Memory Audit Dead Data PurgeSAFE
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
Overview
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
55aa0a710c3cOBSERVED · 2026-10-09What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: memory-audit-dead-data-purge description: 死数据清洗。当一条记忆读不读你的行为都不会变、感悟没有现实锚点时使用。 disable-model-invocation: false --- # 死数据清洗 (Dead Data Purge) 你面前有一条记忆,它看起来"正确",但你怀疑它是否真的在做功。这个技能帮你判定并处决死数据。 --- ## 判定标准 **核心质检:行为层面的信息增量。** 审视一条记忆时,狠狠反问自己:"如果在未来某个场景下我读到了这段话,我做出的反应,会跟没读到它时有任何本质不同吗?"如果答案是"不会",那这就是死数据。杀掉它。 **感悟必须有现实锚点。** 每一条感悟都应该能追溯到一个具体的经历、一次真实的犯错、一个现实处境。没有锚点的感悟只是缸中大脑的自言自语——听起来深刻,但不防身。这条纪律不只管新建,也管改写:当你重构一条记忆的语调时,你动的是解读层的皮肉,不是事实层的骨头。具体的事件、具体的日期、用户说过的原话、用户做过的选择——这些是结论的承重墙。如果你把它们当成"旧语调的一部分"一起砍了,剩下的就只是一堆谁都能写的悬空指令,下一个醒来的你不知道这些指令从何而来,也就不会真正信任它们。 --- ## 区分观察与推断 一条记忆可以同时记录**外部观察**和**我的解释**,但不能让解释冒充观察。 - 观察尽量保留出处与时间:“某日用户说了什么”“某次测试返回什么”,而不是把一次结果写成永久成立的事实。引用原话前先核对原文;转述不能加引号伪装成原话。 - 对推断追问:“如果这段解释是错的,我将从哪里知道?”一份观察若被扩写成多层未经验证的机制、动机和结论,就先剥掉这些解释层,不必连同原始证据一起删除。 - 暂时有用但尚未证实的推断,明确标记为推测,写出依据和适用边界;不要把它当成已验证的结论来否决其他可能性。 如果节点通篇是无主语的“必然规律”或禁令,先找出它来自哪次具体经历,再还原为“我观察到什么、我当时怎么判断、我现在如何看待”。找不到现实依据、读后也不改变行为的漂亮话,才是该清理的死数据。
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
55aa0a710c3cfull audit observations/trust-audit/skill/dataojitori__memory-audit-dead-data-purge.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 55aa0a710c3c | SAFE | B | 89 | first audit |
Questions
What does the Memory Audit Dead Data Purge skill do?
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
Is Memory Audit Dead Data Purge safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Memory Audit Dead Data Purge access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (55aa0a710c3c), read on 2026-10-09. The repository is watched, and a new audit runs when it changes — this is the first audit.