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 skills add verygoodplugins/mcp-automem --skill skill-mcpgit 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/skills/verygoodplugins/mcp-automem/skill-mcp)<a href="https://agentmods.dev/skills/verygoodplugins/mcp-automem/skill-mcp"><img src="https://agentmods.dev/badge/skills/verygoodplugins/mcp-automem/skill-mcp.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 19 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00016 | $0.00471 |
| Opus 5 | $0.00008 | $0.00235 |
| Sonnet 5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
automem scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Do not fall back to raw curl commands in this mode unless the user explicitly asks for the legacy setup. What it actually says
AutoMem
Use the typed AutoMem tools exposed through mcporter.
Natural language mappings
remember ...orstore this->automem_store_memorywhat do you know about ...orrecall ...->automem_recall_memoryupdate memory ...->automem_update_memorydelete memory ...-> recall first when needed, thenautomem_delete_memorylink these memories ...->automem_associate_memoriesis memory healthy?->automem_check_health
Slash command behavior
Interpret /automem remember ..., /automem recall ..., /automem update ..., and /automem delete ... as requests to use the matching AutoMem tool flow.
Rules
- Recall preferences first with
tags: ["preference"],sort: "updated_desc", andformat: "detailed"when collaboration style or user habits matter. - For task context, prefer one semantic query built from the user's actual nouns. Do not hard-gate recall with default tags unless the conversation is clearly scoped to an unambiguous project slug.
- For debugging, recall with the error symptom as a semantic query and NO tags — bugfix/solution tagging is incomplete, and a tag gate hides cross-corpus fixes.
- Tags are a hard gate. Use bare tags only, and avoid platform tags like
openclaw. - Store only durable information worth reusing later.
- Default project tags are for stored memories. Recall should stay semantic unless tags are explicitly needed.
- Use
memory-coreand file-backed workspace memory for local notes and raw transcripts; AutoMem is the semantic cross-session layer. - If delete targets are ambiguous, show the likely matches and ask for confirmation before deleting.
- Do not fall back to raw curl commands in this mode unless the user explicitly asks for the legacy setup.
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.
- 8d ago First seen · 38 lines · 16 tokens per session scan A da1b69edbf6c
automem is a skill published in the GitHub repository verygoodplugins/mcp-automem (64 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 471 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
omnigraph
Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…
codebase-memory
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…
context-recovery
Recovers project handoff context from local Codex, Claude Code, Gemini, CodeBuddy, and codexmate-derived sessions. Use when the user asks what happened in prior project/PR/branch/file/error work, needs a handoff brief, wants old decisions or validations recovered, or asks to summarize cross-session project activity…
refactor-memory
Use when about to refactor or refine Claude Code auto memory, the MEMORY.md index and its topic files, to delete stale or derivable memories, fix inconsistencies, promote standing decisions to CLAUDE.md or rules, and regroup the index. Not for CLAUDE.md or rules files themselves.
Wikimate Query
A read-only search and question-answering workflow for a personal Wikimate knowledge base, made from an Obsidian note vault and a Notion index. It checks that note files really exist before using them as evidence.
Wikimate Summarize
A note-summarizing workflow for Wikimate, a personal note system. It creates a one-line summary or, when needed, a separate atomic note containing the main idea.