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/claude-plugins/memory-storegit clone --depth 1 https://github.com/verygoodplugins/claude-pluginsWhat 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 | $0.00010 | $0.00332 |
| Opus 5 | $0.00005 | $0.00166 |
| Sonnet 5 | $0.00002 | $0.00066 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
memory-store 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 yesterday.
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 Store
Store important information for future recall:
-
Identify Memory Type:
- Decision (0.9): Architecture, library, pattern choices
- Insight (0.8): Bug fixes, root causes, learnings
- Pattern (0.7): Reusable approaches, best practices
- Preference (0.6-0.8): User preferences, style choices
- Context (0.5-0.7): Feature summaries, notes
-
Format Content:
Brief title. Context and details. Impact/outcome. -
Store with Tags:
mcp__memory__store_memory({ content: "[formatted content]", type: "[Decision|Insight|Pattern|Preference|Context]", importance: [0.5-1.0], tags: ["project-name", "component", "type", "YYYY-MM"], metadata: { files_modified: ["relevant/files.ts"], // Additional context as needed } }) -
Create Associations (if related memories exist):
mcp__memory__associate_memories({ memory1_id: "[new-memory-id]", memory2_id: "[related-memory-id]", type: "RELATES_TO", strength: 0.8 })
Ask the user what they want to store if not clear from 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.
- yesterday First seen · 46 lines · 10 tokens per session scan A 7c0d4d51a4d9
memory-store is a command published in the GitHub repository verygoodplugins/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 332 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
triage
AI-powered reachability triage for dependency vulnerabilities. Scans for CVEs then searches your source code to estimate whether each vulnerable API is actually called. Outputs a prioritized FOUNDINSOURCE / UNCERTAIN / NOTFOUNDINGREP report.
review
Adversarial security and architectural review. The Devil's Advocate identifies security threats and the fragilities that enable collapse.
excalidraw
Generate or modify Excalidraw diagrams from descriptions or code analysis.
promote
Move .memory/ artifacts to permanent knowledge locations.
speak
Read the last response aloud using TTS.
autospeak
Toggle automatic text-to-speech for all responses.