A template for defining a specialised coding agent: its responsibility, when to start it, what it can do, how it works, and how it reports results. An agent is a focused helper for a particular type of work.

Use it when documenting or configuring a new specialist agent, including its routing rules, workflow, capabilities, and expected deliverables.

It gives an agent clear boundaries and instructions instead of leaving its purpose and output format vague.

agent-name — Agent for Claude Code by SterlingChin: A template for defining a specialised coding agent: its…

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.

agentmods

npx agentmods add agents/sterlingchin/marvin-template/_template

Clone the repo

git clone --depth 1 https://github.com/SterlingChin/marvin-template

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/sterlingchin/marvin-template/_template.svg)](https://agentmods.dev/agents/sterlingchin/marvin-template/_template)

Your own site

<a href="https://agentmods.dev/agents/sterlingchin/marvin-template/_template"><img src="https://agentmods.dev/badge/agents/sterlingchin/marvin-template/_template.svg" alt="Measured on agentmods" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 465 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00011	$0.00465
Opus 5	$0.00005	$0.00233
Sonnet 5	$0.00002	$0.00093
Haiku 4.5	$0.00001	$0.00047

Measured 4d ago against content hash 3a38c6af5a4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.claude/agents/_template.md · 86 lines

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.

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.

4d ago First seen · 86 lines · 11 tokens per session scan A 3a38c6af5a4c

Subscribe to this mod's changes

agent-name is an agent published in the GitHub repository SterlingChin/marvin-template (1,016 stars, last pushed 16d ago), licensed MIT. It adds 11 tokens to every session and 465 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.

Building agents

agent-name