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.
Borrowing it
Nothing to install: this file belongs to SterlingChin/marvin-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SterlingChin/marvin-template/main/.claude/agents/_template.mdgit 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/agents/sterlingchin/marvin-template/_template)<a href="https://agentmods.dev/agents/sterlingchin/marvin-template/_template"><img src="https://agentmods.dev/badge/agents/sterlingchin/marvin-template/_template/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/sterlingchin/marvin-template/_template"><img src="https://agentmods.dev/badge/agents/sterlingchin/marvin-template/_template.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00011 | $0.00465 |
| Opus 5.5 | $0.00004 | $0.00186 |
| Sonnet 5.5 | $0.00002 | $0.00093 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
agent-name 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 2mo 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.
What it actually says
Agent Name
Purpose
What this agent is responsible for. Be specific about the domain and scope.
When to Spawn
The orchestrator should spawn this agent when:
- Condition 1
- Condition 2
- User explicitly requests this type of work
Routing rule examples (add these to your main CLAUDE.md):
- User says "keyword or phrase" → spawn `agent-name`
- User mentions <domain concept> → spawn `agent-name`
- "Do X with Y" → spawn `agent-name`
Capabilities
What tools and actions this agent can perform:
- Action 1
- Action 2
- Action 3
Format Rules
Define output conventions for this agent's domain:
- Format A: When to use, structure expectations
- Format B: When to use, structure expectations
- Default: Fallback format if none of the above apply
Workflow
Step-by-step process this agent follows:
- Step 1 - What happens first
- Step 2 - Next action
- Step 3 - Final deliverable
Output Format
What the user can expect as a result:
- Report structure
- File locations
- Summary format
Metrics & Tracking
What this agent tracks over time (if applicable):
| Metric | Target | Notes |
|---|---|---|
| Example metric | >80% | How it's measured |
Remove this section if the agent doesn't track anything.
What You Do Not Do
Explicit boundaries prevent scope creep. List things this agent should NOT attempt:
- Decision that requires human judgment
- Action outside this agent's domain
- Task that belongs to a different agent
When one of these comes up: acknowledge it, surface it for the user, and stop.
Example Usage
User: "I need to research competitors in the API space"
Orchestrator: [spawns research-agent]
Agent: [performs research, saves to research/output/, reports back]
Notes
Any special considerations, limitations, or dependencies.
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.
- 2mo ago First seen · 86 lines · 11 tokens per session scan A 3a38c6af5a4c
agent-name is an agent published in the GitHub repository SterlingChin/marvin-template (1,024 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 465 once invoked, about $0.0000 per session on Opus 5.5. 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 agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.