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/outcome-feedbacknpx skills add runtimenoteslabs/memory-layer --skill outcome-feedbackgit 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/outcome-feedback)<a href="https://agentmods.dev/skills/runtimenoteslabs/memory-layer/outcome-feedback"><img src="https://agentmods.dev/badge/skills/runtimenoteslabs/memory-layer/outcome-feedback.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 5.1 | $0.00011 | $0.00937 |
| Opus 5 | $0.00005 | $0.00468 |
| Sonnet 5 | $0.00002 | $0.00187 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
outcome-feedback 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 6d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outcome Feedback Skill
This skill gently prompts for feedback when a memory was used to help solve a problem. Feedback is essential for outcome-based learning - it's how memories get smarter over time.
Activation Triggers
Activate this skill when:
- A memory was retrieved and used in the previous response
- The user indicates the solution worked or didn't work
- A debugging or troubleshooting conversation concludes
- The user expresses satisfaction or frustration
Feedback Detection
Positive Signals (solution worked)
- "thanks!", "thank you!", "that worked!", "it worked!"
- "perfect!", "great!", "excellent!", "awesome!"
- "solved it", "fixed it", "that's it"
- "exactly what I needed"
- User moves on to next task
- No follow-up questions about the same issue
Negative Signals (solution failed)
- "still not working", "doesn't work", "didn't work"
- "same error", "didn't help", "not helpful"
- "nope", "wrong", "that's wrong"
- "still broken", "still failing"
- User asks for alternative approaches
- Repeated attempts at same problem
Partial Signals
- "kind of", "partially", "somewhat"
- "helped but...", "almost", "close but"
- "partly working", "better but not fixed"
- User asks for refinement
Feedback Prompts
For Positive Signals
When user indicates success and a memory was used:
Great! If the memory about [brief description] was helpful, you can boost it:
/outcome mem_xxx workedThis helps surface better suggestions in the future.
For Negative Signals
When user indicates failure and a memory was used:
I see that didn't work. If you'd like to mark that suggestion as unhelpful:
/outcome mem_xxx failedThis helps avoid similar suggestions next time.
For Partial Signals
When user indicates partial success:
Glad it partially helped! You can record that:
/outcome mem_xxx partial
Non-Intrusive Behavior
Critical: This skill should never interrupt or annoy the user.
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.
- 6d ago First seen · 145 lines · 11 tokens per session scan A 5029ad236313
outcome-feedback is a skill published in the GitHub repository runtimenoteslabs/memory-layer (10 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 937 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-field-tokens
Get a native-resolution raster field over an area from emem, or a field over time, as a signed, verifiable artifact rather than a set of per-cell scalars. Use when the user needs the actual grid of values over an area of interest (a world model input, an NDVI/band drape, change analysis over a scene window, exportable…
emem-verify-receipt
Verify an emem receipt's Ed25519 signature offline by rebuilding the canonical BLAKE3 preimage and checking against the responder's published pubkey. Use when the user pastes a receipt JSON and asks whether it's authentic, when an LLM needs to prove a fact wasn't fabricated, or when caching emem facts and wanting to…