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 skills/danielsimonjr/memory-mcp/memorynpx skills add danielsimonjr/memory-mcp --skill memorygit clone --depth 1 https://github.com/danielsimonjr/memory-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/danielsimonjr/memory-mcp/memory)<a href="https://agentmods.dev/skills/danielsimonjr/memory-mcp/memory"><img src="https://agentmods.dev/badge/skills/danielsimonjr/memory-mcp/memory.svg" alt="Measured on agentmods" 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 | $0.00155 | $0.01936 |
| Opus 5 | $0.00077 | $0.00968 |
| Sonnet 5 | $0.00031 | $0.00387 |
| Haiku 4.5 | $0.00015 | $0.00194 |
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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
A judgment layer over the memory-mcp server's knowledge-graph tools — entity/relation/observation CRUD, search, tagging, importance scoring, and graph maintenance, backed by sqlite (or JSONL). This skill adds no tools of its own: every action below is one of the server's existing MCP tools, called with the plugin-prefixed name mcp__plugin_memory-mcp_memory-mcp__<tool>. Its job is to steer you toward the right operation for a given intent — search before create, tag and score for retrieval later, maintain the graph periodically — rather than reinvent memory management ad hoc.
Skill root: this skill ships inside the memory-mcp plugin (repo danielsimonjr/memory-mcp, skills/memory/). Slash trigger: /memory.
When to use / not
Use this skill for anything that touches the knowledge graph as long-term memory: storing a fact or decision, recalling what's known about a topic, searching or browsing entities, tagging/scoring/deduping/compressing the graph, indexing a project's current state into memory, or migrating the storage backend between JSONL and SQLite.
Not for the repo's general dev-utility commands — chunk (file chunking for context-limited edits), cton/compress-for-context, commit, deps (dependency graphs), graph, search (repo code search) — those are separate, unrelated commands and out of scope here even though some share a word ("graph", "search") with graph operations. If in doubt: does the action read/write the memory-mcp knowledge graph? If not, this skill doesn't apply.
Core memory operations
The server exposes a large tool surface, but everyday graph work reduces to a small set of operations. All names below are called as mcp__plugin_memory-mcp_memory-mcp__<tool>; if a tool isn't loaded, fetch its schema via ToolSearch select:mcp__plugin_memory-mcp_memory-mcp__<tool>.
| Intent | Tool |
|---|---|
| Graph stats (entity/relation counts, types) | get_graph_stats |
| Search entities by query/tags/importance | search_nodes |
| Open specific entities by name | open_nodes |
| Read the entire graph (sparingly — see Gotchas) | read_graph |
| Find potential duplicate entities | find_duplicates |
| Add an observation to an existing entity | add_observations |
| Create a new entity | create_entities |
| Create a relation between entities | create_relations |
| Add tags to an entity | add_tags |
| Set an entity's importance (0–10) | set_importance |
| Delete an entity | delete_entities |
| Delete specific observations | delete_observations |
| Merge two+ entities into one | merge_entities |
| Compress the graph (merge near-duplicates) | compress_graph |
What ships with it
1 file 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.
- 4d ago First seen · 83 lines · 155 tokens per session scan A 1ba739f7def6
memory is a skill published in the GitHub repository danielsimonjr/memory-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 155 tokens to every session and 1,936 once invoked, about $0.0008 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 skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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…