memory-audit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Memory audit — the surgical one-file pass

内存审计——单文件精准处理

This is the cap-trip response, not the daily ritual.

/memory-kit:close-session

runs every session and captures; this runs when the hot cache has actually outgrown itself and something must LEAVE it. Keeping them separate is the point: a daily ritual that also has to do surgery becomes a ritual people skip.

Always pause for approval before writing. The user talks; you write — including here.

这是超限响应操作，而非日常例行任务。

/memory-kit:close-session

会在每个会话结束时运行并捕获内容；而本操作仅在热缓存实际超出容量、必须移除部分内容时才执行。将两者区分开是关键：如果日常例行任务还要执行清理操作，人们会跳过这个例行任务。

在写入前务必暂停等待审批。用户确认后再执行写入操作——此处也不例外。

Inputs

输入项

```
.claude/memory/MEMORY.md
```
— read in full.
```
knowledge/concepts/*.md
```
— filenames + first 5 lines, for duplicate detection (the directory may not exist yet; the first move creates it).
```
context/handoffs/
```
— to confirm a session narrative already lives there → drop, not move.

```
.claude/memory/MEMORY.md
```
—— 完整读取。
```
knowledge/concepts/*.md
```
—— 文件名+前5行内容，用于重复检测（该目录可能尚未存在；首次移动操作会创建它）。
```
context/handoffs/
```
—— 确认会话记录已存在于此→直接删除，而非移动。

Step 1 — classify every section

步骤1 —— 对每个章节进行分类

Scan by

##

heading. For each, count lines and mark exactly one action:

Mark	When
`move (create)`	a settled pattern (confirmed on 3+ distinct dates) with >25 lines of reference detail
`move (merge)`	same, but a concept article on the topic already exists
`drop`	a per-session chronicle — it already lives in a handoff; distil at most one settled line
`update in-place`	stale: names a deleted file, a closed ticket, a superseded decision
`simplify`	true and useful, but three times longer than it needs to be
`keep`	earns its lines

按

##

标题扫描。对每个章节，统计行数并标记唯一操作：

标记	适用场景
`move (create)`	已定型模式（在3个以上不同日期确认）且包含超过25行参考细节
`move (merge)`	同上，但该主题的概念文章已存在
`drop`	单会话记录——已存在于交接目录中；最多提炼1行定型内容
`update in-place`	过期内容：提及已删除的文件、已关闭的工单、已被取代的决策
`simplify`	内容真实有用，但篇幅是所需的三倍
`keep`	篇幅合理且有留存价值

Step 2 — the move plan (a table, never prose)

步骤2 —— 移动计划（仅用表格，禁止 prose）

#	Section	Lines	Action	Target	Reason
1	…	N	move / merge / drop / simplify / keep	`knowledge/concepts/<slug>.md` or —	…

Close the table with: estimated line savings, and the projected line/byte count afterwards against the caps (180 lines / 32 KB / 3000 chars per line).

序号	章节	行数	操作	目标位置	原因
1	…	N	move / merge / drop / simplify / keep	`knowledge/concepts/<slug>.md` 或 —	…

表格末尾需添加：预估行数节省量，以及操作后预计的行数/字节数与上限（180行 / 32 KB / 每行3000字符）的对比。

Step 3 — PAUSE

步骤3 —— 暂停

Print the plan and ask for approval. Wait for an explicit yes or edits. No writes before that.

打印计划并请求审批。等待明确的同意或修改意见。审批前不得执行任何写入操作。

Step 4 — execute the approved moves, atomically

步骤4 —— 以原子方式执行已批准的移动操作

move (create): write
```
knowledge/concepts/<slug>.md
```
with frontmatter matching
```
knowledge/index.md
```
's spec, then add its one-line entry to that index in the same pass.
move (merge): append under a
```
### From MEMORY.md (YYYY-MM-DD)
```
header — never duplicate a section that already says the same thing.
in MEMORY.md: replace the moved section with a one-line pointer plus a one-line teaser. A move without a pointer orphans the content — that is the failure this audit exists to prevent.
drop: delete; keep at most one distilled line.

move (create)：按照
```
knowledge/index.md
```
的规范写入带前置元数据（frontmatter）的
```
knowledge/concepts/<slug>.md
```
，并在同一操作中向该索引添加一行条目。
move (merge)：在
```
### From MEMORY.md (YYYY-MM-DD)
```
标题下追加内容——绝不重复已存在的相同章节。
在MEMORY.md中：将被移动的章节替换为一行指向目标的链接加一行内容提要。如果移动后没有链接，内容会变成孤立状态——这正是本次审计要避免的失败情况。
drop：删除该章节；最多保留1行提炼后的内容。

Step 5 — the header, then the report

步骤5 —— 更新头部，生成报告

Replace the MEMORY.md current-state header (≤3 lines, dated). Report before/after line and byte counts, every file touched, and save declined candidates to

context/handoffs/memory-audit-deferred-YYYY-MM-DD.md

so the next audit starts from them.

替换MEMORY.md的当前状态头部（≤3行，带日期）。报告操作前后的行数和字节数、所有被修改的文件，并将未通过的候选内容保存到

context/handoffs/memory-audit-deferred-YYYY-MM-DD.md

，以便下次审计从这些内容开始。

Refuse when

拒绝执行的情况

No cap is tripped AND no settled-pattern candidate exists → say "no audit needed" and stop. A SINGLE tripped cap is reason enough to proceed (one 3000-char line qualifies).
The user declines the plan → save it next to the handoffs and stop.

未触发超限且无定型模式候选对象→回复“无需审计”并停止操作。只要有一项超限就足以执行（比如一行达到3000字符）。
用户拒绝计划→将计划保存到交接目录旁并停止操作。

Anti-patterns

反模式

Writing anything before the approval.
Creating a new concept when a keyword grep matches an existing one — merge bias broken.
Promoting a session CHRONICLE into a knowledge article. Concepts hold settled patterns; narrative belongs to handoffs, and the action for it here is
```
drop
```
.
Burying the plan in prose. The table is what makes it reviewable in ten seconds.

审批前执行任何写入操作。
当关键词搜索匹配到现有概念时仍创建新的概念文章——违反合并优先原则。
将会话记录（CHRONICLE）升级为知识文章。概念文章用于存放定型模式；记录内容属于交接目录，此处对应的操作是
```
drop
```
。
用 prose 描述计划。表格是让计划能在10秒内完成审核的关键。