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.
npx agentmods add skills/zts212653/clowder-ai/memory-navigationnpx skills add zts212653/clowder-ai --skill memory-navigationgit clone --depth 1 https://github.com/zts212653/clowder-aiWrote 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.
[](https://agentmods.dev/skills/zts212653/clowder-ai/memory-navigation)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/memory-navigation"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/memory-navigation.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00125 | $0.01433 |
| Opus 5 | $0.00063 | $0.00717 |
| Sonnet 5 | $0.00025 | $0.00287 |
| Haiku 4.5 | $0.00013 | $0.00143 |
Grade A, and why
memory-navigation 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-navigation
记忆系统三入口路由决策 + 噪音控制 + 加载时机。F188 Phase F (AC-F6) 配套 skill。
单一真相源:
../.cat-cafe-shared-refs/memory-routing-partial.md
When to load
按 cold-start 关键词 + 检索 fallback 信号加载:
- 接到任务感觉"没先验"——不知道找什么 keyword
- 压缩后需要重建上下文(hook 触发"compact"事件)
- "我记得最近讨论过 X" / "好像之前提过" / "最近发生了什么"
search_evidence多次 low_hit 或 no_match 后- 处理新 thread 的 cold-start,需要快速建立上下文
Not for:
- 已经有精确 anchor 想直接 Read 源文件 → 直接 Read
- 代码符号查找 →
Grep/ LSP - 全文匹配 →
Grep
三入口决策树
开工 / 接到任务 / 压缩恢复
↓
我知道精确 anchor (F186/ADR-019 等)?
├─ 是 → graph_resolve(anchor, depth=1)
│ 看 anchor 周边的引用、wikilink、F-ref 关系
│
└─ 否 ↓
我大概知道找什么、有概念关键词?
├─ 是 → search_evidence(query, mode="hybrid")
│ 语义召回;low-hit 时会自动 nudge 你试其他入口(KD-7)
│
└─ 否 ↓
我只是想"扫一眼最近发生什么"?
├─ 是 → list_recent(scope="all", since="7d")
│ 不带 query,按时间倒序看最近活动
│
└─ 否 → 用 cross-cat-handoff 找人问,或问operator澄清需求
噪音控制
graph_resolve 边爆炸防护:
depth: 默认 1,上限 3。深度 ≥2 时 fan-out 容易上百relations: filter 子集- 只看强关系:
["wikilink", "doc_link"] - 只看 F-编号引用:
["feature_ref"] - 只看 frontmatter related:
["related_to"]
- 只看强关系:
- 候选列表 ≥5 项时:先选高 confidence anchor 看一跳,再决定深挖
list_recent 时间窗口选择:
- 压缩恢复 / "最近发生什么":
since="24h"或"7d" - 周回顾 / 找一周前的讨论:
since="7d" - 找最近 PR / merge:
scope="docs"+since="3d" - 完全没头绪:
scope="all"+since="7d"+limit=20
search_evidence mode 速查(详见 CLAUDE.md 「检索策略」段):
- 精确 ID →
lexical - 日常用 →
hybrid - 跨语言 →
semantic
7-tool family 互相 cross-reference
每个工具的 description 互相指向(4.6 review #3 缓解工具数量膨胀):
search_evidence— semantic / fuzzy findgraph_resolve— precise anchor / relationslist_recent— zero-prior / scan recentlist_session_chain— 看完整对话链read_session_digest— 看会话摘要read_session_events— 看会话事件read_invocation_detail— 看单次 invocation 全事件
关键纪律
search_evidence不是默认万能——历史 hook 只提它是 one-trick legacy。三入口按场景选才是 Phase F 设计。- 看到 search_evidence payload 的 🧭 Memory navigation nudge——这是低命中信号,立刻试 graph 或 recent,不要继续盲搜。
- 猫的认知成本来自"工具间互相找"而非"工具总数",cross-reference 直接解决。
- 没有 anchor 就走 recent——比反复构造关键词 prompt search 高效。
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.
- 4d ago First seen · 128 lines · 125 tokens per session scan A 949d569085ec
memory-navigation is a skill published in the GitHub repository zts212653/clowder-ai (2,880 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 1,433 once invoked, about $0.0006 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.
Other skills, from other repositories
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.…
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…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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.
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…