@fitlab-ai/agent-infra 0.8.2 → 0.8.4

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

@@ -21,7 +21,7 @@ description: >
 
 ## 步骤开始：记录开始时间
 
-本技能会**创建** task.md，开始时尚无文件可写。先在内存记录开始时间 `started_at`（`date "+%Y-%m-%d %H:%M:%S%:z"`）；在最后写活动日志时**一次性补两条**——started 行用 `started_at`、done 行用完成时间，二者同基名（started 行 action 加 ` [started]` 后缀、note 用 `started`）。基名必须跟实际导入场景一致：
+本技能会**创建** task.md，开始时尚无文件可写。先在内存记录开始时间 `started_at`（`date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'`）；在最后写活动日志时**一次性补两条**——started 行用 `started_at`、done 行用完成时间，二者同基名（started 行 action 加 ` [started]` 后缀、note 用 `started`）。基名必须跟实际导入场景一致：
 
 ```
 # 场景 B：新 Issue 导入
@@ -127,7 +127,7 @@ assigned_to: {当前 AI 代理}
 获取当前时间：
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
+date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ```
 
 更新 `.agents/workspace/active/{task-id}/task.md`：
@@ -195,7 +195,7 @@ Issue #{number} 已导入。
 
 下一步 - 执行需求分析：
   - Claude Code / OpenCode：/analyze-task {task-ref}
-  - Gemini CLI：/agent-infra:analyze-task {task-ref}
+  - Gemini CLI：/{{project}}:analyze-task {task-ref}
   - Codex CLI：$analyze-task {task-ref}
 ```
 

package/templates/.agents/skills/init-labels/SKILL.zh-CN.md

@@ -94,7 +94,7 @@ bash .agents/skills/init-labels/scripts/init-labels.sh
 ```
 下一步 - 初始化 Milestones（可选）：
   - Claude Code / OpenCode：/init-milestones
-  - Gemini CLI：/agent-infra:init-milestones
+  - Gemini CLI：/{{project}}:init-milestones
   - Codex CLI：$init-milestones
 ```
 

package/templates/.agents/skills/init-milestones/SKILL.en.md

@@ -30,7 +30,7 @@ bash .agents/skills/init-milestones/scripts/init-milestones.sh "$ARGUMENTS"
 The script and `.agents/rules/label-milestone-setup.md` are responsible for:
 - Creating and cleaning up a temporary workspace
 - Detecting whether `--history` was requested
-- Resolving the version baseline from the latest `v*` Git tag, then `package.json`, then defaulting to `0.1.0`
+- Scanning all `v*` Git tags, selecting the highest valid version by SemVer precedence, and using compatibility default `0.1.0` when none is valid, without reading ecosystem manifests
 - Listing current milestones with the platform-specific milestone query command
 - Building the desired milestone set and creating only the missing titles
 - Printing the final execution summary
@@ -50,6 +50,7 @@ When `--history` is present, each historical `vX.Y.Z` tag additionally contribut
 
 The summary must include:
 - Version baseline
+- Version baseline source
 - Whether `--history` was enabled
 - Created and skipped milestone counts
 - Newly created milestone titles
@@ -81,6 +82,6 @@ Next step - initialize labels (optional):
 - Authentication failed: prompt "the platform CLI is not authenticated"
 - Repository access failed: prompt "Unable to access the current repository with the platform CLI"
 - Version detection failed: prompt "Unable to determine current version baseline"
-- No `v*` tags found in `--history` mode: prompt "No history tags found matching v*; only standard milestones will be created"
+- No valid SemVer `v*` tags found in `--history` mode: prompt "No valid SemVer history tags found matching v*; only standard milestones will be created"
 - Permission error: prompt "No permission to manage milestones in this repository"
 - API rate limit: prompt "platform API rate limit reached, please retry later"

package/templates/.agents/skills/init-milestones/SKILL.zh-CN.md

@@ -30,7 +30,7 @@ bash .agents/skills/init-milestones/scripts/init-milestones.sh "$ARGUMENTS"
 脚本与 `.agents/rules/label-milestone-setup.md` 共同负责：
 - 创建并清理临时工作目录
 - 检测是否传入 `--history`
-- 按“最新 `v*` Git tag → `package.json` → 默认 `0.1.0`”解析版本基线
+- 扫描所有 `v*` Git tag，按 SemVer precedence 选择最高合法版本；没有合法版本时使用兼容默认值 `0.1.0`，且不读取任何生态 manifest
 - 使用平台对应的 milestones 查询命令读取当前里程碑
 - 构建目标里程碑集合，并且只创建缺失标题
 - 输出最终执行摘要
@@ -50,6 +50,7 @@ bash .agents/skills/init-milestones/scripts/init-milestones.sh "$ARGUMENTS"
 
 摘要必须包含：
 - 版本基线
+- 版本基线来源
 - 是否启用 `--history`
 - 创建与跳过的里程碑数量
 - 新创建的里程碑标题
@@ -71,7 +72,7 @@ bash .agents/skills/init-milestones/scripts/init-milestones.sh "$ARGUMENTS"
 ```
 下一步 - 初始化 Labels（可选）：
   - Claude Code / OpenCode：/init-labels
-  - Gemini CLI：/agent-infra:init-labels
+  - Gemini CLI：/{{project}}:init-labels
   - Codex CLI：$init-labels
 ```
 
@@ -81,6 +82,6 @@ bash .agents/skills/init-milestones/scripts/init-milestones.sh "$ARGUMENTS"
 - 认证失败：提示 "the platform CLI is not authenticated"
 - 仓库访问失败：提示 "Unable to access the current repository with the platform CLI"
 - 版本解析失败：提示 "Unable to determine current version baseline"
-- `--history` 模式下未找到任何 `v*` git tags：提示 "No history tags found matching v*; only standard milestones will be created"
+- `--history` 模式下未找到合法 SemVer `v*` git tags：提示 "No valid SemVer history tags found matching v*; only standard milestones will be created"
 - 权限不足：提示 "No permission to manage milestones in this repository"
 - API 限流：提示 "platform API rate limit reached, please retry later"

package/templates/.agents/skills/init-milestones/scripts/init-milestones.github.sh

@@ -33,34 +33,171 @@ esac
 
 echo "History mode: $history_mode"
 
-current_version=""
-latest_tag="$(git tag --list 'v*' --sort=-v:refname | head -1)"
-
-if [ -n "$latest_tag" ]; then
-  current_version="${latest_tag#v}"
-elif [ -f package.json ]; then
-  current_version="$(node -p "const version = require('./package.json').version || ''; version.replace(/^v/, '').replace(/-.*/, '')")"
-fi
-
-if [ -z "$current_version" ]; then
-  current_version="0.1.0"
-fi
-
-major="${current_version%%.*}"
-rest="${current_version#*.}"
-minor="${rest%%.*}"
-patch="${rest#*.}"
-patch="${patch%%[^0-9]*}"
+parse_semver_tags() {
+  LC_ALL=C awk -v mode="$1" '
+    function valid_core_number(value) {
+      return value ~ /^(0|[1-9][0-9]*)$/
+    }
+
+    function valid_identifiers(value, prerelease,    count, index_, identifiers) {
+      if (value == "") return 0
+      count = split(value, identifiers, ".")
+      for (index_ = 1; index_ <= count; index_++) {
+        if (identifiers[index_] !~ /^[0-9A-Za-z-]+$/) return 0
+        if (prerelease && identifiers[index_] ~ /^[0-9]+$/ && identifiers[index_] !~ /^(0|[1-9][0-9]*)$/) return 0
+      }
+      return 1
+    }
+
+    function parse_version(tag,    version, main, core, plus_at, dash_at, count) {
+      if (substr(tag, 1, 1) != "v") return 0
+      version = substr(tag, 2)
+      main = version
+      parsed_build = ""
+      plus_at = index(main, "+")
+      if (plus_at > 0) {
+        parsed_build = substr(main, plus_at + 1)
+        main = substr(main, 1, plus_at - 1)
+        if (!valid_identifiers(parsed_build, 0)) return 0
+      }
+
+      parsed_prerelease = ""
+      dash_at = index(main, "-")
+      if (dash_at > 0) {
+        parsed_prerelease = substr(main, dash_at + 1)
+        main = substr(main, 1, dash_at - 1)
+        if (!valid_identifiers(parsed_prerelease, 1)) return 0
+      }
+
+      count = split(main, core, ".")
+      if (count != 3) return 0
+      if (!valid_core_number(core[1]) || !valid_core_number(core[2]) || !valid_core_number(core[3])) return 0
+
+      parsed_tag = tag
+      parsed_major = core[1]
+      parsed_minor = core[2]
+      parsed_patch = core[3]
+      return 1
+    }
+
+    function compare_decimal(left, right,    index_, left_digit, right_digit) {
+      if (length(left) != length(right)) return length(left) > length(right) ? 1 : -1
+      for (index_ = 1; index_ <= length(left); index_++) {
+        left_digit = substr(left, index_, 1) + 0
+        right_digit = substr(right, index_, 1) + 0
+        if (left_digit != right_digit) return left_digit > right_digit ? 1 : -1
+      }
+      return 0
+    }
+
+    function compare_ascii(left, right,    alphabet, limit, index_, left_rank, right_rank) {
+      alphabet = "+-.0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
+      limit = length(left) < length(right) ? length(left) : length(right)
+      for (index_ = 1; index_ <= limit; index_++) {
+        left_rank = index(alphabet, substr(left, index_, 1))
+        right_rank = index(alphabet, substr(right, index_, 1))
+        if (left_rank != right_rank) return left_rank > right_rank ? 1 : -1
+      }
+      if (length(left) == length(right)) return 0
+      return length(left) > length(right) ? 1 : -1
+    }
+
+    function compare_prerelease(left, right,    left_count, right_count, limit, index_, comparison, left_numeric, right_numeric, left_ids, right_ids) {
+      if (left == "" || right == "") {
+        if (left == right) return 0
+        return left == "" ? 1 : -1
+      }
+
+      left_count = split(left, left_ids, ".")
+      right_count = split(right, right_ids, ".")
+      limit = left_count < right_count ? left_count : right_count
+      for (index_ = 1; index_ <= limit; index_++) {
+        left_numeric = left_ids[index_] ~ /^[0-9]+$/
+        right_numeric = right_ids[index_] ~ /^[0-9]+$/
+        if (left_numeric && right_numeric) {
+          comparison = compare_decimal(left_ids[index_], right_ids[index_])
+        } else if (left_numeric != right_numeric) {
+          comparison = left_numeric ? -1 : 1
+        } else {
+          comparison = compare_ascii(left_ids[index_], right_ids[index_])
+        }
+        if (comparison != 0) return comparison
+      }
+
+      if (left_count == right_count) return 0
+      return left_count > right_count ? 1 : -1
+    }
+
+    function candidate_is_higher(    comparison) {
+      comparison = compare_decimal(parsed_major, best_major)
+      if (comparison != 0) return comparison > 0
+      comparison = compare_decimal(parsed_minor, best_minor)
+      if (comparison != 0) return comparison > 0
+      comparison = compare_decimal(parsed_patch, best_patch)
+      if (comparison != 0) return comparison > 0
+      comparison = compare_prerelease(parsed_prerelease, best_prerelease)
+      if (comparison != 0) return comparison > 0
+      return compare_ascii(parsed_tag, best_tag) > 0
+    }
+
+    function increment_decimal(value,    index_, digit, output) {
+      output = ""
+      for (index_ = length(value); index_ >= 1; index_--) {
+        digit = substr(value, index_, 1) + 0
+        if (digit < 9) return substr(value, 1, index_ - 1) (digit + 1) output
+        output = "0" output
+      }
+      return "1" output
+    }
+
+    parse_version($0) {
+      if (mode == "history") {
+        printf "%s\t%s\t%s\n", parsed_major, parsed_minor, parsed_patch
+        next
+      }
+
+      if (!have_best || candidate_is_higher()) {
+        have_best = 1
+        best_tag = parsed_tag
+        best_major = parsed_major
+        best_minor = parsed_minor
+        best_patch = parsed_patch
+        best_prerelease = parsed_prerelease
+      }
+    }
+
+    END {
+      if (mode == "history") exit
+      if (!have_best) {
+        best_tag = "-"
+        best_major = "0"
+        best_minor = "1"
+        best_patch = "0"
+      }
+      printf "%s\t%s\t%s\t%s\t%s\n", best_tag, best_major, best_minor, best_patch, increment_decimal(best_patch)
+    }
+  '
+}
+
+selection="$(git tag --list 'v*' | parse_semver_tags select)"
+previous_ifs="$IFS"
+IFS="$(printf '\t')" read -r selected_tag major minor patch next_patch <<EOF
+$selection
+EOF
+IFS="$previous_ifs"
 
-if ! printf '%s %s %s\n' "$major" "$minor" "$patch" | grep -Eq '^[0-9]+ [0-9]+ [0-9]+$'; then
-  echo "Unable to determine current version baseline"
-  exit 1
+current_version="$major.$minor.$patch"
+if [ "$selected_tag" = "-" ]; then
+  version_source="compatibility default"
+else
+  version_source="git tag $selected_tag"
 fi
 
 line_milestone="$major.$minor.x"
-next_version="$major.$minor.$((patch + 1))"
+next_version="$major.$minor.$next_patch"
 
 echo "Detected version baseline: $current_version"
+echo "Version baseline source: $version_source"
 echo "Line milestone: $line_milestone"
 echo "Next version milestone: $next_version"
 
@@ -80,26 +217,12 @@ $next_version	Issues that we want to release in v$next_version.	open
 EOF
 
 if [ "$history_mode" = "true" ]; then
-  git tag --list 'v*' --sort=v:refname > "$tmpdir/history-tags.txt"
+  git tag --list 'v*' | parse_semver_tags history > "$tmpdir/history-versions.tsv"
 
-  if [ ! -s "$tmpdir/history-tags.txt" ]; then
-    echo "No history tags found matching v*; only standard milestones will be created."
+  if [ ! -s "$tmpdir/history-versions.tsv" ]; then
+    echo "No valid SemVer history tags found matching v*; only standard milestones will be created."
   else
-    while IFS= read -r tag; do
-      [ -n "$tag" ] || continue
-
-      ver="${tag#v}"
-      h_major="${ver%%.*}"
-      h_rest="${ver#*.}"
-      h_minor="${h_rest%%.*}"
-      h_patch="${h_rest#*.}"
-      h_patch="${h_patch%%[^0-9]*}"
-
-      if ! printf '%s %s %s\n' "$h_major" "$h_minor" "$h_patch" | grep -Eq '^[0-9]+ [0-9]+ [0-9]+$'; then
-        echo "Skip non-semver tag: $tag"
-        continue
-      fi
-
+    while IFS="$(printf '\t')" read -r h_major h_minor h_patch; do
       printf '%s\t%s\t%s\n' \
         "$h_major.$h_minor.x" \
         "Issues that we want to resolve in $h_major.$h_minor line." \
@@ -109,7 +232,7 @@ if [ "$history_mode" = "true" ]; then
         "$h_major.$h_minor.$h_patch" \
         "Issues that we want to release in v$h_major.$h_minor.$h_patch." \
         "closed" >> "$tmpdir/desired.tsv"
-    done < "$tmpdir/history-tags.txt"
+    done < "$tmpdir/history-versions.tsv"
   fi
 fi
 
@@ -143,6 +266,7 @@ echo "GitHub Milestones initialized."
 echo
 echo "Summary:"
 echo "- Version baseline: $current_version"
+echo "- Version baseline source: $version_source"
 echo "- History mode: $history_mode"
 echo "- Created milestones: $created_count"
 echo "- Skipped existing milestones: $skipped_count"

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

@@ -117,7 +117,7 @@ Create `.agents/workspace/active/{task-id}/{plan-artifact}`.
 Get the current time:
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
+date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ```
 
 Update `.agents/workspace/active/{task-id}/task.md`:

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

@@ -116,7 +116,7 @@ tail .agents/workspace/active/{task-id}/task.md
 获取当前时间：
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
+date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ```
 
 更新 `.agents/workspace/active/{task-id}/task.md`：
@@ -183,7 +183,7 @@ node .agents/scripts/validate-artifact.js gate plan-task .agents/workspace/activ
 
 下一步 - 审查技术方案：
   - Claude Code / OpenCode：/review-plan {task-ref}
-  - Gemini CLI：/agent-infra:review-plan {task-ref}
+  - Gemini CLI：/{{project}}:review-plan {task-ref}
   - Codex CLI：$review-plan {task-ref}
 ```
 

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

@@ -95,7 +95,7 @@ Write only files that were actually recovered from Issue comments. Do not invent
 Get the current time:
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
+date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ```
 
 Update the restored `task.md`:

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

@@ -94,7 +94,7 @@ description: >
 获取当前时间：
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
+date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ```
 
 更新恢复出的 `task.md`：

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

@@ -73,7 +73,7 @@ Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 Get the current time:
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
+date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ```
 
 Set `current_step` to `requirement-analysis-review`, refresh task metadata, and append:

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

@@ -79,7 +79,7 @@ tail .agents/workspace/active/{task-id}/task.md
 获取当前时间：
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
+date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ```
 
 更新 task.md：

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

@@ -27,7 +27,7 @@ Task {task-id} requirement analysis review completed. Verdict: approved.
 
 Next step - write the technical plan:
   - Claude Code / OpenCode: /plan-task {task-ref}
-  - Gemini CLI: /agent-infra:plan-task {task-ref}
+  - Gemini CLI: /{{project}}:plan-task {task-ref}
   - Codex CLI: $plan-task {task-ref}
 
 [When manual-validation > 0, append:]
@@ -43,12 +43,12 @@ Task {task-id} requirement analysis review completed. Verdict: approved.
 
 Next step - revise analysis before continuing (recommended):
   - Claude Code / OpenCode: /analyze-task {task-ref}
-  - Gemini CLI: /agent-infra:analyze-task {task-ref}
+  - Gemini CLI: /{{project}}:analyze-task {task-ref}
   - Codex CLI: $analyze-task {task-ref}
 
 Or proceed directly to planning:
   - Claude Code / OpenCode: /plan-task {task-ref}
-  - Gemini CLI: /agent-infra:plan-task {task-ref}
+  - Gemini CLI: /{{project}}:plan-task {task-ref}
   - Codex CLI: $plan-task {task-ref}
 
 [When manual-validation > 0, append:]
@@ -64,7 +64,7 @@ Task {task-id} requirement analysis review completed. Verdict: changes requested
 
 Next step - revise requirement analysis:
   - Claude Code / OpenCode: /analyze-task {task-ref}
-  - Gemini CLI: /agent-infra:analyze-task {task-ref}
+  - Gemini CLI: /{{project}}:analyze-task {task-ref}
   - Codex CLI: $analyze-task {task-ref}
 
 [When manual-validation > 0, append:]
@@ -80,7 +80,7 @@ Task {task-id} requirement analysis review completed. Verdict: rejected, fresh a
 
 Next step - re-analyze:
   - Claude Code / OpenCode: /analyze-task {task-ref}
-  - Gemini CLI: /agent-infra:analyze-task {task-ref}
+  - Gemini CLI: /{{project}}:analyze-task {task-ref}
   - Codex CLI: $analyze-task {task-ref}
 
 [When manual-validation > 0, append:]

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

@@ -27,7 +27,7 @@
 
 下一步 - 编写技术方案：
   - Claude Code / OpenCode：/plan-task {task-ref}
-  - Gemini CLI：/agent-infra:plan-task {task-ref}
+  - Gemini CLI：/{{project}}:plan-task {task-ref}
   - Codex CLI：$plan-task {task-ref}
 
 [当 manual-validation > 0 时，在最后附加一行：]
@@ -43,12 +43,12 @@
 
 下一步 - 修订分析后继续（推荐）：
   - Claude Code / OpenCode：/analyze-task {task-ref}
-  - Gemini CLI：/agent-infra:analyze-task {task-ref}
+  - Gemini CLI：/{{project}}:analyze-task {task-ref}
   - Codex CLI：$analyze-task {task-ref}
 
 或直接进入方案设计：
   - Claude Code / OpenCode：/plan-task {task-ref}
-  - Gemini CLI：/agent-infra:plan-task {task-ref}
+  - Gemini CLI：/{{project}}:plan-task {task-ref}
   - Codex CLI：$plan-task {task-ref}
 
 [当 manual-validation > 0 时，在最后附加一行：]
@@ -64,7 +64,7 @@
 
 下一步 - 修订需求分析：
   - Claude Code / OpenCode：/analyze-task {task-ref}
-  - Gemini CLI：/agent-infra:analyze-task {task-ref}
+  - Gemini CLI：/{{project}}:analyze-task {task-ref}
   - Codex CLI：$analyze-task {task-ref}
 
 [当 manual-validation > 0 时，在最后附加一行：]
@@ -80,7 +80,7 @@
 
 下一步 - 重新分析：
   - Claude Code / OpenCode：/analyze-task {task-ref}
-  - Gemini CLI：/agent-infra:analyze-task {task-ref}
+  - Gemini CLI：/{{project}}:analyze-task {task-ref}
   - Codex CLI：$analyze-task {task-ref}
 
 [当 manual-validation > 0 时，在最后附加一行：]

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

@@ -74,9 +74,10 @@ Read the highest-round code artifact and, if present, the highest-round fix arti
 ### 4. Perform the Review
 
 Follow `.agents/workflows/feature-development.yaml` and inspect the full change context:
-- `git diff --binary HEAD -- <post-review-globs>` for tracked changes
+- Capture `R=$(git rev-parse HEAD)` exactly once; reuse that R for this round's report, fingerprint, and task review fact, and do not re-read HEAD later as a substitute
+- `git diff --binary "$R" -- <post-review-globs>` for tracked changes
 - `git ls-files -o --exclude-standard -z -- <post-review-globs>` for untracked new files
-- `node .agents/scripts/review-diff-fingerprint.js worktree HEAD` for the reviewed diff fingerprint; write it into the report
+- `node .agents/scripts/review-diff-fingerprint.js worktree "$R"` for the reviewed diff fingerprint; write it into the report
 
 > Detailed review criteria, severity rules, and reviewer expectations live in `reference/review-criteria.md`. Read `reference/review-criteria.md` before reviewing.
 > Test review gate: when `git diff` touches test files, read `.agents/rules/testing-discipline.md` first and check it item by item, especially "do not add negative assertions when a positive assertion already covers the behavior".
@@ -92,10 +93,13 @@ Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 Get the current time:
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
+date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ```
 
-Update task.md and append:
+Update task.md:
+- When this round's `Overall Verdict` / `总体结论` is `Approved` / `通过`, write `last_reviewed_commit: {R}`; the presence of a worktree diff does not affect this write, and repeating the same R is idempotent
+- When this round is not Approved, preserve the existing `last_reviewed_commit`; do not advance or clear it
+- Append:
 `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Code (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}, Manual-validation: {n} → {artifact-filename}`
 
 Always include the `Manual-validation: {n}` field in the done log, including when it is 0.

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

@@ -73,9 +73,10 @@ tail .agents/workspace/active/{task-id}/task.md
 ### 4. 执行审查
 
 遵循 `.agents/workflows/feature-development.yaml`，并同时检查完整变更上下文：
-- `git diff --binary HEAD -- <post-review-globs>` 覆盖已跟踪变更
+- 一次性记录 `R=$(git rev-parse HEAD)`；本轮报告、指纹和任务审查事实都复用该 R，禁止稍后重新读取 HEAD 代替
+- `git diff --binary "$R" -- <post-review-globs>` 覆盖已跟踪变更
 - `git ls-files -o --exclude-standard -z -- <post-review-globs>` 覆盖未跟踪新文件
-- `node .agents/scripts/review-diff-fingerprint.js worktree HEAD` 生成审查差异指纹，并写入报告
+- `node .agents/scripts/review-diff-fingerprint.js worktree "$R"` 生成审查差异指纹，并写入报告
 
 > 详细审查标准、严重程度划分和 reviewer 关注点见 `reference/review-criteria.md`。执行此步骤前先读取 `reference/review-criteria.md`。
 > 测试审查硬门禁：当 `git diff` 触及测试文件时，必须先读取 `.agents/rules/testing-discipline.md` 并逐条核对（尤其"正向已覆盖时不应再加反向断言"）。
@@ -91,13 +92,15 @@ tail .agents/workspace/active/{task-id}/task.md
 获取当前时间：
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
+date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
 ```
 
 - `current_step`：code-review
 - `assigned_to`：{当前代理}
 - `updated_at`：{当前时间}
 - `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
+- 若本轮 `总体结论` / `Overall Verdict` 为 `通过` / `Approved`，写入 `last_reviewed_commit: {R}`；是否存在工作区 diff 不影响写入，重复写同一 R 幂等
+- 若本轮结论不是 Approved，保留既有 `last_reviewed_commit`，不得推进或清空
 - 追加：
 `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Code (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}, Manual-validation: {n} → {artifact-filename}`
 

package/templates/.agents/skills/review-code/config/verify.en.json

@@ -36,6 +36,7 @@
       ],
       "freshness_minutes": 30
     },
+    "review-fact": {},
     "activity-log": {
       "expected_action_pattern": "(Review Code|Code Review) \\(Round \\d+\\)",
       "freshness_minutes": 30

package/templates/.agents/skills/review-code/config/verify.zh-CN.json

@@ -36,6 +36,7 @@
       ],
       "freshness_minutes": 30
     },
+    "review-fact": {},
     "activity-log": {
       "expected_action_pattern": "(Review Code|Code Review) \\(Round \\d+\\)",
       "freshness_minutes": 30

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

@@ -29,7 +29,7 @@ Task {task-id} review completed. Verdict: approved.
 
 Next step - commit the code:
   - Claude Code / OpenCode: /commit
-  - Gemini CLI: /agent-infra:commit
+  - Gemini CLI: /{{project}}:commit
   - Codex CLI: $commit
 
 [When manual-validation > 0, append this final line:]
@@ -45,12 +45,12 @@ Task {task-id} review completed. Verdict: approved.
 
 Next step - fix before commit (recommended):
   - Claude Code / OpenCode: /code-task {task-ref}
-  - Gemini CLI: /agent-infra:code-task {task-ref}
+  - Gemini CLI: /{{project}}:code-task {task-ref}
   - Codex CLI: $code-task {task-ref}
 
 Or commit directly (skip fix):
   - Claude Code / OpenCode: /commit
-  - Gemini CLI: /agent-infra:commit
+  - Gemini CLI: /{{project}}:commit
   - Codex CLI: $commit
 
 [When manual-validation > 0, append this final line:]
@@ -66,7 +66,7 @@ Task {task-id} review completed. Verdict: changes requested.
 
 Next step - fix the findings:
   - Claude Code / OpenCode: /code-task {task-ref}
-  - Gemini CLI: /agent-infra:code-task {task-ref}
+  - Gemini CLI: /{{project}}:code-task {task-ref}
   - Codex CLI: $code-task {task-ref}
 
 [When manual-validation > 0, append this final line:]
@@ -82,7 +82,7 @@ Task {task-id} review completed. Verdict: rejected, re-design the technical plan
 
 Next step - re-design the technical plan:
   - Claude Code / OpenCode: /plan-task {task-ref}
-  - Gemini CLI: /agent-infra:plan-task {task-ref}
+  - Gemini CLI: /{{project}}:plan-task {task-ref}
   - Codex CLI: $plan-task {task-ref}
 
 > Note: Rejected means the implementation direction needs to be reworked end-to-end, not patched locally. `code-task/scripts/detect-mode.js` branch #7 refuses a direct `/code-task` and requires a fresh plan first.

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

@@ -29,7 +29,7 @@
 
 下一步 - 提交代码：
   - Claude Code / OpenCode：/commit
-  - Gemini CLI：/agent-infra:commit
+  - Gemini CLI：/{{project}}:commit
   - Codex CLI：$commit
 
 [当 manual-validation > 0 时，在最后附加一行：]
@@ -45,12 +45,12 @@
 
 下一步 - 修复问题后提交（推荐）：
   - Claude Code / OpenCode：/code-task {task-ref}
-  - Gemini CLI：/agent-infra:code-task {task-ref}
+  - Gemini CLI：/{{project}}:code-task {task-ref}
   - Codex CLI：$code-task {task-ref}
 
 或直接提交（跳过修复）：
   - Claude Code / OpenCode：/commit
-  - Gemini CLI：/agent-infra:commit
+  - Gemini CLI：/{{project}}:commit
   - Codex CLI：$commit
 
 [当 manual-validation > 0 时，在最后附加一行：]
@@ -66,7 +66,7 @@
 
 下一步 - 修复问题：
   - Claude Code / OpenCode：/code-task {task-ref}
-  - Gemini CLI：/agent-infra:code-task {task-ref}
+  - Gemini CLI：/{{project}}:code-task {task-ref}
   - Codex CLI：$code-task {task-ref}
 
 [当 manual-validation > 0 时，在最后附加一行：]
@@ -82,7 +82,7 @@
 
 下一步 - 重新设计技术方案：
   - Claude Code / OpenCode：/plan-task {task-ref}
-  - Gemini CLI：/agent-infra:plan-task {task-ref}
+  - Gemini CLI：/{{project}}:plan-task {task-ref}
   - Codex CLI：$plan-task {task-ref}
 
 > 注意：Rejected 表示实现方向需要整体重做，不是局部修复。`code-task/scripts/detect-mode.js` 分支 #7 会拒绝直接 `/code-task`，要求先重新方案设计。