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 PAIR-Systems-Inc/goodmem-claude-code-plugin --skill mcpgit clone --depth 1 https://github.com/PAIR-Systems-Inc/goodmem-claude-code-pluginWrote 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/pair-systems-inc/goodmem-claude-code-plugin/mcp)<a href="https://agentmods.dev/skills/pair-systems-inc/goodmem-claude-code-plugin/mcp"><img src="https://agentmods.dev/badge/skills/pair-systems-inc/goodmem-claude-code-plugin/mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pair-systems-inc/goodmem-claude-code-plugin/mcp"><img src="https://agentmods.dev/badge/skills/pair-systems-inc/goodmem-claude-code-plugin/mcp.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.01365 |
| Opus 5.5 | $0.00020 | $0.00546 |
| Sonnet 5.5 | $0.00010 | $0.00273 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
goodmem:mcp 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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GoodMem MCP Tools — Workflow Guide
The GoodMem MCP server exposes tools across multiple API namespaces plus local utilities. Most tools map to a GoodMem REST API endpoint; the utilities (goodmem_configure, goodmem_lookup_model, goodmem_client_info) run locally without contacting the server. Use tools/list to discover exact parameter schemas — this document covers workflow and patterns only.
Setup: The MCP server needs GOODMEM_BASE_URL and GOODMEM_API_KEY. These can be set as environment variables before launch, or configured from chat via goodmem_configure.
TLS: If the server uses a private or self-signed CA, set NODE_EXTRA_CA_CERTS to the absolute path of its PEM certificate file before launch. Restart the MCP connection after changing this setting. An expired or invalid server certificate must be fixed on the server.
Typical workflow
- Configure — call
goodmem_configureif credentials weren't set via env vars. - Register providers — create embedder, LLM, and optionally reranker. Use
goodmem_lookup_modelto check the model registry before creating — it auto-infers provider, endpoint, and dimensionality for known models. - Create a space — a space binds an embedder and chunking config. Memories ingested into a space are automatically chunked and embedded.
- Ingest memories — use
goodmem_memories_create(single) orgoodmem_memories_batch_create(bulk). Supports text, base64-encoded files, or URL references. - Wait for processing — after ingestion, memories are processed asynchronously. Poll with
goodmem_memories_getuntilprocessingStatusisCOMPLETED. - Retrieve —
goodmem_memories_retrieveperforms semantic search. Returns NDJSON with ranked results.
Namespaces
Embedders (goodmem_embedders_*)
Register and manage embedding models. The four SaaS provider types (OpenAI, Cohere, Voyage, Jina) require credentials. OpenAI-compatible endpoints (Anthropic, Google, Mistral) also require credentials when used under the OPENAI provider type. Omitting credentials for a known SaaS endpoint throws an error before the request is sent.
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.
- 1mo ago Changed 85525ffd4755
- 1mo ago First seen · 112 lines · 51 tokens per session scan A 798e6c459238
goodmem:mcp is a skill published in the GitHub repository PAIR-Systems-Inc/goodmem-claude-code-plugin (9 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,365 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
openclaw
Wire mnemostack into OpenClaw as an MCP server, alongside the native OpenClaw memory tools (memorysearch / memoryget). The two coexist — mnemostack handles the hybrid pipeline (Vector + BM25 + Memgraph + Temporal + 8-stage rerank), while the native tools do fast file-scoped retrieval.
claude-code
Wire mnemostack into Claude Desktop (and by extension Claude Code, which reads the same MCP config) as an MCP server.
cursor
Wire mnemostack into Cursor as an MCP server. Cursor reads MCP servers from its own settings, not from Claude Desktop's config.
graph-ask
Ask any natural language question about the memory graph. You generate Cypher directly and execute it. Use when the user has a complex or ad-hoc question that the standard graph tools don't cover.
ingest-audio
Transcribe a local audio or video file using Whisper and ingest it into the memory graph. Use when the user has a local MP3, WAV, M4A, MP4, or similar audio/video file they want to add to their knowledge graph.
ingest
Ingest a file or URL into the memory graph. Handles local files (text, PDF, DOCX, XLSX, images, etc.) and URLs (web pages, YouTube, Wikipedia, RSS). Use when the user wants to add any document or web content to their knowledge graph.