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.
git clone --depth 1 https://github.com/studiomeyer-io/studiomeyer-marketplaceWrote 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/commands/studiomeyer-io/studiomeyer-marketplace/memory-learn)<a href="https://agentmods.dev/commands/studiomeyer-io/studiomeyer-marketplace/memory-learn"><img src="https://agentmods.dev/badge/commands/studiomeyer-io/studiomeyer-marketplace/memory-learn.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 | $0.00017 | $0.00314 |
| Opus 5 | $0.00009 | $0.00157 |
| Sonnet 5 | $0.00003 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
memory-learn 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 3d 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.
What it actually says
The user wants to save something to memory: $ARGUMENTS
- Decide the category based on the content:
mistake: something that went wrong and must not be repeatedpattern: a recurring technique or structure worth reusinginsight: a non-obvious realizationresearch: findings from investigationarchitecture: system-level design factworkflow: how a process should runsecurity: a security-relevant fact
- Call
nex_learnfrom thestudiomeyer-memoryMCP server with:content: the full content from the usercategory: from step 1confidence: 0.9 for factual user-provided info, 0.7 for inferredproject: pass it through when the user named one. Left out, the save inherits the session's project, which is usually what you want. For something that holds regardless of project, pass"global".
- If the server returns a
duplicate_offield, tell the user that a similar learning already exists and link to it. Do not complain. This is the gatekeeper working correctly. - Confirm the save with one line: category + first 60 chars of the content.
Match the user's language.
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.
- 3d ago Changed 30484316cb4b
- 8d ago First seen · 25 lines · 17 tokens per session scan A bf34f65fbf06
memory-learn is a command published in the GitHub repository studiomeyer-io/studiomeyer-marketplace (2 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 314 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 commands, from other repositories
pane
Open the Engram graph pane — make sure the machine core is running and share the URL.
save
Manually save current context as a memo to the memex vault.
status
Show memex statistics and status including projects, memos, and pending items.
digest
Digest this project into Engram — an explicit, one-time ingestion of the current working tree into typed memory nodes.
log
Command "log" from allenc84/sapience, covering /log — judgment ledger command, routing, new assessment: /log, review: /log review [domain] and resolve: /log resolve.
recall
Search the engineering memlog and inject the top matching prior lessons. Use when you suspect a recurring issue.