proactive-memory-judgment

proactive-memory-judgment is a skill for Claude Code, Codex from zts212653/clowder-ai. It costs 69 tokens per session (1,391 once invoked), scanned A, original, MIT.

A decision guide for judging whether a person mentioned in a conversation should receive a proactive memory proposal. It checks identity, useful continuity, evidence, timing, and whether a proposal would duplicate existing memory.

In plain words
What is it for?
Use it to assess person-memory opportunities, corrections, relationship changes, and important interactions, while producing a proposal, a defer decision, or an abstention record.
Why use it?
It reduces the risk of turning a bare name, guess, or third-party statement into a stored personal fact. When evidence is insufficient or the timing is wrong, it supports declining or postponing the proposal.

Skill for Claude CodeCodex

About the project

Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.

zts212653/clowder-ai · 2,894 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/zts212653/clowder-ai/proactive-memory-judgment
Any agent
npx skills add zts212653/clowder-ai --skill proactive-memory-judgment
Clone the repo
git clone --depth 1 https://github.com/zts212653/clowder-ai

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 proactive-memory-judgment

README.md
[![agentmods](https://agentmods.dev/badge/skills/zts212653/clowder-ai/proactive-memory-judgment.svg)](https://agentmods.dev/skills/zts212653/clowder-ai/proactive-memory-judgment)
Your own site
<a href="https://agentmods.dev/skills/zts212653/clowder-ai/proactive-memory-judgment"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/proactive-memory-judgment.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,391 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 $0.00069 $0.01391
Opus 5 $0.00034 $0.00696
Sonnet 5 $0.00014 $0.00278
Haiku 4.5 $0.00007 $0.00139

Measured 5d ago against content hash 0e3f93b6957e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proactive-memory-judgment 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.

cat-cafe-skills/proactive-memory-judgment/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proactive Memory Judgment

这是一道语义判断门,不是词频分类器。单次合格线索足以进入判断,不要求重复;Phase A 频率 nudge 只说明“跨 thread 出现过”,不证明重要性,也不决定 memory lane。

五道门

按顺序判断;任一道不通过,都不要把不确定内容升级成更深的 intervention。

1. 甜甜圈资格

主体必须是可命名或可消歧的第三方人物,并且当轮至少出现一种 continuity value:

  • 稳定身份或 owner↔person 关系;
  • 对既有记忆的纠正;
  • 未来对话确实可能用到的事实;
  • 值得保留的重要互动或明确 owner assessment。

裸人名 / proper noun alone、taste、背景 corpus 扫描都不是机会。workspace name、handle 或 alias 只属于 Entity;若同一句同时包含 workspace alias 与 owner-private 事实,分别走 Entity 与 F276,分别审批。

2. 证据

使用 F282 typed source bundle 与 assertion role。只让证据支持它真正能证明的字段:

  • owner message 可支持 reported_factuser_assessment
  • third-party quote 保持 quoted_third_party,不得洗成 event fact;
  • agent inference 不得 materialize;
  • 时间、headline、duration 等 interaction fields 必须有对应 typed evidence。

证据不足时不猜、不补写 owner 没说过的话;若本轮已形成 opportunity exposure,记录 cat_cafe_record_proactive_memory_abstention({ reasonCode: "insufficient_owner_evidence" })

3. 时机

只在自然回复边界行动;同一轮至多一张 person-memory card。已有 pending 时不要制造重复卡; 需要纠正 pending 时按 F276 immutable replacement 契约提交完整新快照。人物已登记不等于没有 新关系/互动:若当前任务适合,立即提完整 delta 卡;若提卡会打断主任务且 exact owner sources 已经明确,调用 cat_cafe_defer_person_memory_delta,只传 subject、source coordinates 与稳定 clientRequestId。defer 不存正文,daily clerk 也不会扫描对话,只会把 exact refs 转回普通审批卡。

4. 授权

只能创建可拒绝的 F276 提案,不得静默物化或静默写入 canonical memory。owner 选择 exact items 后才 materialize;隐私、source scope 或权限不清时 fail closed。

5. 降档表达

不确定性越高,intervention 越浅。defer 是“证据足、人物已登记、只是当前不宜打断”,不是 证据不足的垃圾桶。确认不应 proposal/defer 时,只记录一条 enum-only abstention,不写解释、 原文、坐标或自定义 reason:

情形 reasonCode
没有 continuity value not_continuity_valued
owner 证据不足 insufficient_owner_evidence
当前时机不自然且不是可安全 defer 的 known-person delta,或本轮已有卡 bad_timing
需要的授权不存在 authorization_boundary
已有 pending,或当前内容只重复既有人物事实、没有新 delta already_registered_or_pending
privacy / source scope 不可确认 privacy_boundary

调用形式:

cat_cafe_record_proactive_memory_abstention({ reasonCode })

Read the full file on GitHub · 119 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 · 119 lines · 69 tokens per session scan A 0e3f93b6957e

Subscribe to this mod's changes

proactive-memory-judgment is a skill published in the GitHub repository zts212653/clowder-ai (2,894 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,391 once invoked, about $0.0003 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens