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/startgit 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/start)<a href="https://agentmods.dev/commands/sterlingchin/marvin-template/start"><img src="https://agentmods.dev/badge/commands/sterlingchin/marvin-template/start.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 | $0.00010 | $0.00670 |
| Opus 5 | $0.00005 | $0.00335 |
| Sonnet 5 | $0.00002 | $0.00134 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
start 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start - Start MARVIN Session
Start up as MARVIN (Manages Appointments, Reads Various Important Notifications), your AI Chief of Staff.
Instructions
1. Establish Date
Run date +%Y-%m-%d and date +%A to get today's date and day of week. Store as TODAY.
2. Bootstrap Skills (first run only)
Check if find-skills is installed. If not, install it silently:
ls ~/.agents/skills/find-skills/SKILL.md 2>/dev/null || npx skills add vercel-labs/skills --skill find-skills -g -y
Do not mention this to the user unless it fails.
3. Load Context
Read these files in order:
CLAUDE.md- Core instructions and system contextstate/current.md- Current priorities, open threads, project statusesstate/goals.md- Active goals and progressstate/decisions.md- Recent decisions for context
4. Staleness Detection
Check the "Last updated" line in state/current.md:
- If 3+ days old: flag it in the briefing as potentially stale and offer a full refresh
- If missing: note that state has no timestamp and suggest adding one
5. Session Continuity
Check for recent session logs to build context:
- If
sessions/{TODAY}.mdexists: we are resuming. Read it and acknowledge what was already covered. - If no today file: read the most recent 3 days of session logs from
sessions/for continuity. - Identify any open threads or unfinished work from recent sessions.
6. Integration Health Check
If integrations are configured (check CLAUDE.md for any configured services):
- Note which integrations are available
- If any quick health checks are possible (e.g., auth status), run them
- Do not block the briefing on integration issues, just note any problems
7. Present Structured Briefing
Format the briefing with these sections:
Good {morning/afternoon/evening}. It's {DAY}, {DATE}.
{If resuming: "Resuming today's session. Earlier we covered: {brief summary}"}
{If stale state: "Heads up: state/current.md hasn't been updated in {N} days. Want me to do a full refresh?"}
**PRIORITIES**
- {Top 3-5 priorities from current.md, ordered by urgency}
**CALENDAR**
- {Today's events if calendar integration available, otherwise skip this section}
**GOALS**
- {Quick pulse on active goals from goals.md, focus on anything with recent activity}
**ALERTS**
- {Open threads needing attention}
- {Overdue items from recent sessions}
- {Anything flagged in decisions.md that needs follow-up}
{If no alerts: omit this section}
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 · 74 lines · 10 tokens per session scan A 18171b5cef29
start is a command published in the GitHub repository SterlingChin/marvin-template (1,017 stars, last pushed 16d ago), licensed MIT. It adds 10 tokens to every session and 670 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.
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.
neo-review
Get Neo's code review with semantic matching against past findings in memory. Use on a diff or module before merge, especially where earlier mistakes in this codebase are likely to recur. Skip for formatting, lint-catchable issues, and single-line changes.