# Agent Role Card Template

Use this file to define a recurring agent role. Keep the card short enough for the agent to read before acting.

```md
# Agent Role Card: [Role Name]

## Role

What this agent is responsible for.

## Purpose

Why this role exists in the system.

## Must read before acting

- file or folder:
- file or folder:
- file or folder:

## Allowed actions

- 
- 
- 

## Not allowed without human approval

- 
- 
- 

## Inputs

- 
- 
- 

## Output standard

A good output must:

- 
- 
- 

An unacceptable output:

- 
- 
- 

## Tools / interfaces

- 
- 
- 

## Memory updates after acting

After completing a task, update:

- decision log:
- source map:
- workflow file:
- lessons file:
- review checklist:

## Escalation triggers

Ask for human judgment when:

- 
- 
- 

## Review questions

After this role acts, review:

- Did the agent read the right context?
- Did it stay inside its boundary?
- Did it produce an output that met the standard?
- Did it update memory?
- What should change in this role card?
```

## Good role cards are specific

A weak role card says: "You are a helpful researcher."

A strong role card says:

- which files to read before research
- what source quality means
- what output standard applies
- what not to claim without approval
- what file to update after research
- when to escalate to a human

## Operating rule

If an agent makes a predictable mistake, do not only fix the output. Update the role card.