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/a2z2k26/semantic-memory-mcp/memorygit clone --depth 1 https://github.com/a2z2k26/semantic-memory-mcpWhat 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 | $0.00900 |
| Opus 5 | $0.00005 | $0.00450 |
| Sonnet 5 | $0.00002 | $0.00180 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
memory 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Memory Command
Execute memory operations against the shared Semantic Memory MCP server.
Available Actions
Core Memory Operations
store- Store a memory entry:/memory store mykey '{"data": "value"}'retrieve- Get a memory by key:/memory retrieve mykeysearch- Search memories:/memory search "search query"list- List recent memories:/memory liststats- Get storage statistics:/memory statshealth- Check system health:/memory health
Team Coordination
team- Show team status and context:/memory teamhandoff- Create work handoff for another agent:/memory handoff task-namedecide- Record a decision with rationale:/memory decide "Use SQLite" "Better concurrency"
Sandbox Integration
sync- Check Memory Bridge status for E2B sandboxes:/memory syncsandboxes- List sandbox memories:/memory sandboxes
Usage Examples
/memory store user:preferences '{"theme": "dark", "lang": "en"}'
/memory retrieve user:preferences
/memory search "API configuration"
/memory list
/memory stats
/memory health
/memory team
/memory handoff feature-implementation
/memory decide "Use FTS5 for search" "Best balance of simplicity and performance"
/memory sync
/memory sandboxes
When to Use Memory
- Store important findings - When you discover something that future agents or sessions should know
- Record decisions - Document architectural decisions, design choices, rationale
- Share context - Pass information between different Claude sessions/worktrees
- Track artifacts - Store code snippets, configurations, outputs for reference
- Create handoffs - When passing incomplete work to another agent
- Check sandbox results - Access work from E2B sandbox agents
Action: $ARGUMENTS.action
Key: $ARGUMENTS.key Value: $ARGUMENTS.value Query: $ARGUMENTS.query Decision: $ARGUMENTS.decision Rationale: $ARGUMENTS.rationale
Based on the action requested, use the appropriate MCP tool:
- For
store: Usememory_storewith the key and parsed JSON value - For
retrieve: Usememory_retrievewith the key - For
search: Usememory_searchwith the query - For
list: Usememory_list - For
stats: Usememory_stats - For
health: Usesystem_health - For
team: Useteam_get_status - For
handoff: Useteam_store_contextwith keyhandoff:{key}containing:- status: 'in_progress'
- handoffAt: current timestamp
- description: Ask user what to include
- completed: List of completed items
- remaining: List of remaining items
- notes: Any relevant context
- For
decide: Useteam_record_decisionwith:- decision: The decision text
- rationale: The rationale provided
- agentId: Current agent identifier
- For
sync: Check Memory Bridge server at http://127.0.0.1:3847/status Report whether bridge is running and show active sandboxes - For
sandboxes: Usememory_searchwith query "sandbox:*" List all memories from E2B sandboxes
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 First seen · 99 lines · 9 tokens per session scan A c17a048b08f9
memory is a command published in the GitHub repository a2z2k26/semantic-memory-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 900 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 2026-08-31.
Other commands, from other repositories
upgrade-webkit
Upgrade Bun's WebKit fork to the latest upstream version of WebKit.
riskreview
The user invoked the /riskreview facade command from the risk-review-pipeline pack.
dev
Runs Vendure in development mode. By default it starts three processes: the GraphQL server (ts-node ./src/index.ts), the worker (ts-node ./src/index-worker.ts), and the dashboard (a Vite dev server).
start
Runs a project that has already been compiled with vendure build.
update
Use when: search results seem noisy, after bulk imports, or for periodic memory/registry maintenance.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.