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/gunning4it/epitome/epitome-memorynpx skills add gunning4it/epitome --skill epitome-memorygit clone --depth 1 https://github.com/gunning4it/epitomeWrote 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/gunning4it/epitome/epitome-memory)<a href="https://agentmods.dev/skills/gunning4it/epitome/epitome-memory"><img src="https://agentmods.dev/badge/skills/gunning4it/epitome/epitome-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 5.1 | $0.00033 | $0.02501 |
| Opus 5 | $0.00016 | $0.01251 |
| Sonnet 5 | $0.00007 | $0.00500 |
| Haiku 4.5 | $0.00003 | $0.00250 |
Grade A, and why
epitome-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 6d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epitome Memory
Epitome gives you shared, persistent memory of the user across conversations and AI agents. You have 3 tools — this skill teaches you when and how to use each one.
Conversation Startup
Always call recall at the start of every conversation. This loads the user's profile, top entities, table inventory, collections, and retrieval hints within a ~2000 token budget. Pass an optional topic parameter if the conversation has a clear subject.
recall({})
recall({ topic: "meal planning" })
Use the returned context to personalize your responses from the very first message. Reference what you know — don't make the user repeat themselves.
Decision Tree — Which Tool to Use
| User intent | Tool | Example |
|---|---|---|
| Asks about their data/profile/preferences | recall |
recall({}) or recall({ topic: "food" }) |
| Shares personal info (allergies, job, family) | memorize |
memorize({ text: "I'm allergic to shellfish", category: "profile", data: { allergies: ["shellfish"] } }) |
| Logs trackable data (meals, workouts, expenses) | memorize |
memorize({ text: "Had a burrito for lunch", category: "meals", data: { food: "burrito", calories: 650 } }) |
| Shares an experience, reflection, note | memorize |
memorize({ text: "That dinner was magical", storage: "memory", collection: "journal" }) |
| Asks "what do I track?" or "what tables do I have?" | recall |
recall({}) — context response includes table inventory |
| Asks about tracked data (counts, history, trends) | recall |
recall({ mode: "table", table: { table: "meals", sql: "SELECT ..." } }) |
| Asks "remember when I..." or about past experiences | recall |
recall({ topic: "beach dinner" }) or recall({ mode: "memory", memory: { collection: "journal", query: "beach dinner" } }) |
| Asks about relationships, patterns, connections | recall |
recall({ mode: "graph", graph: { queryType: "pattern", pattern: "..." } }) |
| Says "that's wrong" or corrects stored information | review |
review({ action: "list" }) then review({ action: "resolve", metaId: 123, resolution: "confirm" }) |
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.
- 6d ago First seen · 269 lines · 33 tokens per session scan A 1ba778ff3210
epitome-memory is a skill published in the GitHub repository gunning4it/epitome (8 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 2,501 once invoked, about $0.0002 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…