@fitlab-ai/agent-infra 0.9.2 → 0.9.4

package/templates/.agents/skills/complete-manual-validation/SKILL.zh-CN.md

@@ -7,6 +7,8 @@ description: >
 ---
 
 # 完成人工验证
+> `--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`。
+
 
 ## 行为边界 / 关键规则
 
@@ -35,7 +37,7 @@ 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} manual-validation.started --agent {agent}`，并以返回的 `artifactContext` 记录本轮身份。
+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} manual-validation.started --agent {standard-agent-token}`，并以返回的 `artifactContext` 记录本轮身份。
 
 ## 执行步骤
 
@@ -83,9 +85,9 @@ complete-manual-validation {task-ref} [{pr-ref}] {verification-summary}
 
 ### 6. 更新 task.md
 
-执行 `agent-infra-internal task-event {task-id} manual-validation.completed --agent {agent} --artifact {manual-validation-artifact} --summary-result "{summary-result}"`，由核心在保持 `current_step` 不变的同时原子登记实现备注链接、时间/版本和完成日志。
+执行 `agent-infra-internal task-event {task-id} manual-validation.completed --agent {standard-agent-token} --artifact {manual-validation-artifact} --summary-result "{summary-result}"`，由核心在保持 `current_step` 不变的同时原子登记实现备注链接、时间/版本和完成日志。
 
-如任务存在有效 `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 {manual-validation-artifact} --agent {agent}`。
+如任务存在有效 `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 {manual-validation-artifact} --agent {standard-agent-token}`。
 
 ### 7. 完成校验
 
@@ -106,7 +108,7 @@ agent-infra-internal task-verify {task-id} manual-validation.completed --artifac
 - 产物路径
 - PR 摘要同步结果
 - 当次完成校验输出
-- 下一步建议：继续 `commit` / `create-pr` 或进入最终审查流程
+- 下一步建议：进入最终收尾流程，运行 /complete-task {task-ref}
 
 渲染最终输出前，先读取 `.agents/rules/next-step-output.md`，并在绝对最后一行追加 `Completed at: YYYY-MM-DD HH:mm:ss`。
 

package/templates/.agents/skills/complete-manual-validation/reference/summary-update.en.md

@@ -10,7 +10,7 @@ Follow `.agents/rules/pr-sync.md` for the shared summary structure and failure s
 
 ```bash
 agent-infra-internal platform-pr summary-sync {task-id} \
-  --agent {agent} --body-file {summary-body-file}
+  --agent {standard-agent-token} --body-file {summary-body-file}
 ```
 
 The core owns marker/HEAD wrapping, pagination, and in-place reconciliation. If context says no manual validation is required, stop without marking it passed.

package/templates/.agents/skills/complete-manual-validation/reference/summary-update.zh-CN.md

@@ -10,7 +10,7 @@
 
 ```bash
 agent-infra-internal platform-pr summary-sync {task-id} \
-  --agent {agent} --body-file {summary-body-file}
+  --agent {standard-agent-token} --body-file {summary-body-file}
 ```
 
 marker、当前 HEAD、分页查找和原地更新由 core 负责。若当前 context 表明无需人工校验，则停止并返回 `summary failed: no manual validation required`，不误标通过。

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

@@ -7,11 +7,14 @@ description: >
 ---
 
 # Complete 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.
+
 
 ## Boundary / Critical Rules
 
 - This command updates task metadata AND physically moves the task directory
 - Do not move a task that has incomplete workflow steps unless forced
+- The entry point accepts optional `--external-pr <N>` only to select among ambiguous external-delivery candidates; it never bypasses identity or platform gates
 
 Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
 
@@ -54,6 +57,16 @@ Scenario A is the normal active-task path. Scenario B `finalization-retry` retri
 
 ### 2. Verify Completion Prerequisites (Failure Must Stop)
 
+Read `reference/external-delivery.md`, then run for the active task:
+
+```bash
+agent-infra-internal platform-pr resolve-external {task-id} --agent {standard-agent-token} [--pr {external-pr}]
+```
+
+- `mode=external`: only this invocation's typed `authorization` and `selected` fields authorize and identify external delivery; continue through every existing hard gate below.
+- `mode=normal`: use the existing local lifecycle prerequisites; historical `pr_number` / `pr_status` values do not authorize external delivery.
+- `status=failed|blocked`: stop immediately and show the stable error; `--force` cannot bypass it.
+
 **Gate read (project-level PR flow policy)**: Before running this step, read `.agents/.airc.json`'s `prFlow` field (three states: field absent = recommend PR by default, skipping allowed; `"required"` = PR mandatory; `"disabled"` = no PR flow), and `pr_status` from `task.md` frontmatter (`pending` / `created` / `skipped`).
 
 **PR dimension decision (evaluate the `prFlow` strong constraint FIRST, then `pr_status`)**:
@@ -88,6 +101,7 @@ Before marking complete, verify ALL of these:
 - [ ] Code has been committed (no uncommitted changes related to this task)
 - [ ] Tests are passing
 - [ ] The disagreement ledger has no unclosed disagreements or un-re-reviewed post-review commits; on a bound-PR path local HEAD, `last_reviewed_commit`, and PR head either match strictly, or a merged squash has complete platform snapshot and remote Git equivalence evidence and current Git credentials can read the evidence refs; without a valid PR, a single-parent local rewrite is content-equivalent to `last_reviewed_commit` and has no later protected commits
+- [ ] Manual validation items are complete (when the latest review-code's Manual validation count is > 0, a passed manual-validation artifact and its completion record must exist, and that completion record must sit after the latest review-code; skipped when the count is 0 or there are no pending items)
 
 > **⚠️ Prerequisite Branch Check — you must decide whether to continue or stop before proceeding:**
 >
@@ -124,9 +138,9 @@ Check whether task.md has a valid `issue_number`. If it does not, skip this step
 
 When an `issue_number` exists, execute in this exact order:
 
-1. In artifact-catalog order, run `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {artifact} --agent {artifact-agent} --backfill` for every local artifact.
-2. Run `agent-infra-internal platform-issue sync {task-id} --agent {agent} --requirements --fields`.
-3. Write the business summary to a temporary file and run `agent-infra-internal platform-comment sync {task-id} --kind summary --body-file {path} --agent {agent}`.
+1. Run `agent-infra-internal platform-comment backfill {task-id} --agent {standard-agent-token}` so core publishes only the completion canonical inventory in fixed order and resolves matching historical warnings only after full success.
+2. Run `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --requirements --fields`.
+3. Write the business summary to a temporary file and run `agent-infra-internal platform-comment sync {task-id} --kind summary --body-file {path} --agent {standard-agent-token}`.
 
 Do not sync the task comment here; it requires the terminal task.md written by lifecycle. Do not set a `status:` label; platform automation clears status labels after the Issue closes.
 
@@ -146,14 +160,14 @@ After platform writes succeed and before moving the directory or releasing the s
 agent-infra-internal task-verify {task-id} complete-task.preflight --format text
 ```
 
-This event runs `review-ledger`, `post-review-commit`, then `platform-sync-preflight`. On any non-zero exit (fail/blocked), keep the task active, derive the stable code/target from the gate result, record it through `task-warning ... add --step complete-task ...`, and stop. For a review/head mismatch, rerun `commit` or `review-code`; never fall back to the review baseline.
+This event runs `review-ledger`, `manual-validation`, `post-review-commit`, then `platform-sync-preflight`. On any non-zero exit (fail/blocked), keep the task active, derive the stable code/target from the gate result, record it through `task-warning ... add --step complete-task ...`, and stop. For a review/head mismatch, rerun `commit` or `review-code`; never fall back to the review baseline.
 
-`--force` does not lift this hard gate: close ledger disagreements; re-review or exempt post-review commits, use the platform adapter's authoritative snapshot and remote refs for the bound change request (PR/MR) to prove a content-equivalent single-parent squash merge in an isolated temporary repository, or, without a valid change request, prove from local Git objects that the only protected commit is a content-equivalent single-parent rewrite with no later protected commits; then pass platform preflight. An unsupported adapter capability, missing required platform facts, Git objects, topology, or content evidence, or current Git credentials that cannot read the remote evidence refs fails closed. The platform adapter supplies normalized required-checks state, which remains enforced before merge by branch protection / rulesets and the `review-code` / `watch-pr` routes.
+`--force` does not lift this hard gate: close ledger disagreements; re-review or exempt post-review commits, use the platform adapter's authoritative snapshot and remote refs for the bound change request (PR/MR) to prove a content-equivalent single-parent squash merge in an isolated temporary repository, or, without a valid change request, prove from local Git objects that the only protected commit is a content-equivalent single-parent rewrite with no later protected commits; then pass platform preflight. An unsupported adapter capability, missing required platform facts, Git objects, topology, or content evidence, or current Git credentials that cannot read the remote evidence refs fails closed. The platform adapter supplies normalized state for all checks, enforced before merge by the `review-code` / `watch-pr` routes; required checks remain additionally enforced by branch protection / rulesets.
 
 ### 6. Apply the Local Lifecycle Intent and Verify the Move
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} complete --agent {agent}
+agent-infra-internal task-lifecycle {task-id} complete --agent {standard-agent-token}
 ```
 
 Only `status=applied|no-op` means local completion succeeded. On `status=failed`, show the structured error and recovery steps and retry the same intent; do not claim completion or hand-repair partial state.
@@ -169,7 +183,7 @@ Confirm the task directory was successfully moved.
 Both Scenario A and Scenario B `finalization-retry` execute this step from the completed directory. If a valid `issue_number` exists, first run:
 
 ```bash
-agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}
+agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}
 ```
 
 If this call fails, the task is already archived and `task-warning` cannot accept it. Keep the task completed and stop. After fixing the network or platform issue, rerun complete-task; Step 1 will enter `finalization-retry` and repeat only this step.
@@ -232,6 +246,7 @@ Completed at: {completion-time}
    - Code is committed but not reviewed
    - Review found blockers that haven't been fixed
    - PR is created but not merged
+   - Manual validation items are incomplete
 
 2. **Rollback**: If a task was incorrectly moved:
    ```bash

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

@@ -7,11 +7,14 @@ description: >
 ---
 
 # 完成任务
+> `--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`。
+
 
 ## 行为边界 / 关键规则
 
 - 本命令更新任务元数据并物理移动任务目录
 - 除非强制执行，不要转移有未完成工作流步骤的任务
+- 入口接受可选 `--external-pr <N>`；仅用于外部交付候选歧义时的显式选择，不绕过身份或平台门禁
 
 版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
 
@@ -53,6 +56,16 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ### 2. 验证完成前置条件（未满足则必须停止）
 
+先读取 `reference/external-delivery.md`，然后在 active 任务上调用：
+
+```bash
+agent-infra-internal platform-pr resolve-external {task-id} --agent {standard-agent-token} [--pr {external-pr}]
+```
+
+- `mode=external`：只以本次 typed result 的 `authorization` 和 `selected` 作为外部交付授权与绑定身份，继续本步骤的既有硬门禁。
+- `mode=normal`：走现有本地生命周期前置条件；历史 `pr_number` / `pr_status` 不构成外部授权。
+- `status=failed|blocked`：立即停止并展示稳定错误；`--force` 不得绕过。
+
 **门控读取（项目级 PR 流程策略）**：在执行本步骤前，读取 `.agents/.airc.json` 的 `prFlow` 字段（三态：字段缺省 = 默认推荐 PR、允许跳过；`"required"` = 强制 PR；`"disabled"` = 强制无 PR），以及 `task.md` frontmatter 的 `pr_status`（`pending` / `created` / `skipped`）。
 
 **PR 维度判定（先判 `prFlow` 强约束，后看 `pr_status`）**：
@@ -87,6 +100,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 - [ ] 代码已提交（没有与此任务相关的未提交变更）
 - [ ] 测试通过
 - [ ] 审查分歧账本无未关闭分歧、无未复审的 post-review 提交；绑定 PR 路径中本地 HEAD、`last_reviewed_commit`、PR head 严格一致，或已合并 squash 的平台快照与远端 Git 等价证据完整且当前 Git 凭据可读取证据 refs；无有效 PR 路径中本地单父重写与 `last_reviewed_commit` 内容等价且之后无受保护提交
+- [ ] 人工校验项已完成（最新 review-code 的 Manual validation 计数 > 0 时，须存在通过校验的 manual-validation 产物及其完成记录，且该完成记录位于最新 review-code 之后；计数为 0 或无未决项时跳过）
 
 > **⚠️ 前置条件分支判断 — 你必须先判断“继续”还是“停止”：**
 >
@@ -123,9 +137,9 @@ Please complete the missing steps first, or use --force to override.
 
 如果存在有效的 `issue_number`，严格按以下顺序执行：
 
-1. 按 artifact catalog 顺序，对本地已有产物逐项调用 `agent-infra-internal platform-comment sync {task-id} --kind artifact --artifact {artifact} --agent {artifact-agent} --backfill`。
-2. 调用 `agent-infra-internal platform-issue sync {task-id} --agent {agent} --requirements --fields`。
-3. 把业务摘要写入临时文件，并调用 `agent-infra-internal platform-comment sync {task-id} --kind summary --body-file {path} --agent {agent}`。
+1. 调用 `agent-infra-internal platform-comment backfill {task-id} --agent {standard-agent-token}`，由 core 仅按 completion canonical inventory 固定顺序补发产物并在全部成功后精确恢复目标历史告警。
+2. 调用 `agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --requirements --fields`。
+3. 把业务摘要写入临时文件，并调用 `agent-infra-internal platform-comment sync {task-id} --kind summary --body-file {path} --agent {standard-agent-token}`。
 
 不要在本步骤同步 task 评论；它依赖 lifecycle 写入后的完整终态 task.md。不要设置 `status:` label，平台自动化应在 Issue 关闭后清理状态标签。
 
@@ -145,14 +159,14 @@ agent-infra-internal task-warning {task-id} add --step complete-task --severity
 agent-infra-internal task-verify {task-id} complete-task.preflight --format text
 ```
 
-该事件依次执行 `review-ledger`、`post-review-commit`、`platform-sync-preflight`。任一退出码非 0（fail/blocked）时，任务必须继续留在 active；从 gate 结果取稳定 code/target，通过 `task-warning ... add --step complete-task ...` 落账后停止。若审查基线或 head 不一致，必须先重新 `commit` / `review-code`；不得回退审查基线。
+该事件依次执行 `review-ledger`、`manual-validation`、`post-review-commit`、`platform-sync-preflight`。任一退出码非 0（fail/blocked）时，任务必须继续留在 active；从 gate 结果取稳定 code/target，通过 `task-warning ... add --step complete-task ...` 落账后停止。若审查基线或 head 不一致，必须先重新 `commit` / `review-code`；不得回退审查基线。
 
-`--force` 不解除本硬门禁：未关闭分歧必须先在账本闭合，未复审提交必须重新审查、具备有效豁免，或由平台适配器为绑定的变更请求（PR/MR）提供权威合并快照与远端 refs，并在隔离临时仓库中证明单父 squash merge 等价，或在无有效变更请求时由本地 Git 对象证明唯一受保护提交是内容等价的单父重写且之后无受保护提交；平台 preflight 必须通过。适配器不支持所需能力，平台事实、Git 对象、拓扑、内容证据缺失，或当前 Git 凭据不能读取远端证据 refs 时 fail closed。required checks 由平台适配器提供规范化状态，并在合并前通过分支保护 / ruleset 以及 `review-code` / `watch-pr` 路由承担。
+`--force` 不解除本硬门禁：未关闭分歧必须先在账本闭合，未复审提交必须重新审查、具备有效豁免，或由平台适配器为绑定的变更请求（PR/MR）提供权威合并快照与远端 refs，并在隔离临时仓库中证明单父 squash merge 等价，或在无有效变更请求时由本地 Git 对象证明唯一受保护提交是内容等价的单父重写且之后无受保护提交；平台 preflight 必须通过。适配器不支持所需能力，平台事实、Git 对象、拓扑、内容证据缺失，或当前 Git 凭据不能读取远端证据 refs 时 fail closed。全部 checks 由平台适配器提供规范化状态，并在合并前通过 `review-code` / `watch-pr` 路由承担；其中 required checks 仍受分支保护 / ruleset 强制。
 
 ### 6. 执行本地生命周期意图并验证转移
 
 ```bash
-agent-infra-internal task-lifecycle {task-id} complete --agent {agent}
+agent-infra-internal task-lifecycle {task-id} complete --agent {standard-agent-token}
 ```
 
 仅 `status=applied|no-op` 视为本地完成。`status=failed` 时展示 `error` 与 completed/pending steps，以同一 intent 重试；不得宣称完成或手工补写局部状态。
@@ -168,7 +182,7 @@ ls .agents/workspace/completed/{task-id}/task.md
 场景 A 与场景 B `finalization-retry` 都从 completed 目录执行本步骤。若存在有效的 `issue_number`，先调用：
 
 ```bash
-agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}
+agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}
 ```
 
 该调用失败时任务已归档，不能调用只接受 active 任务的 `task-warning`；保留 completed 状态并停止。修复网络或平台问题后重跑 complete-task，会由步骤 1 进入 `finalization-retry`，只重复本步骤。
@@ -231,6 +245,7 @@ Completed at: {completion-time}
    - 代码已提交但未审查
    - 审查发现阻塞项但未修复
    - PR 已创建但未合并
+   - 人工校验项未完成
 
 2. **回滚**：如果任务被错误转移：
    ```bash

package/templates/.agents/skills/complete-task/config/verify.en.json

@@ -25,6 +25,7 @@
       "require_all_checked": true
     },
     "review-ledger": {},
+    "manual-validation": {},
     "post-review-commit": {},
     "platform-sync-preflight": {
       "when": "issue_number_exists",

package/templates/.agents/skills/complete-task/config/verify.zh-CN.json

@@ -25,6 +25,7 @@
       "require_all_checked": true
     },
     "review-ledger": {},
+    "manual-validation": {},
     "post-review-commit": {},
     "platform-sync-preflight": {
       "when": "issue_number_exists",

package/templates/.agents/skills/complete-task/reference/external-delivery.en.md

@@ -0,0 +1,17 @@
+# External PR Delivery
+
+This scenario applies only to an active task whose completion canonical inventory is empty because an already-merged external PR delivered the implementation.
+
+## Typed State Machine
+
+Run `agent-infra-internal platform-pr resolve-external {task-id} --agent {agent} [--pr {N}]`. Core checks the completion inventory first. A non-empty inventory returns `mode=normal`, and supplying `--pr` then fails. An empty inventory requires a positive `issue_number`; otherwise core returns `EXTERNAL_DELIVERY_ISSUE_REQUIRED`.
+
+The platform adapter supplies authoritative Issue closing change requests across all pages. Only candidates with a matching base repository, complete identity, and merge evidence are eligible. One candidate is selected automatically; ambiguity, conflicts, and missing evidence fail closed. `--pr` may only select an authoritative eligible closing candidate and cannot bypass repository, Issue, merge, or identity validation.
+
+## Authorization and Persistent Audit
+
+Only the current typed result's `mode=external`, `authorization`, and `selected` fields control the machine branch. `pr_status: created` is a compatibility shim for existing verifiers: it means a verifiable PR is bound, not that this task created it, and it cannot authorize lifecycle skipping by itself.
+
+A successful bind atomically writes PR fields and appends a `Bind External PR` Activity Log entry containing the authorization source, Issue, PR URL/number, base/head repository/ref/SHA, merge time, and merge commit. Replaying identical complete evidence is a no-op; an existing same-number binding without the signature adds it once; number or identity changes fail. The PR create path must never run.
+
+External mode still passes review-ledger, manual-validation, post-review-commit, platform-sync, preflight, and terminal gates. Without a canonical review-code artifact, only existing verifier N/A rules apply. `--force` does not disable any hard gate.

package/templates/.agents/skills/complete-task/reference/external-delivery.zh-CN.md

@@ -0,0 +1,17 @@
+# 外部 PR 交付
+
+本场景只适用于 completion canonical inventory 为空、实现实际由已合并的外部 PR 交付的 active 任务。
+
+## Typed 状态机
+
+调用 `agent-infra-internal platform-pr resolve-external {task-id} --agent {agent} [--pr {N}]`。core 先检查 completion inventory；非空时返回 `mode=normal`，且显式 `--pr` 会失败。空 inventory 必须有正整数 `issue_number`，否则返回 `EXTERNAL_DELIVERY_ISSUE_REQUIRED`。
+
+core 通过平台 adapter 读取 Issue 的权威 closing change requests，穷尽分页后只把 base 仓库匹配任务仓库且已经合并、身份字段完整的候选视为 eligible。唯一候选自动选择；多候选、身份冲突或证据缺失均 fail closed。`--pr` 只能从权威 closing eligible 集合中显式选择，不能绕过仓库、Issue、合并或身份校验。
+
+## 授权与持久审计
+
+当次调用只以 typed result 的 `mode=external`、`authorization` 和 `selected` 为机器分支依据。`pr_status: created` 只是现有 verifier 的兼容 shim，表示任务已绑定可验证的 PR；它既不表示 PR 由本任务创建，也不能单独授权跳过 lifecycle。
+
+成功绑定会原子写入 PR 字段并追加 `Bind External PR` Activity Log，记录授权来源、Issue、PR URL/编号、base/head repository/ref/SHA、合并时间和 merge commit。相同完整证据重试为 no-op；已有同号但缺审计签名时补写一次；编号或身份变化失败。不得调用 PR create 路径。
+
+外部模式仍须通过 review ledger、manual validation、post-review commit、平台同步、preflight 与终态校验。无 canonical review-code 时仅沿用 verifier 已定义的 N/A 规则；`--force` 不解除任何硬门禁。

package/templates/.agents/skills/create-pr/SKILL.en.md

@@ -6,6 +6,8 @@ description: >
 ---
 
 # Create Pull Request
+> `--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.
+
 
 Create a Pull Request and, when task-related, sync the essential metadata and reviewer summary immediately.
 
@@ -66,13 +68,13 @@ Use `agent-infra-internal git-workflow inspect` for upstream/remote facts and `g
 
 ### 5. Create or Recover the PR
 
-Read `.agents/rules/issue-pr-commands.md`, write the title and body to temporary files, then invoke its `platform-pr create` intent. The core first performs exact head/base lookup: one existing PR is reused and bound, zero creates, and multiple matches fail deterministically. Replays must not create duplicate PRs.
+Read `.agents/rules/issue-pr-commands.md`, write the title and body to temporary files, then invoke its `platform-pr create` intent. Under the task lock and before any Create PR started entry, POST, or reuse-bind, core checks commit finalization. An active intent, open Commit, missing review anchor, or tree drift returns a stable code and directs the caller to rerun commit/review-code; create-pr never repairs Commit state. Only after the gate passes does core perform exact head/base lookup: one existing PR is reused and bound, zero creates, and multiple matches fail deterministically. Replays must not create duplicate PRs.
 
 If `{task-id}` is available and the related task provides `issue_number`, keep `Closes #{issue-number}` in the PR body.
 
 ### 6. Sync PR Metadata
 
-Run `agent-infra-internal platform-pr sync {task-id} --agent {agent} --metadata --closing-issue`. The core copies type / `in:` labels, assignee, and a specific milestone from the Issue and maintains the closing association. Permission-bound items degrade independently, and the Issue is never updated in reverse.
+Run `agent-infra-internal platform-pr sync {task-id} --agent {standard-agent-token} --metadata --closing-issue`. The core copies type / `in:` labels, assignee, and a specific milestone from the Issue and maintains the closing association. Permission-bound items degrade independently, and the Issue is never updated in reverse.
 
 ### 7. Publish the Review Summary
 
@@ -112,11 +114,11 @@ Explain the created PR URL, summarize metadata sync and summary-comment results,
 Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill watch-pr --task-ref {task-ref}`.
 
 ```
-Next step - Watch PR checks (auto self-heal until required checks are green):
+Next step - Watch PR checks (auto self-heal until all checks are green):
 {next-step-commands}
 ```
 
-Alternatively, to skip active monitoring and attempt completion immediately, use `complete-task`; its required-checks hard gate still fails closed for pending/failed checks or head mismatch:
+Alternatively, to skip active monitoring and attempt completion immediately, use `complete-task`; its all-checks hard gate still fails closed for pending/failed checks or head mismatch:
 
 Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill complete-task --task-ref {task-ref}`.
 
@@ -125,7 +127,7 @@ Next step (alternative) - Skip active monitoring and attempt completion:
 {next-step-commands}
 ```
 
-`watch-pr` is the primary path. The alternative `complete-task` block skips active polling only; it never skips required checks and does not guarantee immediate archival.
+`watch-pr` is the primary path. The alternative `complete-task` block skips active polling only; it never skips the full check set and does not guarantee immediate archival.
 
 ## Notes
 

package/templates/.agents/skills/create-pr/SKILL.zh-CN.md

@@ -6,6 +6,8 @@ description: >
 ---
 
 # 创建 Pull Request
+> `--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`。
+
 
 创建 Pull Request，并在与任务关联时立即补齐核心元数据和 reviewer 摘要。
 
@@ -66,13 +68,13 @@ description: >
 
 ### 5. 创建或恢复 PR
 
-执行前先读取 `.agents/rules/issue-pr-commands.md`，把标题和正文写入临时文件，并调用其中的 `platform-pr create` intent。core 先按 head/base 精确定位：唯一既有 PR 会复用并绑定，零个才创建，多个稳定失败；重放不得产生重复 PR。
+执行前先读取 `.agents/rules/issue-pr-commands.md`，把标题和正文写入临时文件，并调用其中的 `platform-pr create` intent。core 在任务锁内、任何 Create PR started / POST / reuse-bind 之前检查 commit finalization；active intent、open Commit、审查锚点缺失或 tree 漂移时返回稳定 code 并指向重跑 commit/review-code，不自动恢复。门禁通过后才按 head/base 精确定位：唯一既有 PR 会复用并绑定，零个才创建，多个稳定失败；重放不得产生重复 PR。
 
 如果获取到 `{task-id}` 且对应任务提供了 `issue_number`，必须在 PR 正文中保留 `Closes #{issue-number}`。
 
 ### 6. 同步 PR 元数据
 
-调用 `agent-infra-internal platform-pr sync {task-id} --agent {agent} --metadata --closing-issue`。core 从 Issue 复制 type / `in:` labels、assignee 和具体 milestone，并维护 Development 关联；逐项权限不足返回 degraded，不反向更新 Issue。
+调用 `agent-infra-internal platform-pr sync {task-id} --agent {standard-agent-token} --metadata --closing-issue`。core 从 Issue 复制 type / `in:` labels、assignee 和具体 milestone，并维护 Development 关联；逐项权限不足返回 degraded，不反向更新 Issue。
 
 ### 7. 发布审查摘要
 
@@ -112,11 +114,11 @@ agent-infra-internal task-verify {task-id} create-pr.completed --format text
 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}`。
 
 ```
-下一步 - 监控 PR 检查（required checks 全绿前自动自愈）：
+下一步 - 监控 PR 检查（全部 checks 全绿前自动自愈）：
 {next-step-commands}
 ```
 
-或者，若想跳过主动监控并立即尝试完成，改用 `complete-task`；其 required-checks 硬门禁仍会对 pending/failed/head mismatch fail-closed：
+或者，若想跳过主动监控并立即尝试完成，改用 `complete-task`；其全部 checks 硬门禁仍会对 pending/failed/head mismatch fail-closed：
 
 使用 `agent-infra-internal agent-client next-steps --skill complete-task --task-ref {task-ref}` 生成本场景的 `{next-step-commands}`。
 
@@ -125,7 +127,7 @@ agent-infra-internal task-verify {task-id} create-pr.completed --format text
 {next-step-commands}
 ```
 
-`watch-pr` 为主路径；上面的 `complete-task` 备选块只跳过主动轮询，不跳过 required checks，也不保证立即归档。
+`watch-pr` 为主路径；上面的 `complete-task` 备选块只跳过主动轮询，不跳过全部 checks，也不保证立即归档。
 
 ## 注意事项
 

package/templates/.agents/skills/create-pr/reference/comment-publish.en.md

@@ -6,7 +6,7 @@ Write the plain summary body to a temporary file, then run:
 
 ```bash
 agent-infra-internal platform-pr summary-sync {task-id} \
-  --agent {agent} --body-file {summary-body-file}
+  --agent {standard-agent-token} --body-file {summary-body-file}
 ```
 
 The caller does not add markers, HEAD metadata, or comment API parameters. A summary failure records the existing `create-pr` warning and does not roll back the PR.

package/templates/.agents/skills/create-pr/reference/comment-publish.zh-CN.md

@@ -6,7 +6,7 @@
 
 ```bash
 agent-infra-internal platform-pr summary-sync {task-id} \
-  --agent {agent} --body-file {summary-body-file}
+  --agent {standard-agent-token} --body-file {summary-body-file}
 ```
 
 调用方不添加 marker、HEAD 或评论 API 参数。摘要失败沿用 `create-pr` 错误处理并记录 warning，不回滚已创建 PR。结果映射沿用 `.agents/rules/pr-sync.md`。

package/templates/.agents/skills/create-release-note/SKILL.en.md

@@ -126,35 +126,36 @@ If no historical release notes exist, use the following default Markdown format:
      - Sort reporters by reported Issue count descending, then lexicographically by login for ties
 5. Empty sections: Omit sections with no entries
 
-### 8. Present and Confirm
+### 8. Stage, Present, and Confirm
 
-Show the generated release notes to the user.
-
-Ask:
-1. Need any adjustments?
-2. Write these notes onto the Release for this version?
-
-### 9. Publish the Release Notes (If Confirmed)
-
-9.1 Write the generated notes to a temp file **outside the working tree** so no uncommitted artifact is left behind in the repo (do not write into `.agents/workspace/` or any version-controlled directory):
+Write the candidate notes to a temporary file outside the working tree, then call typed stage to normalize the file and retain its structured `sha256`:
 
 ```bash
 NOTES_FILE="$(mktemp "${TMPDIR:-/tmp}/agent-infra-release-notes.XXXXXX")"
+agent-infra-internal platform-release-notes stage \
+  --notes-file "$NOTES_FILE"
 ```
 
-Write the notes content to `$NOTES_FILE`.
+Present the exact staged file and delete it before asking. Adjustments invalidate the digest. Only an unambiguous affirmative reply for this preview in the current session authorizes publishing; denial, questions, ambiguity, or interruption stop without publish.
+
+### 9. Recheck and Publish Release Notes
 
-9.2 Call the typed publish intent (use `$NOTES_FILE` for `{notes-file}`); it updates an existing Release or creates a missing one:
+After confirmation, write the confirmed normalized text to a new external temporary file and stage it again. Delete and return to preview if its digest differs. On a match, call:
 
 ```bash
 agent-infra-internal platform-release-notes publish \
-  --tag "v<version>" --title "v<version>" --notes-file "$NOTES_FILE"
+  --tag "v<version>" \
+  --title "v<version>" \
+  --notes-file "$NOTES_FILE" \
+  --expected-sha256 "{preview-sha256}"
 ```
 
-9.3 Remove the temp file whether publishing succeeds or fails:
+Delete the temporary file on every exit path. After success, render:
 
 ```bash
-rm -f "$NOTES_FILE"
+agent-infra-internal agent-client next-steps \
+  --skill post-release \
+  --version <version>
 ```
 
 Output:
@@ -174,7 +175,7 @@ The notes have been written to the Release. Edit further at the URL above if nee
 2. **Tags must exist**: Run the release skill first to create tags
 3. **Release auto-published**: the `v{version}` Release is created and published by the release workflow (the upload target for Homebrew bottles); this skill writes/refreshes the notes on that Release
 4. **Classification accuracy**: Auto-classification is based on title/scope/files; complex PRs may need manual adjustment
-5. **No leftover artifacts**: Always write notes to a temp file outside the working tree (`mktemp`) and delete it after publishing; never write into the repo directory
+5. **No leftover artifacts**: Delete preview files before asking and publish files on every exit path; interruption invalidates session-only notes and authorization
 
 ## Error Handling
 

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

@@ -126,35 +126,36 @@ agent-infra-internal platform-release-notes context \
      - Reporter 之间按报告的 Issue 数量降序排列，数量相同时按 login 字典序
 5. 空部分：省略没有条目的部分
 
-### 8. 展示并确认
+### 8. Stage、展示并确认
 
-向用户展示生成的发布说明。
-
-询问：
-1. 需要调整吗？
-2. 是否把 notes 写入该版本的 Release？
-
-### 9. 发布 Release notes（如确认）
-
-9.1 把生成的 notes 写入**工作树之外**的临时文件，避免在仓库残留未提交产物（不要写入 `.agents/workspace/` 或任何受版本控制的目录）：
+把候选 notes 写入工作树外临时文件，调用 typed stage 规范化并保存结构化 `sha256`：
 
 ```bash
 NOTES_FILE="$(mktemp "${TMPDIR:-/tmp}/agent-infra-release-notes.XXXXXX")"
+agent-infra-internal platform-release-notes stage \
+  --notes-file "$NOTES_FILE"
 ```
 
-把 notes 内容写入 `$NOTES_FILE`。
+只展示 stage 后同一文件的精确内容，在询问前删除文件。调整会使旧 digest 失效。只有当前会话中针对当前预览的无歧义明确肯定答复才授权发布；否定、疑问、歧义或中断均停止。
+
+### 9. 复核并发布 Release notes
 
-9.2 调用 typed publish intent（命令中的 `{notes-file}` 用 `$NOTES_FILE`）；它会更新已存在的 Release，不存在时创建：
+确认后把已确认文本写入新的工作树外临时文件并再次 stage。digest 不一致时删除并回到预览；一致时调用：
 
 ```bash
 agent-infra-internal platform-release-notes publish \
-  --tag "v<version>" --title "v<version>" --notes-file "$NOTES_FILE"
+  --tag "v<version>" \
+  --title "v<version>" \
+  --notes-file "$NOTES_FILE" \
+  --expected-sha256 "{preview-sha256}"
 ```
 
-9.3 无论发布成功或失败，都删除临时文件：
+所有退出路径删除临时文件。成功后渲染：
 
 ```bash
-rm -f "$NOTES_FILE"
+agent-infra-internal agent-client next-steps \
+  --skill post-release \
+  --version <version>
 ```
 
 输出：
@@ -174,7 +175,7 @@ Release notes 已更新。
 2. **标签必须存在**：先执行 release 技能创建标签
 3. **Release 已自动发布**：`v{version}` 的 Release 由 release 工作流自动创建并发布（给 Homebrew bottle 提供上传落点）；本技能往该 Release 写入/刷新 notes
 4. **分类准确性**：自动分类基于标题/scope/文件；复杂的 PR 可能需要手动调整
-5. **不留残留产物**：notes 一律写入工作树之外的临时文件（`mktemp`）并在发布后删除，禁止写入仓库目录
+5. **不留残留产物**：预览文件在询问前删除，发布文件在所有退出路径删除；会话中断时授权和草稿失效
 
 ## 错误处理
 

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

@@ -6,6 +6,8 @@ description: >
 ---
 
 # Create 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.
+
 
 ## Boundary / Critical Rules
 
@@ -131,12 +133,12 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 After task.md is written, call the declarative intents; the internal core owns templates, body rendering, identity validation, capability degradation, idempotency, and task binding:
 
 ```bash
-agent-infra-internal platform-issue create {task-id} --agent {agent}
-agent-infra-internal platform-issue sync {task-id} --agent {agent} --status waiting-for-triage --assignees current --milestone initial --issue-type --fields
+agent-infra-internal platform-issue create {task-id} --agent {standard-agent-token}
+agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status waiting-for-triage --assignees current --milestone initial --issue-type --fields
 ```
 
 Handle the result:
-- Intent created the Issue: `issue_number` was written through the task writer; run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
+- Intent created the Issue: `issue_number` was written through the task writer; run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
 - Rule failed (auth / network / template parse / etc.): do not roll back task.md or append an extra Activity Log entry; run `agent-infra-internal task-warning {task-id} add --step create-task --severity ACTION_REQUIRED --code ISSUE_CREATE_FAILED --target issue --message "{error_code}: {error_message}" --action "Fix auth/network/template issues and manually retry Issue creation, or create/find an Issue and write issue_number"` to submit a structured warning intent (callers do not allocate ids or edit rows), then follow Scenario C
 - Intent returned no-op/degraded: continue applicable operations without blocking the workflow
 - task.md already has a valid `issue_number`: create validates the binding and returns no-op without creating a duplicate

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

@@ -6,6 +6,8 @@ description: >
 ---
 
 # 创建任务
+> `--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`。
+
 
 ## 行为边界 / 关键规则
 
@@ -130,12 +132,12 @@ date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 在 task.md 落盘并记录 `Create Task` 后调用声明式 Issue intent；标题、正文、模板、身份校验、权限降级、幂等创建和 task.md 绑定均由 internal core 处理：
 
 ```bash
-agent-infra-internal platform-issue create {task-id} --agent {agent}
-agent-infra-internal platform-issue sync {task-id} --agent {agent} --status waiting-for-triage --assignees current --milestone initial --issue-type --fields
+agent-infra-internal platform-issue create {task-id} --agent {standard-agent-token}
+agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status waiting-for-triage --assignees current --milestone initial --issue-type --fields
 ```
 
 处理结果：
-- intent 成功创建 Issue：`issue_number` 已由任务写入内核回写；调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
+- intent 成功创建 Issue：`issue_number` 已由任务写入内核回写；调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token}`
 - 规则失败（认证 / 网络 / 模板解析等）：不回滚 task.md；不追加额外 Activity Log；先调用 `agent-infra-internal task-warning {task-id} add --step create-task --severity ACTION_REQUIRED --code ISSUE_CREATE_FAILED --target issue --message "{error_code}: {error_message}" --action "修复认证/网络/模板问题后手动重试 Issue 创建，或手动创建/找到 Issue 后写入 issue_number"` 提交结构化 warning 意图（调用方不分配编号或写表格）；再按"场景 C：Issue 创建失败"输出
 - intent 为 no-op/degraded：按结构化 operations 继续可执行部分；自定义或空平台不创建评论且不阻塞工作流
 - task.md 已存在有效 `issue_number`：create intent 校验绑定后返回 no-op，不重复创建