mhlaghari

mhlaghari/stuntman

Plugin Claude Code

Plugin marketplace listing 1 plugin: stuntman.

mhlaghari/stuntman

Plugin Claude Code

Claude doesn't do its own stunts. Plan with Claude, execute with a near-free model (DeepSeek, Groq, Ollama, Grok, Kimi… via a local proxy or opencode), OpenAI's Codex CLI, Google's Antigravity CLI (agy), or Meta's Muse Code CLI, review with Claude — your subscription tokens go only where intelligence matters.

mhlaghari/stuntman

Instructions file

Instructions for mhlaghari/stuntman, covering claude.md and project memory protocol.

mhlaghari/stuntman

Hook

Runs when the agent finishes a response, executing handoff-guard.sh. From mhlaghari/stuntman.

mhlaghari/stuntman

Skill Claude CodeCodex

Delegate implementation work to a stunt double (a headless worker — Claude Code via a local proxy, opencode running DeepSeek/Groq/Ollama/Grok/Kimi, OpenAI's Codex CLI, Google's Antigravity CLI, or Meta's Muse Code CLI). Claude plans the task, the worker executes it, Claude reviews the diff and iterates. Use when the…

mhlaghari/stuntman

Skill Claude CodeCodex

Resume work in a scaffolded project by reading its memory docs first, then continuing where the last session left off. Reads HANDOFF.md (the session baton), STATUS.md (the status board), README.md, and anything else the CLAUDE.md "read this first" list points to, gives a short read-back of where things stand, then…

mhlaghari/stuntman

Skill Claude CodeCodex

Build a complete, research-backed product-launch plan. Fans out a multi-agent workflow that does cited web research on every competitor, sizes the market, finds the regulatory/trust tailwinds, ranks launch channels, then has strategists write the positioning, pricing, and a week-by-week launch playbook …

mhlaghari/stuntman

Skill Claude CodeCodex

Run long work across Claude's 5-hour usage limit automatically. A rate-limit-aware self-loop — it reads your 5-hour window (utilization + exact reset time) at zero token cost, keeps the cheap stunt double executing while Claude is capped (the worker has no Anthropic limit), and resumes the Claude side the moment the…

mhlaghari/stuntman

Skill Claude CodeCodex

Set up a project's self-resuming memory system in one shot. Writes a contract into CLAUDE.md (a "read this first" list + a "before you stop" process contract) and creates the docs it references — HANDOFF.md (the session baton) and STATUS.md (the status board) — then populates them from the project's current state.…

mhlaghari/stuntman

Skill Claude CodeCodex

Show usage and limits for every stunt-double subscription on one board — Claude's 5-hour/weekly windows (live), Codex's 5-hour/weekly windows (from its last session snapshot), the DeepSeek balance behind opencode (live), and honest n/a rows for backends that expose nothing (agy, muse). Use when the user invokes…

mhlaghari/stuntman

Skill Claude CodeCodex

Scaffold an LLM-wiki "second brain" for the current folder in one shot — lays the vault skeleton, writes a note per project from its README/code, builds a graphify knowledge graph, and wires the graphify MCP so Claude can query prior work across projects. Auto-detects a single project vs a folder of many projects. Use…