
-Push refs normally, preserve partial success for replay, and never force push.
+Push refs normally, preserve partial success for replay, never force push, and inspect again after the operation.
 
 ## 5. Report Facts
 
-Show the snapshot and render next-step client commands through the shared helper. Treat unknown external state as blocked.
+After a complete publish, render the versioned next step without exposing internal actions or skipping directly to post-release:
+
+```bash
+agent-infra-internal agent-client next-steps \
+  --skill create-release-note \
+  --version {version}
+```

package/templates/.agents/skills/release/SKILL.zh-CN.md

@@ -7,36 +7,42 @@ description: >
 
 # 版本发布
 
-发布由事实驱动，并拆为独立授权的 prepare 与 publish。
+在单次调用中准备发布、展示最新事实快照并请求一次远端发布授权。状态由外部事实重建。
 
-## 1. 检查输入与 entropy 报告
+## 1. 验证输入与人工检查点
 
-确认 SemVer 和人工发布检查点已满足。
+验证唯一参数 `{version}` 是规范 SemVer，并确认 entropy 人工检查点已满足。
 
-## 2. 检查事实
+## 2. 准备并检查发布事实
 
 ```bash
 agent-infra-internal release-workflow inspect {version}
 ```
 
-## 3. 准备发布
+未 prepared 时执行 prepare 并重新 inspect；已准备或部分发布时复用当前事实。unknown 必须 blocked。
 
 ```bash
 agent-infra-internal release-workflow prepare {version} --entropy-report {path}
 ```
 
-prepare 后停止，不得隐式 publish。
+## 3. 展示快照并确认
 
-## 4. 独立发布
+展示最新 snapshot。只有当前会话中针对该快照的无歧义明确肯定答复才授权发布；否定、调整、疑问、歧义或中断均停止。快照变化后重新确认。
 
-仅在用户明确授权后执行：
+## 4. 发布并复核
 
 ```bash
 agent-infra-internal release-workflow publish {version}
 ```
 
-逐 ref 普通 push；部分成功可重放，禁止 force push。
+逐 ref 普通 push；部分成功可重放，禁止 force push。操作后重新 inspect。
 
 ## 5. 输出事实摘要
 
-完整展示 snapshot 和后续 TUI 命令；unknown 必须视为 blocked。
+完整发布后渲染携带版本的下一步，不显示内部 action，也不直接跳到 post-release：
+
+```bash
+agent-infra-internal agent-client next-steps \
+  --skill create-release-note \
+  --version {version}
+```

package/templates/.agents/skills/restore-task/SKILL.en.md

@@ -6,6 +6,8 @@ description: >
 ---
 
 # Restore Task
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
 
 Restore local task workspace files from platform Issue comments that contain sync markers.
 
@@ -58,6 +60,7 @@ Rules:
   - `review-plan` / `review-plan-r{N}` -> matching `.md`
   - `code` / `code-r{N}` -> matching `.md`
   - `review-code` / `review-code-r{N}` -> matching `.md`
+  - `pr-review` / `pr-review-r{N}` -> matching `.md`
 
 ### 4. Process Chunks and Check the Local Directory
 
@@ -88,7 +91,7 @@ Write only files that were actually recovered from Issue comments. Do not invent
 ### 6. Apply the Restore Lifecycle Intent
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} restore --agent {agent} \
+agent-infra-internal task-lifecycle {task-id} restore --agent {standard-agent-token} \
   --staging-dir "{staging-dir}" --issue-number {issue-number}
 ```
 

package/templates/.agents/skills/restore-task/SKILL.zh-CN.md

@@ -6,6 +6,8 @@ description: >
 ---
 
 # 还原任务
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
 
 从带有 sync 标记的平台 Issue 评论中恢复本地任务工作区文件。
 
@@ -57,6 +59,7 @@ description: >
   - `review-plan` / `review-plan-r{N}` -> 对应 `.md`
   - `code` / `code-r{N}` -> 对应 `.md`
   - `review-code` / `review-code-r{N}` -> 对应 `.md`
+  - `pr-review` / `pr-review-r{N}` -> 对应 `.md`
 
 ### 4. 处理分片并检查本地目录
 
@@ -87,7 +90,7 @@ description: >
 ### 6. 执行 restore 生命周期意图
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} restore --agent {agent} \
+agent-infra-internal task-lifecycle {task-id} restore --agent {standard-agent-token} \
   --staging-dir "{staging-dir}" --issue-number {issue-number}
 ```
 

package/templates/.agents/skills/review-analysis/SKILL.en.md

@@ -7,6 +7,9 @@ description: >
 ---
 
 # Requirement Analysis Review
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
+If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to both the summary finalizer and completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts.
 
 Review the latest analysis artifact and produce `review-analysis.md` or `review-analysis-r{N}.md`.
 
@@ -35,7 +38,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## Step Start: Declare the started Event
 
-After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-analysis.started --agent {agent}`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-analysis.started --agent {standard-agent-token}`.
 
 ## Steps
 
@@ -66,7 +69,7 @@ Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 
 ### 6. Update Task Status
 
-After the report, submit each new finding with `agent-infra-internal task-ledger {task-id} finding-upsert --stage analysis --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`; submit prior-response dispositions with `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {evidence}`. Do not scan ids or edit ledger rows. After all ledger writes, call `agent-infra-internal task-review {task-id} finalize-summary --stage analysis --artifact {review-artifact}` exactly once.
+After the report, submit each new finding with `agent-infra-internal task-ledger {task-id} finding-upsert --stage analysis --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`; submit prior-response dispositions with `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {evidence}`. Do not scan ids or edit ledger rows. After all ledger writes, call `agent-infra-internal task-review {task-id} finalize-summary --stage analysis --artifact {review-artifact} {execution-flag}` exactly once.
 
 Bind and reuse this structured mapping from that one response:
 
@@ -76,11 +79,11 @@ Bind and reuse this structured mapping from that one response:
 {unresolved-minor} = stageStatus.unresolvedFindingCounts.minor
 ```
 
-The intent atomically finalizes the report summary and returns the same ledger snapshot. Do not call `stage-status`, replace placeholders manually, or rescan the finding list. If finalization fails or a response field is missing, stop before the completion event. Derive the verdict and next-step branch from the same response's `stageStatus.canAdvance`: only `canAdvance=true` permits `approved`; otherwise use `changes-requested` or `rejected`. Then run `agent-infra-internal task-event {task-id} review-analysis.completed --agent {agent} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n}`.
+The intent atomically finalizes the report summary and returns the same ledger snapshot. Do not call `stage-status`, replace placeholders manually, or rescan the finding list. If finalization fails or a response field is missing, stop before the completion event. Derive the verdict and next-step branch from the same response's `stageStatus.canAdvance`: only `canAdvance=true` permits `approved`; otherwise use `changes-requested` or `rejected`. Then run `agent-infra-internal task-event {task-id} review-analysis.completed --agent {standard-agent-token} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`.
 
 `manual-validation` is the data source for the `Manual-validation` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.
 
-If task.md has a valid `issue_number`, run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`, then `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {agent}`.
+If task.md has a valid `issue_number`, run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`, then `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {standard-agent-token}`.
 
 ### 7. Run Completion Gate
 

package/templates/.agents/skills/review-analysis/SKILL.zh-CN.md

@@ -7,6 +7,9 @@ description: >
 ---
 
 # 需求分析审查
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
+若入口业务操作数包含 `--orchestrated`，绑定 `{execution-flag}` = `--orchestrated` 并原样转发给 summary finalizer 与 completed 事件；否则绑定为空。不得从 `orchestration.json`、环境变量或历史产物推断该标记。
 
 审查最新需求分析产物，并产出 `review-analysis.md` 或 `review-analysis-r{N}.md`。
 
@@ -37,7 +40,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## 步骤开始：声明 started 事件
 
-确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-analysis.started --agent {agent}`。
+确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-analysis.started --agent {standard-agent-token}`。
 
 ## 执行步骤
 ### 1. 验证前置条件
@@ -69,7 +72,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ### 6. 更新任务状态
 
-报告完成后，新 finding 逐条调用 `agent-infra-internal task-ledger {task-id} finding-upsert --stage analysis --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`；复核上一轮响应时调用 `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {相称证据}`。不得扫描编号或手写账本行。全部账本写入完成后只调用一次 `agent-infra-internal task-review {task-id} finalize-summary --stage analysis --artifact {review-artifact}`。
+报告完成后，新 finding 逐条调用 `agent-infra-internal task-ledger {task-id} finding-upsert --stage analysis --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`；复核上一轮响应时调用 `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {相称证据}`。不得扫描编号或手写账本行。全部账本写入完成后只调用一次 `agent-infra-internal task-review {task-id} finalize-summary --stage analysis --artifact {review-artifact} {execution-flag}`。
 
 从该次返回值绑定并复用以下结构化映射：
 
@@ -79,11 +82,11 @@ agent-infra-internal task-snapshot {task-id} --format text
 {unresolved-minor} = stageStatus.unresolvedFindingCounts.minor
 ```
 
-该 intent 原子最终化报告摘要并返回同一次账本快照；不得再调用 `stage-status`、手工替换占位符或扫描问题清单。最终化失败或返回字段缺失时，停止在完成事件之前。以同一次返回的 `stageStatus.canAdvance` 决定 verdict 和下一步：仅 `canAdvance=true` 可用 `approved`，否则必须用 `changes-requested` 或 `rejected`。随后执行 `agent-infra-internal task-event {task-id} review-analysis.completed --agent {agent} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n}`。
+该 intent 原子最终化报告摘要并返回同一次账本快照；不得再调用 `stage-status`、手工替换占位符或扫描问题清单。最终化失败或返回字段缺失时，停止在完成事件之前。以同一次返回的 `stageStatus.canAdvance` 决定 verdict 和下一步：仅 `canAdvance=true` 可用 `approved`，否则必须用 `changes-requested` 或 `rejected`。随后执行 `agent-infra-internal task-event {task-id} review-analysis.completed --agent {standard-agent-token} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`。
 
 `manual-validation` 是 `ai task log` 中 review 行「人工校验点」（EN `Manual-validation`）计数的数据源；不要新增并行人工验证字段。
 
-如果 task.md 中存在有效的 `issue_number`，调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`，再调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {agent}`；失败按 `.agents/rules/issue-sync.md` 记录 warning。
+如果 task.md 中存在有效的 `issue_number`，调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`，再调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {standard-agent-token}`；失败按 `.agents/rules/issue-sync.md` 记录 warning。
 
 ### 7. 完成校验
 

package/templates/.agents/skills/review-code/SKILL.en.md

@@ -7,6 +7,9 @@ description: >
 ---
 
 # Code Review
+> `--agent` values follow the "Collaborator Token Specification" in `.agents/rules/task-management.md`: standard AI short tokens (`claude`/`codex`/`antigravity`/`opencode`/`cursor`), long-name normalization (`claude-code`->`claude`, `antigravity-cli`->`antigravity`), or the `human` manual exception.
+
+If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--orchestrated` and forward it unchanged to both the summary finalizer and completed event; otherwise bind it to an empty value. Never infer it from `orchestration.json`, environment variables, or prior artifacts.
 
 Review the latest code round and produce `review-code.md` or `review-code-r{N}.md`.
 
@@ -46,7 +49,7 @@ Before the state check is complete, do not make external-state assertions such a
 
 ## Step Start: Write the started Marker
 
-After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-code.started --agent {agent}`.
+After resolving the artifact context and before this round's first artifact action, run `agent-infra-internal task-event {task-id} review-code.started --agent {standard-agent-token}`.
 
 ## Steps
 
@@ -94,8 +97,8 @@ Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 ### 6. Update Task Status
 
 Update task.md:
-- After the report, submit each new finding with `agent-infra-internal task-ledger {task-id} finding-upsert --stage code --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`; submit prior-response dispositions with `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {evidence}`. Do not scan ids or edit ledger rows
-- After all ledger writes, call `agent-infra-internal task-review {task-id} finalize-summary --stage code --artifact {review-artifact}` exactly once
+- After the report, submit each new finding with `agent-infra-internal task-ledger {task-id} finding-upsert --stage code --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`; submit prior-response dispositions with `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {evidence}`. When escalating to `needs-human-decision`, append `--needs-implementation true|false` using the judgment recorded in the detail block. Do not scan ids or edit ledger rows
+- After all ledger writes, call `agent-infra-internal task-review {task-id} finalize-summary --stage code --artifact {review-artifact} {execution-flag}` exactly once
 
   Bind and reuse this structured mapping from that one response:
 
@@ -107,16 +110,16 @@ Update task.md:
 
   The intent atomically finalizes the report summary and returns the same ledger snapshot. Do not call `stage-status`, replace placeholders manually, or rescan the finding list. If finalization fails or a response field is missing, stop before the completion event. Derive the verdict and next-step branch from the same response's `stageStatus.canAdvance`; only `canAdvance=true` permits Approved
 - Only when `canAdvance=true`, the verdict is Approved, and `T == R^{tree}`, write `last_reviewed_commit: {R}`. Clear an old value for an Approved snapshot with uncommitted differences; otherwise preserve the existing value and do not advance it
-- For an Approved exit, collect PR and required-checks facts as defined in `reference/output-templates.md`: route uncommitted/unpushed code to `commit`, no PR to `create-pr` (except no-PR flow), non-terminal checks to `watch-pr`, and route to `complete-task` only when `HEAD == last_reviewed_commit == PR head` with checks `passed|no-required`; never route by review round alone
-- After handling `last_reviewed_commit`, run `agent-infra-internal task-event {task-id} review-code.completed --agent {agent} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n}`
+- For an Approved exit, collect PR and all-check facts as defined in `reference/output-templates.md`: route uncommitted/unpushed code to `commit`, no PR to `create-pr` (except no-PR flow), non-terminal checks to `watch-pr`, and route to `complete-task` only when `HEAD == last_reviewed_commit == PR head` with checks `passed|no-required`; never route by review round alone
+- After handling `last_reviewed_commit`, run `agent-infra-internal task-event {task-id} review-code.completed --agent {standard-agent-token} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`
 
 Always include the `Manual-validation: {n}` field in the done log, including when it is 0.
 `manual-validation` is the data source for the `Manual-validation` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.
 
 If task.md contains a valid `issue_number`, perform these sync actions (skip and continue on any failure):
-- Run `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status in-progress`
-- Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
-- Run `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {agent}`
+- Run `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status in-progress`
+- Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
+- Run `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {standard-agent-token}`
 
 ### 7. Verification Gate
 

package/templates/.agents/skills/review-code/SKILL.zh-CN.md

@@ -7,6 +7,9 @@ description: >
 ---
 
 # 代码审查
+> `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」：标准 AI 短名（`claude`/`codex`/`antigravity`/`opencode`/`cursor`）、长名归一化（`claude-code`→`claude`、`antigravity-cli`→`antigravity`）或人工例外 `human`。
+
+若入口业务操作数包含 `--orchestrated`，绑定 `{execution-flag}` = `--orchestrated` 并原样转发给 summary finalizer 与 completed 事件；否则绑定为空。不得从 `orchestration.json`、环境变量或历史产物推断该标记。
 
 审查最新代码轮次，并产出 `review-code.md` 或 `review-code-r{N}.md`。
 
@@ -46,7 +49,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ## 步骤开始：声明 started 事件
 
-确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-code.started --agent {agent}`。
+确认前置条件和产物上下文后、本轮第一个产出动作之前执行 `agent-infra-internal task-event {task-id} review-code.started --agent {standard-agent-token}`。
 
 ## 执行步骤
 ### 1. 验证前置条件
@@ -92,8 +95,8 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ### 6. 更新任务状态
 
-- 报告完成后，新 finding 逐条调用 `agent-infra-internal task-ledger {task-id} finding-upsert --stage code --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`；复核上一轮响应时调用 `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {相称证据}`。不得扫描编号或手写账本行
-- 全部账本写入完成后只调用一次 `agent-infra-internal task-review {task-id} finalize-summary --stage code --artifact {review-artifact}`
+- 报告完成后，新 finding 逐条调用 `agent-infra-internal task-ledger {task-id} finding-upsert --stage code --review-artifact {review-artifact} --ordinal {n} --severity {blocker|major|minor} --evidence {review-artifact}#{anchor}`；复核上一轮响应时调用 `finding-review --id {ledger-id} --status {confirmed|closed|open|needs-human-decision} --evidence {相称证据}`。升级为 `needs-human-decision` 时，按详情块中的判断追加 `--needs-implementation true|false`。不得扫描编号或手写账本行
+- 全部账本写入完成后只调用一次 `agent-infra-internal task-review {task-id} finalize-summary --stage code --artifact {review-artifact} {execution-flag}`
 
   从该次返回值绑定并复用以下结构化映射：
 
@@ -105,16 +108,16 @@ agent-infra-internal task-snapshot {task-id} --format text
 
   该 intent 原子最终化报告摘要并返回同一次账本快照；不得再调用 `stage-status`、手工替换占位符或扫描问题清单。最终化失败或返回字段缺失时，停止在完成事件之前。以同一次返回的 `stageStatus.canAdvance` 决定 verdict 和下一步；仅 `canAdvance=true` 可用 Approved
 - 仅当 `canAdvance=true`、本轮结论为 Approved 且 `T == R^{tree}` 时写入 `last_reviewed_commit: {R}`；Approved 快照包含未提交差异时清除旧值。否则保留既有值，不得推进或清空
-- Approved 出口继续按 `reference/output-templates.md` 采集 PR 与 required-checks 事实：未提交/未推送走 `commit`，无 PR 走 `create-pr`（无 PR 流程除外），checks 未终态走 `watch-pr`，仅 `HEAD == last_reviewed_commit == PR head` 且 checks 为 `passed|no-required` 时走 `complete-task`；不得仅按审查轮次分流
-- 完成 `last_reviewed_commit` 处理后执行 `agent-infra-internal task-event {task-id} review-code.completed --agent {agent} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n}`
+- Approved 出口继续按 `reference/output-templates.md` 采集 PR 与全部 checks 事实：未提交/未推送走 `commit`，无 PR 走 `create-pr`（无 PR 流程除外），checks 未终态走 `watch-pr`，仅 `HEAD == last_reviewed_commit == PR head` 且 checks 为 `passed|no-required` 时走 `complete-task`；不得仅按审查轮次分流
+- 完成 `last_reviewed_commit` 处理后执行 `agent-infra-internal task-event {task-id} review-code.completed --agent {standard-agent-token} --artifact {review-artifact} --verdict {approved|changes-requested|rejected} --blockers {unresolved-blockers} --major {unresolved-major} --minor {unresolved-minor} --manual-validation {n} {execution-flag}`
 
 完成日志必须始终写入 `Manual-validation: {n}` 字段，0 也保留。
 `manual-validation` 是 `ai task log` 中 review 行「人工校验点」（EN `Manual-validation`）计数的数据源；不要新增并行人工验证字段。
 
 如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（任一失败则跳过并继续）：
-- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status in-progress`
-- 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
-- 调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {agent}`
+- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status in-progress`
+- 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
+- 调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {review-artifact} --agent {standard-agent-token}`
 
 ### 7. 完成校验
 

package/templates/.agents/skills/review-code/reference/output-templates.en.md

@@ -59,7 +59,7 @@ Next step - create a Pull Request:
 {next-step-commands}
 ```
 
-#### Branch A3: Watch Required Checks
+#### Branch A3: Watch All Checks
 
 Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill watch-pr --task-ref {task-ref}`.
 

package/templates/.agents/skills/review-code/reference/output-templates.zh-CN.md

@@ -59,7 +59,7 @@
 {next-step-commands}
 ```
 
-#### 场景 A3：监控 required checks
+#### 场景 A3：监控全部 checks
 
 使用 `agent-infra-internal agent-client next-steps --skill watch-pr --task-ref {task-ref}` 生成本场景的 `{next-step-commands}`。