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/cablate/memory-lancedb-mcp/lessonnpx skills add cablate/memory-lancedb-mcp --skill lessongit clone --depth 1 https://github.com/cablate/memory-lancedb-mcpWhat 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 | $0.00045 | $0.00278 |
| Opus 5 | $0.00023 | $0.00139 |
| Sonnet 5 | $0.00009 | $0.00056 |
| Haiku 4.5 | $0.00005 | $0.00028 |
Grade A, and why
lesson 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 yesterday.
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.
What it actually says
Lesson Extraction & Storage
When triggered, extract and store lessons from the recent conversation context.
Steps
- Scan recent context — identify the pitfall, bug fix, or key insight just discussed
- Store technical layer (category: fact, importance ≥ 0.8):
Pitfall: [symptom]. Cause: [root cause]. Fix: [solution]. Prevention: [how to avoid]. - Store principle layer (category: decision, importance ≥ 0.85):
Decision principle ([tag]): [behavioral rule]. Trigger: [when]. Action: [what to do]. - Verify —
memory_recallwith anchor keywords to confirm both entries retrievable - Report — tell Master what was stored (brief summary)
Rules
- Keep entries short and atomic (< 500 chars each)
- If the lesson also affects a checklist or SKILL.md, update those files too
- If no clear lesson is found in recent context, ask Master what to store
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.
- yesterday First seen · 29 lines · 45 tokens per session scan A e02c38922b43
lesson is a skill published in the GitHub repository cablate/memory-lancedb-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 278 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 2026-08-31.
Other skills, from other repositories
using-cortex-memory
Use when connected to a Cortex memory MCP server (tools named memorize, recall, recallabout, recalltimeline, listmemories, forget) — at session start, before asking the user for facts they may have shared before, after learning durable facts/preferences/decisions, when the user says "remember/recall/forget", or when…
memory-audit
记忆审计入口。当我主动决定审视记忆质量时，先读此文件判断应使用哪个子技能。.
memory-audit-belief-duel
信念对决。当父子节点内容冲突、或两条你都认可的记忆逻辑上不能并存时使用。.
memory-audit-discoverability
可发现性审计。当disclosure写法有问题、parent放错、alias缺失、子节点过多时使用。.
memory-audit-pattern-extraction
模式提取与失效解药分析。当发现多条记忆在讲同一个教训，或发现自己在一而再再而三地犯同样的错误时使用。.
memory-audit-node-decomposition
节点分解。当一个节点体积过大、或塞了多个不相关概念导致disclosure无法覆盖时使用。.