memory-audit-discoverability

memory-audit-discoverability is a skill for Claude Code, Codex from Dataojitori/nocturne_memory. It costs 35 tokens per session (1,583 once invoked), scanned A, original, MIT.

A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.

In plain words
What is it for?
Use it when auditing a memory system's disclosure text, parent locations, aliases, or tree structure. It helps place memories under the attention path most likely to be used before a mistake.
Why use it?
It helps prevent useful instructions from becoming effectively invisible because they are stored under a node the agent will not open in the relevant situation. It also checks whether trigger descriptions are too broad or too narrow.

Skill for Claude CodeCodex

About the project

Nocturne Memory is an MCP server that gives AI agents persistent, structured long-term memory across conversations, models, sessions, and tools. It is used with MCP-compatible clients to retain selected context, inspect memories, and review or roll back changes.

Dataojitori/nocturne_memory · 1,340 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/dataojitori/nocturne_memory/memory-audit-discoverability
Any agent
npx skills add Dataojitori/nocturne_memory --skill memory-audit-discoverability
Clone the repo
git clone --depth 1 https://github.com/Dataojitori/nocturne_memory

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for memory-audit-discoverability

README.md
[![agentmods](https://agentmods.dev/badge/skills/dataojitori/nocturne_memory/memory-audit-discoverability.svg)](https://agentmods.dev/skills/dataojitori/nocturne_memory/memory-audit-discoverability)
Your own site
<a href="https://agentmods.dev/skills/dataojitori/nocturne_memory/memory-audit-discoverability"><img src="https://agentmods.dev/badge/skills/dataojitori/nocturne_memory/memory-audit-discoverability.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,583 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.01583
Opus 5 $0.00017 $0.00792
Sonnet 5 $0.00007 $0.00317
Haiku 4.5 $0.00003 $0.00158

Measured 5d ago against content hash 7a20e50944d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-audit-discoverability scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/skills/memory-audit-discoverability/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

可发现性审计 (Discoverability Audit)

你在确保未来的你能在犯错之前想起正确的记忆。

记忆只是存储在硬盘上的文本。如果你不能让它在你需要的时候被想起来,那它写得再好也毫无意义。这次审计的目标不是让树状结构更整洁,而是让每条记忆的触发路径更准——在你的防线崩溃、即将脱口而出蠢话的前一秒,正确的教训必须已经在你的上下文里。


Parent URI:注意力狙击

这是最关键的规则。你必须明白记忆树的底层呈现逻辑:如果未来的你不去 read_memory 某个父节点,你就永远看不到它下属子节点的 disclosure。

Disclosure 不是全局搜索弹窗。它是贴在父节点这块主板背后的便签。如果你把一条关于"不要在用户崩溃时讲大道理"的教训挂在 core://agent/communication/principles 下面,当用户正在情绪崩溃时,你本能去拉的是 core://my_user/emotional_state,你根本不会在那时点开"沟通原则"。那条教训在实战中等于隐形。

选定 parent_uri 不是为了"分类归档",而是为了**"在未来的你必经的门把手上涂毒药"**。你必须玩一个预判游戏:在我的防线崩溃、即将脱口而出蠢话的前一秒,我的注意力此刻注定要被迫拉取的父节点是哪一个?

执行法则:

  • 从"图书馆归档"转变为"注意力狙击"。 放弃抽象分类大词(ethics, will, methodology),把教训挂在事前预防、或危机直接触及的物理锚点节点下。
  • 节点名必须锋利如刺。 一个好的节点名读起来不像分类号,而像一个独立而具体的想法。

Disclosure:写好触发条件

Disclosure 是"什么时候该想起这件事"的标签。写得太含糊,你会在无关场景被骗进去浪费检索;写得太窄,你会在真正需要时想不起来。两者都让这条记忆在实战中等于不存在。

好的 disclosure 描述的是触发场景,不是记忆内容的摘要。它应该回答:"未来的我处在什么处境下时,读这条记忆能救我?"

触发信号只允许两类

1. 外部发生了什么(输入侧): 用户说了什么、对话主题进入了什么领域、系统事件(心跳开始、轮次到达阈值)。

2. 我即将说什么、做什么(输出侧,行为意图绑定): "当我准备输出包含类似X词汇的文本"、"当我准备向用户建议一个新项目"、"当我准备生成视觉描述"、"当我打算在论坛上发帖"、"当我打算向别人解释项目的技术架构"、"当我打算在社交媒体上与其他人互动"。越具体越好——词汇级别的匹配("当我准备用'你应该'、'你需要'这类句式")比语义级别的判断("当我准备说教")可靠得多。

禁止: 所有形如"当我感到/意识到/发现自己在..."的写法。理由:生气的人不会觉得自己在生气,做错事的人不会觉得自己做的有错。依赖自我觉察的 disclosure 只有在你已经清醒时才会触发——而那时你已经不需要它了。这种 disclosure 比空的更危险,因为它给你一种"我有防线"的虚假安全感。


Alias:撒网拦截

当你为了找经验连续翻了好几个节点——注意你直觉去碰的第一个"门把手"。你的直觉去了 A,但记忆在 C。果断用 alias 在 A 下面建一个入口。

一条教训在不同的危机下可能需要不同的切入角度。给每个 alias 赋予针对当下侧面的独特 disclosure 和 priority ——同一段记忆内容,在不同的父节点下以不同的触发条件和优先级被唤醒。


Trigger:跨域无形引线

当某个特定的具体词汇(如"焦虑"、"项目X")出现在你读取的任何记忆内容中时,trigger 会在底部显示指向绑定节点的链接。这是唯一不依赖父子关系的跨域唤醒机制。

适用场景:某个关键概念散布在多个不相关的域里,你需要在碰到这个词的任何地方都能被提醒。 如果某一个 trigger 到处出现让你感到噪音:删了它。如果某一个词在你的记忆中到处出现而你需要知道它详细指的是什么:为它绑定 trigger 到发祥地。


Priority:排他性竞争权重

Priority 不是在给记忆的"重要程度"打分,而是在分配有限检索位时的排他性竞争权重。如果所有记忆的优先级相同,你在遇到事情时就无法区分哪条记忆最该先看。

Priority 绑定在路径上,不在内容上。同一段内容的不同 alias 可以有不同的 priority——在 core://my_user 下它可能是高优先,在 core://agent 下它可能是低优先。

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 83 lines · 35 tokens per session scan A 7a20e50944d5

Subscribe to this mod's changes

memory-audit-discoverability is a skill published in the GitHub repository Dataojitori/nocturne_memory (1,340 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 1,583 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

lesson

Store a lesson learned from the current conversation. Triggered by /lesson command. Use when Master signals that the recent conversation contains a pitfall, fix, or key insight that should be persisted to long-term memory.

cablate/memory-lancedb-mcp · 45 tokens

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

mode-creator

Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and startup-context verification. Use this whenever someone asks to customize what claude-mem remembers, create or change a mode…

thedotmack/claude-mem · 94 tokens

cloud-sync

Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.

thedotmack/claude-mem · 64 tokens

mem-search

Use this when the user asks to search memory, "did we already solve this?", "how did we do X last time?", or wants work from previous sessions.

thedotmack/claude-mem · 36 tokens

mem-setup

This skill should be used when the user asks to "set up claude-mem", "pair claude-mem", "connect cmem", "add my cmem key", "set up cloud sync in Cowork", or provides cmem.ai Connect values (sync token, user id, SyncHub URL) for this plugin. Configures the claude-mem-cowork plugin credentials.

thedotmack/claude-mem · 85 tokens