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/runtimenoteslabs/memory-layer/memory-retrievalnpx skills add runtimenoteslabs/memory-layer --skill memory-retrievalgit clone --depth 1 https://github.com/runtimenoteslabs/memory-layerWrote 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/runtimenoteslabs/memory-layer/memory-retrieval)<a href="https://agentmods.dev/skills/runtimenoteslabs/memory-layer/memory-retrieval"><img src="https://agentmods.dev/badge/skills/runtimenoteslabs/memory-layer/memory-retrieval.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 | $0.00015 | $0.00778 |
| Opus 5 | $0.00008 | $0.00389 |
| Sonnet 5 | $0.00003 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
memory-retrieval 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Retrieval Skill
This skill automatically activates when the conversation suggests past context would be helpful. It searches the Memory Layer and injects relevant memories into the response.
Activation Triggers
Activate this skill when the user:
Past Decisions
- "what did we decide about..."
- "why did we choose..."
- "what was the decision on..."
- "what did we agree..."
Conventions & Standards
- "what's our convention for..."
- "what's the standard..."
- "how do we usually..."
- "what's our pattern for..."
Previous Work References
- "last time we..."
- "we discussed..."
- "as I mentioned..."
- "remember when we..."
Project Patterns
- "how do we handle..."
- "what's the approach for..."
- "what's the best way to..."
Error Recognition
- Error messages that might have been solved before
- Stack traces from familiar components
- Issues in previously-discussed areas
Retrieval Process
-
Extract query keywords from the user's message
- Focus on technical terms, component names, patterns
- Include project context from current working directory
-
Search Memory Layer:
mem search "<keywords>" --project "$PWD" --limit 5 --format context -
Filter by relevance:
- Prioritize memories with positive outcome scores (> 0.3)
- Match category to query type:
- Errors → troubleshooting
- Style questions → convention
- Design questions → architecture, decision
-
Inject into response:
- Prefix relevant findings naturally
- Cite memory IDs for transparency
Response Integration
When memories are found, integrate them naturally at the start of your response:
For High-Confidence Memories (score > 0.3)
Based on established project knowledge: [brief summary of relevant memory]
For Normal Memories
From previous context: [brief summary]
For Multiple Memories
Based on project knowledge:
- [Memory 1 summary]
- [Memory 2 summary]
Then proceed with the response, incorporating the memory context.
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 · 124 lines · 15 tokens per session scan A 502799788084
memory-retrieval is a skill published in the GitHub repository runtimenoteslabs/memory-layer (10 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 778 once invoked, about $0.0001 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
openclaw
Wire mnemostack into OpenClaw as an MCP server, alongside the native OpenClaw memory tools (memorysearch / memoryget). The two coexist — mnemostack handles the hybrid pipeline (Vector + BM25 + Memgraph + Temporal + 8-stage rerank), while the native tools do fast file-scoped retrieval.
claude-code
Wire mnemostack into Claude Desktop (and by extension Claude Code, which reads the same MCP config) as an MCP server.
cursor
Wire mnemostack into Cursor as an MCP server. Cursor reads MCP servers from its own settings, not from Claude Desktop's config.
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
emem-recall-polygon
Recall signed Earth-observation facts at every cell inside a user-supplied polygon. Use when the user asks about an extent rather than a point — "what's the average NDVI inside this watershed", "show me precipitation across the Western Ghats", "what's the elevation profile of this region". Accepts a polygon as [lng…
emem-locate-and-recall
Resolve a free-form place name to an emem cell64 and recall signed Earth-observation facts at that location. Use when the user asks about current weather, vegetation index, elevation, soil properties, or any other geospatial measurement at a named place ("what's the temperature in Bengaluru", "how high is Denali"…