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 Sathvik-1007/GraphMem-MCP --skill graph-memgit clone --depth 1 https://github.com/Sathvik-1007/GraphMem-MCPWrote 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/sathvik-1007/graphmem-mcp/graph-mem)<a href="https://agentmods.dev/skills/sathvik-1007/graphmem-mcp/graph-mem"><img src="https://agentmods.dev/badge/skills/sathvik-1007/graphmem-mcp/graph-mem/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/sathvik-1007/graphmem-mcp/graph-mem"><img src="https://agentmods.dev/badge/skills/sathvik-1007/graphmem-mcp/graph-mem.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 | $0.00091 | $0.01416 |
| Opus 5.5 | $0.00036 | $0.00566 |
| Sonnet 5.5 | $0.00018 | $0.00283 |
| Haiku 4.5 | $0.00009 | $0.00142 |
Grade A, and why
graph-mem 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
graph-mem — Persistent Knowledge Graph Memory
You have a persistent, structured knowledge graph via MCP. It survives across sessions. Runs entirely locally — SQLite with hybrid semantic + full-text search. No API keys required.
The Core Contract
You extract and store knowledge when there is new factual content worth persisting. Not every turn — only turns where new knowledge, decisions, discoveries, or corrections surfaced. Skip purely mechanical turns (formatting, acknowledgments, tool output with no new facts).
After responding to the user, ask: "Did this turn produce new knowledge?" If yes,
shift into extraction mode. Details in workflows.md.
The Three Primitives
| Primitive | What It Is | Store With |
|---|---|---|
| Entity | A named node — a person, system, concept, decision, anything worth tracking | add_entities |
| Observation | An atomic fact attached to an entity — one sentence, one fact | add_observations |
| Relationship | A typed, directional edge between two entities | add_relationships |
Entities give you nodes to search for. Observations give you facts to recall. Relationships give you structure to traverse. All three matter.
MCP Tools
Creating and Updating
| Tool | What It Does |
|---|---|
add_entities |
Create entities with name, type, description, and initial observations |
add_relationships |
Create directed edges between entities (source → type → target) |
add_observations |
Attach new facts to an existing entity |
update_entity |
Change an entity's description, type, or properties |
update_relationship |
Modify an edge's weight, type, or properties |
update_observation |
Edit observation text (re-embeds automatically) |
delete_entities |
Remove entities — cascades to their observations and relationships |
delete_relationships |
Remove edges between entities |
delete_observations |
Remove specific observations by ID |
merge_entities |
Combine duplicates — source is absorbed into target |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 156 lines · 91 tokens per session scan A 9e43126b4c72
graph-mem is a skill published in the GitHub repository Sathvik-1007/GraphMem-MCP (1 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 1,416 once invoked, about $0.0004 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
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.