MARVIN is a personal AI assistant built to remember conversations, track goals, organize work, and connect to external applications. People use it as a chief-of-staff-style extension for Claude Code or GitHub Copilot CLI, with integrations including Google Workspace, Microsoft 365, Slack, Linear, Notion, and Telegram. The catalogue entries provide commands, agents, skills, and instructions that define MARVIN's workflows.
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/sterlingchin/marvin-template/endgit clone --depth 1 https://github.com/SterlingChin/marvin-templateWrote 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/commands/sterlingchin/marvin-template/end)<a href="https://agentmods.dev/commands/sterlingchin/marvin-template/end"><img src="https://agentmods.dev/badge/commands/sterlingchin/marvin-template/end.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 | $0.00012 | $0.00688 |
| Opus 5 | $0.00006 | $0.00344 |
| Sonnet 5 | $0.00002 | $0.00138 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
end 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 5d 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.
/end - End MARVIN Session
Wrap up the current session and save all context for continuity.
The goal: A fresh session tomorrow should read ONLY state/current.md and know exactly where things stand. Every /end must leave that file accurate and complete.
Instructions
1. Summarize This Session
Review the conversation and extract:
- Topics discussed - What did we work on?
- Decisions made - What was decided and why?
- Content shipped - Any content published, drafted, or completed?
- Open threads - What's unfinished or needs follow-up?
- Action items - What needs to happen next?
2. Update Session Log
Get today's date with date +%Y-%m-%d.
Append to sessions/{TODAY}.md (create if it doesn't exist):
## Session End: {TIME}
### Topics
- {topic 1}
- {topic 2}
### Decisions
- {decision and reasoning}
### Content Shipped
- {content item, or "None"}
### Open Threads
- {thread 1}
### Next Actions
- {action 1}
If creating a new file, add header: # Session Log: {TODAY}
3. Log Decisions
If any decisions were made during this session, append each to state/decisions.md:
### {TODAY} - {Decision Title}
**Decision:** {What was decided}
**Context:** {Why this decision was made}
**Status:** Active
Create the file with header # Decision Log if it doesn't exist.
4. Log Content Shipped
If any content was shipped (published, posted, completed drafts), append to content/log.md:
| {TODAY} | {Type} | {Title/Description} | {Where published/saved} |
Create the file with this header if it doesn't exist:
# Content Log
| Date | Type | Title | Destination |
|------|------|-------|-------------|
5. Update State (MANDATORY)
This is the most important step. Check the "Last updated" date in state/current.md:
If 3+ days stale (or no timestamp): Do a full rewrite.
- Re-read the last 3 days of session logs
- Rebuild priorities, open threads, and project statuses from scratch
- Ensure nothing is carried forward that's already resolved
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.
- 5d ago First seen · 99 lines · 12 tokens per session scan A e9174499d1c2
end is a command published in the GitHub repository SterlingChin/marvin-template (1,017 stars, last pushed 17d ago), licensed MIT. It adds 12 tokens to every session and 688 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.