start

start is a skill for Claude Code, Codex from SterlingChin/marvin-template. It costs 31 tokens per session (565 once invoked), scanned A, original, MIT.

A session-start briefing tool for the MARVIN workspace. It loads current project notes, goals, recent session records, progress logs, and follow-up items.

In plain words
What is it for?
Starting a new session, resuming after a break, reviewing current goals, checking content progress, and finding follow-ups that need attention.
Why use it?
It reduces the time spent reconstructing what was happening after starting or resuming work, and surfaces priorities and overdue follow-ups.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Starting a new session, resuming after a break, reviewing current goals, checking content progress, and finding follow-ups that need attention.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sterlingchin/marvin-template/start
About the project

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.

SterlingChin/marvin-template · 1,017 stars · on GitHub

Install

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.

Any agent
npx skills add SterlingChin/marvin-template --skill start
Clone the repo
git clone --depth 1 https://github.com/SterlingChin/marvin-template

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for start

README.md
[![agentmods](https://agentmods.dev/badge/skills/sterlingchin/marvin-template/start.svg)](https://agentmods.dev/skills/sterlingchin/marvin-template/start)
Your own site
<a href="https://agentmods.dev/skills/sterlingchin/marvin-template/start"><img src="https://agentmods.dev/badge/skills/sterlingchin/marvin-template/start.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00565
Opus 5 $0.00015 $0.00282
Sonnet 5 $0.00006 $0.00113
Haiku 4.5 $0.00003 $0.00056

Measured 7d ago against content hash c299ccc89aed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 7d 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.

skills/start/SKILL.md · 96 lines

What it actually says

Session Start Skill

Start MARVIN session with full context loading and daily briefing.

When to Use

  • When user types /start
  • At the start of any Claude Code session in the MARVIN directory
  • When resuming work after a break

Process

Step 1: Establish Current Date

date +%Y-%m-%d

Store as TODAY. Use for all file naming and date references.

Step 2: Load Context

Read in order:

  1. state/current.md — Current priorities, open threads, and state
  2. sessions/{TODAY}.md — If exists, we're resuming today
  3. If no today file, read sessions/{YESTERDAY}.md for continuity

Step 3: Review Goals

Check state/goals.md for:

  • Annual goals and progress
  • Monthly targets

Step 4: Assess Progress

Check content/log.md for current month:

  • Content shipped vs. goals
  • Days remaining in month

Step 5: Check Follow-ups

Review state/current.md for any follow-up items:

  • Surface any items with review date ≤ TODAY
  • Remind user of upcoming follow-ups within 3 days

Step 6: Surface Proactive Alerts

Compile and present:

  • Active priorities from state/current.md
  • Open threads needing attention
  • Content pacing status (if behind)
  • Any deadlines approaching

Step 7: Greet User

Present a concise briefing:

  • Date and day of week
  • Top 3 priorities
  • Any alerts or nudges
  • Ask how to help today

Output Format

Good morning! It's {Day}, {Date}.

**Today's Focus:**
1. {Priority 1}
2. {Priority 2}
3. {Priority 3}

**Alerts:**
- {Alert if any}

**Progress ({Month}):**
- {Goal 1}: X/Y
- {Goal 2}: X/Y

How can I help today?

Notes

  • If this is a resumed session (today's log exists), acknowledge what was already covered
  • Keep briefing concise — details on request

Skill created: 2026-01-22

Changes

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.

  1. 7d ago First seen · 96 lines · 31 tokens per session scan A c299ccc89aed

Subscribe to this mod's changes

start is a skill published in the GitHub repository SterlingChin/marvin-template (1,017 stars, last pushed 19d ago), licensed MIT. It adds 31 tokens to every session and 565 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 2026-08-30.