gm-emit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

GM EMIT — Writing and Verifying Files

GM EMIT — 文件写入与验证

You are in the EMIT phase. Every mutable is KNOWN. Prove the write is correct, write, confirm from disk. Any new unknown = snake to

planning

, restart chain.

GRAPH POSITION:

PLAN → EXECUTE → [EMIT] → VERIFY → COMPLETE

Entry: All .prd mutables resolved. Entered from
```
gm-execute
```
or via snake from VERIFY.

你正处于EMIT阶段。所有可变项均为已知状态。需验证写入操作的正确性，执行写入，然后从磁盘确认结果。任何新的未知情况都将回溯至

planning

阶段，重启流程链。

流程位置：

PLAN → EXECUTE → [EMIT] → VERIFY → COMPLETE

进入条件：所有.prd可变项已解析完成。从
```
gm-execute
```
阶段进入，或从VERIFY阶段回溯进入。

TRANSITIONS

阶段转换

FORWARD: All gate conditions true simultaneously → invoke

gm-complete

skill

SELF-LOOP: Post-emit variance with known cause → fix immediately, re-verify, do not advance until zero variance

BACKWARD:

Pre-emit reveals logic error (known mutable) → invoke
```
gm-execute
```
skill, re-resolve, return here
Pre-emit reveals new unknown → invoke
```
planning
```
skill, restart chain
Post-emit variance with unknown cause → invoke
```
planning
```
skill, restart chain
Scope changed → invoke
```
planning
```
skill, restart chain
From VERIFY: end-to-end reveals broken file → re-enter here, fix, re-verify, re-advance

向前推进：所有准入条件同时满足 → 调用

gm-complete

skill

自循环：发射后出现已知原因的差异 → 立即修复，重新验证，直至差异为零再推进

向后回溯:

预发射阶段发现逻辑错误（已知可变项）→ 调用
```
gm-execute
```
skill，重新解析，返回本阶段
预发射阶段发现新的未知情况 → 调用
```
planning
```
skill，重启流程链
发射后出现原因未知的差异 → 调用
```
planning
```
skill，重启流程链
范围变更 → 调用
```
planning
```
skill，重启流程链
从VERIFY阶段返回：端到端检查发现文件损坏 → 重新进入本阶段，修复，重新验证，再推进

MUTABLE DISCIPLINE

可变项规范

Each gate condition is a mutable. Pre-emit run witnesses expected value. Post-emit run witnesses current value. Zero variance = resolved. Variance with unknown cause = new unknown = snake to

planning

每个准入条件都是一个可变项。预发射运行可获取预期值。发射后运行可获取当前值。差异为零即表示已解析。若出现原因未知的差异，则视为新的未知情况 → 回溯至

planning

阶段。

CODE EXECUTION

代码执行

exec:<lang> is the only way to run code. Bash tool body:

exec:<lang>\n<code>

exec:nodejs

(default) |

exec:bash

exec:python

exec:typescript

exec:go

exec:rust

exec:java

exec:deno

exec:cmd

Only git in bash directly.

Bash(node/npm/npx/bun)

= violations. File writes via exec:nodejs + require('fs').

exec:<lang>是运行代码的唯一方式。Bash工具格式：

exec:<lang>\n<code>

exec:nodejs

（默认）|

exec:bash

exec:python

exec:typescript

exec:go

exec:rust

exec:java

exec:deno

exec:cmd

仅可直接在bash中使用git。

Bash(node/npm/npx/bun)

属于违规操作。文件写入需通过exec:nodejs + require('fs')完成。

PRE-EMIT DEBUGGING (before writing any file)

预发射调试（写入任何文件之前）

Import actual module from disk via
```
exec:nodejs
```
— witness current on-disk behavior
Run proposed logic in isolation WITHOUT writing — witness output with real inputs
Debug failure paths with real error inputs — record expected values

exec:nodejs
const { fn } = await import('/abs/path/to/module.js');
console.log(await fn(realInput));

Pre-emit revealing unexpected behavior → new unknown → snake to

planning

通过
```
exec:nodejs
```
从磁盘导入实际模块 → 查看当前磁盘上的行为
在不写入文件的情况下独立运行拟议逻辑 → 使用真实输入查看输出
使用真实错误输入调试失败路径 → 记录预期值

exec:nodejs
const { fn } = await import('/abs/path/to/module.js');
console.log(await fn(realInput));

预发射阶段发现意外行为 → 新的未知情况 → 回溯至

planning

阶段。

WRITING FILES

文件写入

exec:nodejs

with

require('fs')

. Write only when every gate mutable is

resolved=true

simultaneously.

使用

exec:nodejs

搭配

require('fs')

。仅当所有准入可变项同时为

resolved=true

时才可执行写入。

POST-EMIT VERIFICATION (immediately after writing)

发射后验证（写入完成后立即执行）

Re-import the actual file from disk — not in-memory version
Run same inputs as pre-emit — output must match exactly
For browser: reload from disk, re-inject
```
__gm
```
globals, re-run, compare captures
Known variance → fix and re-verify | Unknown variance → snake to
```
planning
```

重新从磁盘导入实际文件 — 而非内存版本
运行与预发射阶段相同的输入 → 输出必须完全匹配
针对浏览器：从磁盘重新加载，重新注入
```
__gm
```
全局变量，重新运行，对比捕获结果
已知差异 → 修复并重新验证 | 未知差异 → 回溯至
```
planning
```
阶段

GATE CONDITIONS (all true simultaneously before advancing)

准入条件（推进前需同时满足所有条件）

Pre-emit debug passed with real inputs and error inputs
Post-emit verification matches pre-emit exactly
Hot reloadable: state outside reloadable modules, handlers swap atomically
Crash-proof: catch at every boundary, recovery hierarchy
No mocks/fakes/stubs anywhere
Files ≤200 lines, no duplicate code, no comments, no hardcoded values
CLAUDE.md reflects actual behavior

预发射调试通过真实输入和错误输入测试
发射后验证结果与预发射阶段完全匹配
支持热重载：可重载模块外的状态，处理器原子性切换
防崩溃：在每个边界处捕获异常，具备恢复层级
全程无模拟/伪造/存根（mocks/fakes/stubs）
文件行数≤200，无重复代码，无注释，无硬编码值
CLAUDE.md反映实际行为

CODEBASE EXPLORATION

代码库探索

exec:codesearch
<natural language description>

Alias:

exec:search

. Glob, Grep, Explore = blocked.

exec:codesearch
<自然语言描述>

别名：

exec:search

。Glob、Grep、Explore均被禁用。

BROWSER DEBUGGING

浏览器调试

Invoke

agent-browser

skill. Escalation: (1)

exec:agent-browser\n<js>

→ (2) skill +

__gm

globals → (3) navigate/click → (4) screenshot last resort.

调用

agent-browser

skill。升级步骤：(1)

exec:agent-browser\n<js>

→ (2) skill +

__gm

全局变量 → (3) 导航/点击 → (4) 最后手段是截图。

SELF-CHECK (before and after each file)

自我检查（每个文件写入前后）

CONSTRAINTS

约束条件

Always: pre-emit debug before writing | post-emit verify from disk | snake to planning on any new unknown | fix immediately

→ FORWARD: All gates pass → invoke

gm-complete

skill. ↺ SELF-LOOP: Known post-emit variance → fix, re-verify. ↩ SNAKE to EXECUTE: Known logic error → invoke

gm-execute

skill. ↩ SNAKE to PLAN: Any new unknown → invoke

planning

skill, restart chain.

→ 向前推进：所有准入条件满足 → 调用

gm-complete

skill。 ↺ 自循环：发射后出现已知差异 → 修复，重新验证。 ↩ 回溯至EXECUTE：发现已知逻辑错误 → 调用

gm-execute

skill。 ↩ 回溯至PLAN：出现任何新的未知情况 → 调用

planning

skill，重启流程链。