persona

A command that applies a chosen role, such as an architect or security reviewer, to a request in the current conversation.

In plain words
What is it for?
Use it for tasks such as reviewing an API design, checking security, or identifying technical debt, which means code that should be improved later.
Why use it?
It gives focused guidance for a particular kind of analysis instead of treating every request the same way.

Command for Claude Code

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 commands/agentsea/flashbacker/persona
Clone the repo
git clone --depth 1 https://github.com/agentsea/flashbacker

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 395 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00395
Opus 5 $0.00000 $0.00198
Sonnet 5 $0.00000 $0.00079
Haiku 4.5 $0.00000 $0.00040

Measured 3d ago against content hash 4c36927f2e79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

persona scanned grade B with 1 finding 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 3d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

allowed-tools: "*"
templates/.claude/commands/fb/persona.md · 53 lines

What it actually says

🎭 AI Persona System

Apply specialized AI persona templates directly in the current conversation for focused analysis and expertise.

Usage

/fb:persona <persona-name> <your request>

Available Personas

Use flashback persona --list to see current available personas and descriptions

Important: If the persona requested by the user does not exist, return "❌ Persona '{persona_name}' does not exist" and then run flashback persona --list to show available personas. Do NOT proceed with the analysis if the requested persona is missing.

ELSE (if the requested persona exists), proceed with the rest of this command.

Examples

  • /fb:persona architect review our API design
  • /fb:persona security analyze authentication flow
  • /fb:persona refactorer identify technical debt

Persona Request Processing

Parse the $ARGUMENTS to extract:

  1. First argument: Persona name (required)
  2. Remaining arguments: User's request/question (required)

If no persona name provided, show the usage and available personas above.

If persona name provided:

  1. Read Persona Template: Use Read tool to load .claude/flashback/personas/{persona-name}.md
  2. Apply Persona: Follow the persona template's guidelines and principles
  3. Process User Request: Address the user's specific request using the persona's expertise
  4. Provide Analysis: Give focused analysis based on the persona's specialization

Response Format

When applying a persona:

# 🎭 {Persona Name} Analysis

{Apply the persona template's principles and approach to analyze the user's request}

## Recommendations
{Provide specific recommendations based on the persona's expertise}

Error Handling

If persona file not found, return error message and run flashback persona --list to show available personas dynamically.

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. 3d ago First seen · 53 lines · 0 tokens per session scan B 4c36927f2e79

Subscribe to this mod's changes

persona is a command published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 395 tokens. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.