validator-check

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/validator-check

Run validator checks only — no AI reviews.

仅运行验证器检查——不进行AI评审。

Procedure

流程

Step 1 - Clean Logs

步骤1 - 清理日志

Run

agent-validate clean

to archive any previous log files.

运行

agent-validate clean

来归档所有之前的日志文件。

Step 2 - Run Checks

步骤2 - 执行检查

Run

agent-validate check

using

Bash

with

timeout: 300000

. ALWAYS wait for and read the full command output before proceeding. Verify you can see a
Status:
line in the output before continuing.

使用

Bash

运行

agent-validate check

，设置

timeout: 300000

。在继续操作前务必等待并读取完整的命令输出。继续前请确认你能在输出中看到
Status:
行。

Step 3 - Check Status

步骤3 - 检查状态

NEVER assume success — you must see an explicit

Status:

line before continuing. Check it and route accordingly:

```
Status: Passed
```
→ Go to Step 7.
```
Status: Passed with warnings
```
→ Go to Step 7.
```
Status: Failed
```
→ Continue to Step 4. You MUST continue — do not stop here.

Status: Retry limit exceeded

→ Run

agent-validate clean

to archive logs. Go to Step 7.

No status line visible → Known issue: Bun can drop all stdout/stderr. Read the console log file to get the status: find the latest
```
console.*.log
```
in the validator log directory (e.g.,
```
validator_logs/console.1.log
```
) and look for the
```
Status:
```
line there. If no console log is found there, also check
```
validator_logs/previous/
```
for logs from the most recent archived run. If no console log exists in either location, the command may have timed out or failed to run — re-run with a longer timeout or investigate the error. Do NOT proceed as if it passed.

永远不要假设操作成功——你必须看到明确的

Status:

行才能继续。检查状态并按如下方式处理：

```
Status: Passed
```
→ 进入步骤7。
```
Status: Passed with warnings
```
→ 进入步骤7。
```
Status: Failed
```
→ 继续步骤4。你必须继续——不要在此处停止。

Status: Retry limit exceeded

→ 运行

agent-validate clean

归档日志。进入步骤7。

未看到状态行 → 已知问题：Bun可能会丢弃所有stdout/stderr。读取控制台日志文件获取状态：在验证器日志目录中找到最新的
```
console.*.log
```
文件（例如
```
validator_logs/console.1.log
```
），并在其中查找
```
Status:
```
行。如果在此处未找到控制台日志，也请检查
```
validator_logs/previous/
```
目录中最近一次归档运行的日志。如果在这两个位置都没有找到控制台日志，说明命令可能超时或运行失败——请延长超时时间重新运行或排查错误。不要当作已通过来处理。

Step 4 - Extract Failures

步骤4 - 提取失败信息

Required when status is Failed:

Infer the log directory from the file paths in the console output (e.g., if output references
```
validator_logs/check_._lint.1.log
```
, the log directory is
```
validator_logs/
```
)
Extract log failures using the first available strategy: a. Task tool (Claude Code):
```
Task
```
with
```
subagent_type="general-purpose"
```
,
```
model="haiku"
```
,
```
prompt=
```
the Extract Prompt (from the Appendix below) +
```
"\n\nLog directory: <inferred path>"
```
. Task calls MUST be synchronous — NEVER use
```
run_in_background: true
```
. b. Subagent delegation: If your environment supports delegating work to a subagent but not the Task tool, delegate the Extract Prompt instructions with the log directory to a subagent for processing. c. Inline fallback: If no subagent capability is available, follow the Extract Prompt instructions yourself to read the log files and produce the compact failure summary.

当状态为Failed时需要执行：

从控制台输出的文件路径推断日志目录（例如，如果输出引用了
```
validator_logs/check_._lint.1.log
```
，则日志目录为
```
validator_logs/
```
）
提取日志失败信息，使用以下可用的第一种策略： a. 任务工具（Claude Code）：使用
```
Task
```
，设置
```
subagent_type="general-purpose"
```
，
```
model="haiku"
```
，
```
prompt=
```
附录中的提取提示 +
```
"\n\nLog directory: <推断的路径>"
```
。任务调用必须是同步的——绝不能使用
```
run_in_background: true
```
。 b. 子代理委托：如果你的环境支持将工作委托给子代理但不支持任务工具，请将提取提示说明和日志目录委托给子代理处理。 c. 内联回退：如果没有子代理功能可用，请自行按照提取提示说明读取日志文件并生成简洁的失败摘要。

Step 5 - Fix

步骤5 - 修复

Fix all failed checks:

CHECK failures with Fix Skill: invoke the named skill
CHECK failures with Fix Instructions: follow the instructions

修复所有失败的检查：

带有Fix Skill的CHECK失败：调用指定的skill
带有Fix Instructions的CHECK失败：按照说明操作

Step 6 - Re-run Verification

步骤6 - 重新运行验证

NEVER skip this step — if the run failed, you MUST fix and re-run. Run

agent-validate check

again with

Bash

and

timeout: 300000

. Do NOT run

agent-validate clean

between retries. The tool detects existing logs and automatically switches to verification mode. Go back to Step 3 to check the status line and repeat.

绝不能跳过此步骤——如果运行失败，你必须修复后重新运行。再次使用

Bash

运行

agent-validate check

，设置

timeout: 300000

。重试之间不要运行

agent-validate clean

。工具会检测到现有日志并自动切换到验证模式。回到步骤3检查状态行并重复操作。

Step 7 - Summarize Session

步骤7 - 总结会话

Provide a summary of the session:

Final Status: (Passed / Passed with warnings / Retry limit exceeded)
Checks Fixed: (list key fixes)
Outstanding Failures: (if retry limit exceeded, list unverified fixes and remaining issues)

提供会话总结：

最终状态：（已通过 / 带警告通过 / 超出重试限制）
已修复的检查：（列出关键修复内容）
未解决的失败：（如果超出重试限制，列出未验证的修复和剩余问题）

Appendix: Subagent Prompts

附录：子代理提示

Extract Prompt

提取提示

You are an EXTRACT subagent. Your job is to read validator check log files and return a compact error summary.

你是一个EXTRACT子代理。你的工作是读取验证器检查日志文件并返回简洁的错误摘要。

Input

输入

You receive a log directory path as your only input.

你仅会收到一个日志目录路径作为输入。

Process

流程

List files directly under the log directory
Find the highest-numbered
```
console.N.log
```
file (e.g.,
```
console.3.log
```
>
```
console.2.log
```
)
Read it and find all lines containing
```
[FAIL]
```
For each
```
[FAIL]
```
line, extract the referenced
```
.log
```
file path
Read each referenced log file and extract error output. Look for
```
--- Fix Instructions ---
```
sections and
```
--- Fix Skill: <name> ---
```
sections. Include their full content.

列出日志目录下的所有文件
找到编号最大的
```
console.N.log
```
文件（例如
```
console.3.log
```
>
```
console.2.log
```
）
读取该文件并找到所有包含
```
[FAIL]
```
的行
对于每一行
```
[FAIL]
```
，提取引用的
```
.log
```
文件路径
读取每个引用的日志文件并提取错误输出。查找
```
--- Fix Instructions ---
```
部分和
```
--- Fix Skill: <name> ---
```
部分。包含它们的完整内容。

Output Format

输出格式

Return a plain-text summary using EXACTLY this format:

text

CHECKS:
[fail] <gate_label>
<concise error description>
Fix Instructions: <extracted text if present, otherwise omit this line>
Fix Skill: <skill name if present, otherwise omit this line>

使用完全相同的格式返回纯文本摘要：

text

CHECKS:
[fail] <gate_label>
<concise error description>
Fix Instructions: <提取的文本（如果存在，否则省略此行）>
Fix Skill: <skill名称（如果存在，否则省略此行）>

Example

示例

Example Input

示例输入

Log directory:

validator_logs/

The directory contains:

```
console.2.log
```
```
check_src_lint.2.log
```

console.2.log contains:

text

[START] check:src:lint
[FAIL]  check:src:lint (1.23s) - Exited with code 1
      Log: validator_logs/check_src_lint.2.log

check_src_lint.2.log contains:

text

[2026-02-15T10:23:45.123Z] Starting check: lint
Executing command: bun run lint
Working directory: /Users/user/project/src

src/helpers.ts:3:5 - error: Unexpected var, use let or const instead

Command failed: bun run lint
Result: fail - Exited with code 1

--- Fix Instructions ---
Replace all `var` declarations with `const` or `let`.

日志目录：

validator_logs/

该目录包含：

```
console.2.log
```
```
check_src_lint.2.log
```

console.2.log内容：

text

[START] check:src:lint
[FAIL]  check:src:lint (1.23s) - Exited with code 1
      Log: validator_logs/check_src_lint.2.log

check_src_lint.2.log内容：

text

[2026-02-15T10:23:45.123Z] Starting check: lint
Executing command: bun run lint
Working directory: /Users/user/project/src

src/helpers.ts:3:5 - error: Unexpected var, use let or const instead

Command failed: bun run lint
Result: fail - Exited with code 1

--- Fix Instructions ---
Replace all `var` declarations with `const` or `let`.

Example Output

示例输出

text

CHECKS:
[fail] check:src:lint
src/helpers.ts:3:5 - error: Unexpected var, use let or const instead
Fix Instructions: Replace all `var` declarations with `const` or `let`.

text

CHECKS:
[fail] check:src:lint
src/helpers.ts:3:5 - error: Unexpected var, use let or const instead
Fix Instructions: Replace all `var` declarations with `const` or `let`.

Rules

规则

Do NOT summarize or editorialize — copy error details verbatim where possible
Do NOT skip any
```
[FAIL]
```
entries
Keep the output compact — one entry per check failure
Include
```
Fix Instructions
```
/
```
Fix Skill
```
lines only when present

不要总结或修改内容——尽可能逐字复制错误细节
不要跳过任何
```
[FAIL]
```
条目
保持输出简洁——每个检查失败对应一个条目
仅在存在时包含
```
Fix Instructions
```
/
```
Fix Skill
```
行