Scene 01 · Take 1 · Rolling

Claude doesn't doits own stunts.

Claude Code or Codex plans the task and reviews the result. A near-free worker does the typing — DeepSeek, Groq, local Ollama, or the flat-rate subscriptions you already pay for: OpenAI's Codex, Google's Antigravity, Meta's Muse. Your expensive Anthropic tokens are spent on thinking, never on typing.

▶  Roll camera See how it works
scroll
The shot list

How the stunt is pulled off

Claude directs. The stunt double performs. Same footage, a fraction of the budget.

01

Plan

Claude reads your codebase, designs the change, and writes a precise spec — files, edits, acceptance checks.

Claude · subscription
02

Execute

The stunt double picks up the spec and writes every line of code — five interchangeable backends behind one contract.

DeepSeek / Codex / Antigravity / Muse / Ollama
03

Review

Claude inspects the diff like a director at the monitor — catching bugs, style breaks, and missed cases.

Claude · subscription
04

Iterate

Notes go back to the worker for another take. Loop until the shot is clean — no extra thinking budget burned.

DeepSeek / Codex / Antigravity / Muse / Ollama
Dailies · real run

Footage from the cutting room

0
files shipped
a complete feature
0s
wall-clock time
plan to clean diff
0
review issues
passed first cut
$0
Anthropic tokens
on implementation
// not a benchmark — an actual stuntman run, captured end to end.
Overtime · second unit

Rolls right through your rate limit

Hit the 5-hour wall mid-scene? The stunt double keeps shooting on its own dime — and Claude picks up the moment the window reopens. Hands-free.

01

Detect

stuntman reads your 5-hour window — how much is spent, the exact reset — off the same meter /usage uses. Zero tokens, no API call.

window probe
02

Keep rolling

The stunt double isn't on Anthropic's clock. While the limit cools down, it keeps executing the spec'd work in the background — your key, not your cap.

DeepSeek / Codex / Antigravity / Muse / Ollama
03

Resume

The window reopens and Claude wakes where it left off — reviews the night's footage, rolls the next take. Auto when the reset is close; one ping when it's not.

Claude · subscription
Continuity · next call

Picks up on the next take

Hit the context limit, or just start fresh tomorrow? The project keeps its own notes — the next session reads them first and rolls, with zero re-explaining.

01

Scaffold once

One /scaffold writes a contract into your CLAUDE.md and creates four living docs — HANDOFF, STATUS, SPEC, STRATEGY — idempotent, never clobbers.

one-time setup
02

Wrap the take

Before each session ends, the agent refreshes HANDOFF.md, STATUS.md, and the README — what changed, what's next, the gotchas. The project becomes its own memory.

every session
03

Cold open

New session, cleared context, tomorrow morning — /handoff reads the docs first. You just say "execute handoff" and it rolls.

zero re-explaining
The call sheet · every command

Eight commands, one crew

Plan → execute → review is the core. The rest make long runs cheap, rate-limit-proof, context-proof, searchable across every project — turn a blank page into a launch plan, and put every subscription's limits on one board.

/delegate
Plan and review with Claude Code or Codex; execute with a selected worker. Five backends: Claude-via-proxy, opencode (DeepSeek/Groq/Ollama/Grok/Kimi), OpenAI's Codex, Google's Antigravity, Meta's Muse — your ChatGPT/Antigravity/Meta subscriptions become execution capacity. — saves cost · 5 backends in v0.11
/relay
Span Claude's 5-hour usage limit. The stunt double keeps executing while you're capped; Claude resumes at reset. — beats the rate limit
/scaffold
Give a project self-resuming memory. A CLAUDE.md contract + four living docs (HANDOFF · STATUS · SPEC · STRATEGY). — survives the context boundary
/handoff
Resume exactly where the last session stopped. Reads the living docs first — zero re-explaining, even after /clear. — cold-opens any session
/wiki
Build a "second brain" across a folder of projects. An Obsidian vault of notes-per-project + a graphify knowledge graph + a live MCP — so any session can ask "did I solve this already?" — cross-project memory · new in v0.7
/launch
Turn a blank page into a product launch plan. A multi-agent workflow does cited competitor research, sizes the market, ranks channels, then writes pricing, positioning + a week-by-week playbook — pressure-tested by adversarial critics — into one Product Success Overview (markdown + HTML). — go-to-market · new in v0.8
/usages
One board for every subscription's usage + limits. Claude's 5-hour/weekly windows live, Codex's windows from its own snapshots, the DeepSeek balance — read at zero token cost, plus a cached segment for your status line. — know your limits · new in v0.12
/floor
See your agents across projects. Claude Code, Codex, and Stuntman workers share one live Vexel board. Read conversations, see who needs you, and prompt ready tmux sessions. — the agent floor · new in v0.13
The Floor · Dubai studio

Your crew, after hours.

A pixel Dubai skyline, expressive Vexel agents, and a clear view of who needs you.

The Floor board: project bays with expressive Vexel agents playing guitar and headbanging under a pixel Dubai skyline at sunset
Earlier staged preview of the Dubai Floor. The live board shows your real agents with project and status filters, a Show all reset, and optional completion and help tones.

The Floor ships with Stuntman — see the Floor section of the README for setup details and the runtime review for how it behaves live.

Action

Two takes and you're rolling

A plugin for Claude Code and Codex. Open source. Choose the host and worker you already use.

claude-code — stuntman
›/plugin marketplace add mhlaghari/stuntman
›/plugin install stuntman@stuntman

For Codex, run codex plugin marketplace add mhlaghari/stuntman, then codex plugin add stuntman@stuntman. Start a new thread and select a Stuntman skill. Codex setup and hook trust.