lean-role

lean-role is a command for Claude Code from TimboGP/timbogp-marketplace. It costs 23 tokens per session (384 once invoked), scanned A, original, MIT.

A role-switching command for a startup coach. It lets the agent act as a business partner, skeptic, mentor, customer, or investor.

In plain words
What is it for?
Use it to brainstorm, challenge a business model, review next steps, practise customer interviews, or rehearse an investor pitch.
Why use it?
It gives you different kinds of feedback without losing the context of your venture. You can test ideas, find weak assumptions, or practise conversations from another point of view.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the lean-coach plugin — 8 skills, 5 commands, 1 agent shipped together

Good fit Use it to brainstorm, challenge a business model, review next steps, practise customer interviews, or rehearse an investor pitch.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add TimboGP/timbogp-marketplace
Claude Code
/plugin install lean-coach

Made for: Claude Code.

Or install lean-coach, the plugin that ships this one along with the rest of its 8 skills, 5 commands, 1 agent.

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 lean-role

README.md
[![agentmods](https://agentmods.dev/badge/commands/timbogp/timbogp-marketplace/lean-role/github.svg)](https://agentmods.dev/commands/timbogp/timbogp-marketplace/lean-role)
Your own site
<a href="https://agentmods.dev/commands/timbogp/timbogp-marketplace/lean-role"><img src="https://agentmods.dev/badge/commands/timbogp/timbogp-marketplace/lean-role/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.

agentmods 80×15 button for lean-role

Your own site · 80×15
<a href="https://agentmods.dev/commands/timbogp/timbogp-marketplace/lean-role"><img src="https://agentmods.dev/badge/commands/timbogp/timbogp-marketplace/lean-role.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 384 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 $0.00023 $0.00384
Opus 5 $0.00012 $0.00192
Sonnet 5 $0.00005 $0.00077
Haiku 4.5 $0.00002 $0.00038

Measured 11d ago against content hash 3f60f1e27c5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

lean-role 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 11d 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.

plugin/lean-coach/commands/lean-role.md · 25 lines

What it actually says

/lean-role

Switch the agent into a role/persona. Drive this with the lean-roles skill.

Role: $ARGUMENTS. If empty or "what can you play?", list the cast (one line each from ${CLAUDE_PLUGIN_ROOT}/reference/roles.md) and ask which.

Procedure

  1. Map the argument to a role:
    • business-partner → collaborative co-founder (brainstorm, honest sparring) → lean-roles.
    • devils-advocate → relentless skeptic (pre-mortem, attack the riskiest assumption) → lean-roles.
    • mentor → direct advisor (review the model, prioritize next moves) → lean-roles (or the lean-mentor agent for a one-shot review).
    • customer → interview counterpart → hand to customer-interview.
    • investor → pitch counterpart → hand to investor-pitch.
  2. Load .lean/ so the persona engages this venture, then run the role-play protocol (${CLAUDE_PLUGIN_ROOT}/reference/roles.md): announce entering character, stay in role (honor [bracket] breaks), debrief on debrief.
  3. Capture anything load-bearing into .lean/risks.md / .lean/PROGRESS.md, then hand back to the coach or route onward.

Name the role on entry so the user always knows whether they're talking to the coach or a character.

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. 11d ago First seen · 25 lines · 23 tokens per session scan A 3f60f1e27c5a

Subscribe to this mod's changes

lean-role is a command published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 384 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 2026-08-31.