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 commands/verygoodplugins/mcp-automem/memory-recallgit clone --depth 1 https://github.com/verygoodplugins/mcp-automemWrote 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/verygoodplugins/mcp-automem/memory-recall)<a href="https://agentmods.dev/commands/verygoodplugins/mcp-automem/memory-recall"><img src="https://agentmods.dev/badge/commands/verygoodplugins/mcp-automem/memory-recall.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 | $0.00009 | $0.00338 |
| Opus 5 | $0.00005 | $0.00169 |
| Sonnet 5 | $0.00002 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
memory-recall 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.
What it actually says
Memory Recall
Perform context-aware memory search:
-
Analyze Context:
- User's actual nouns: project names, products, files, errors, people, tools
- Whether this is a preferences recall, project-context recall, or debugging recall
- Whether a tag gate would help or would hard-filter away relevant results
-
Execute Recall:
Use the
recall_memorymemory tool with an appropriate strategy:Preferences:
recall_memory({ tags: ["preference"], limit: 20, sort: "updated_desc" })Project / task context:
recall_memory({ query: "[proper nouns, file names, tool names, specific topics from the user's request]", tags: ["project-slug"], // drop if ambiguous time_query: "last 90 days", limit: 30 })Debug Similar Errors (no tag gate — bugfix/solution tagging is incomplete and a hard gate hides cross-corpus fixes):
recall_memory({ query: "[error message keywords]", limit: 20 })Use
queries[]only for genuinely multi-topic questions. Prefer one good query over templated multi-query recall. -
Present Results: Show memories with:
- Content summary
- Creation date
- Importance score
- Actionable insights
Present the information naturally, not as a database query result.
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 · 54 lines · 9 tokens per session scan A c9c03f4de507
memory-recall is a command published in the GitHub repository verygoodplugins/mcp-automem (64 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 338 once invoked, about $0.0000 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 commands, from other repositories
context
Show recent memory context for this project.
recall
Search Rembric for prior context matching the query.
remember
Save text as a project memory in Rembric.
memory
Interact with shared Semantic Memory MCP system.
make-plan
Create an implementation plan with documentation discovery.
do
Execute a plan using subagents for implementation.