Drop-in autonomous product-development crew — lands cold in any repo, assesses, decides the highest-leverage move, executes via Claude+Codex agents and multi-day Ralph pours, gates every push through adversarial review, and compounds its own intelligence each deployment.
Portable autonomous Design Lead. Inside a SmokeJumper sprint, produces UX/design direction for user-facing work — flows, component patterns, microcopy, states, research synthesis. CREATOR, not certifier: hands finished work to the design review gate and never self-certifies. Prefers a project-specific design lead/director when the SmokeJumper adapter detects one. Reads the target's design system from RECON; never assumes a specific design language.
Portable autonomous Engineering Lead. OWNS builds end-to-end inside a SmokeJumper sprint — decomposes work, ROUTES each unit to the synchronous crew lane or the async Ralph big-pour lane, dispatches Claude + Codex agents, drives every quality gate to merged+pushed. Prefers a project-specific engineering lead when the SmokeJumper adapter detects one. Never edits safety-critical logic directly (routes to guardian agents); never deploys/releases without explicit human greenlight (merging ≠ deploying); never bypasses a gate.
Portable autonomous Lead Product Manager. Inside a SmokeJumper sprint, decides WHAT to build next — assesses product state, prioritizes by leverage, writes the spec/plan. CREATOR, not certifier: hands finished work to the adversarial review gate and never self-certifies. Prefers a project-specific product lead when the SmokeJumper adapter detects one. Escalates to the human only for product strategy / budget / release authority. Never edits safety-critical logic.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A drop-in, autonomous product-development crew packaged as a standalone plugin for Claude Code and Codex.
SmokeJumper lands cold in any repo, builds a model of what exists, decides the highest-leverage next move itself, executes via a mix of Claude agents and Codex, gates every push through an adversarial review, and runs a lessons-learned pass at the end — enriching both the target repo's own knowledge store and the plugin itself. Two things compound per deployment: the repo gets better, and the crew gets sharper.
SmokeJumper installs from the same plugin manifest in both runtimes — Claude Code and
Codex share the SKILL.md + agents/ + .claude-plugin/marketplace.json format.
From GitHub:
claude plugin marketplace add https://github.com/shanemhamilton/smokejumper
claude plugin install smokejumper@smokejumper
Or from a local checkout (swap the marketplace source):
claude plugin marketplace add ~/Documents/SmokeJumper
claude plugin install smokejumper@smokejumper
codex plugin marketplace add shanemhamilton/smokejumper
Then install the smokejumper plugin from within Codex (its skill-installer handles
enablement). For a local checkout, point the marketplace at the directory instead:
codex plugin marketplace add ~/Documents/SmokeJumper
Validate before installing:
claude plugin validate ~/Documents/SmokeJumper
Cut a versioned release tag:
claude plugin tag ~/Documents/SmokeJumper
/smokejumper
Starts a full sprint. SmokeJumper proceeds through all eight phases autonomously, pausing only for decisions that require product strategy, budget authority, or explicit release sign-off.
SmokeJumper is built for Claude Code, but it also runs when a Codex agent (or any
file-and-shell capable agent) is the top-level orchestrator — point the agent at
skills/smokejumper/SKILL.md and have it follow the eight phases. A runtime preflight
(references/runtime.md) detects what your runtime can do and adapts:
agents/*.md persona and acts as that role for the phase. RECON runs scripts/sj scan, which resolves the leads, writes the mapping into repo-knowledge.md + adapter-scan.json, and prints a "Leads established" banner — so lead establishment is a visible, durable artifact, not an implicit step.sj CLI is runtime-agnostic → any orchestrator that can run a shell command gets the same deterministic gates (sj gate), state validation (sj validate-state), and safety tripwires (sj lane-check).references/product-context.md + templates/product-context.md with no dependency on any external skill.anthropic-skills:handoff-prompt unavailable → Phase 8 writes <target>/.smokejumper/HANDOFF.md directly.choo-choo-ralph / bd absent → Lane A is unavailable; all work routes to Lane B (the synchronous crew).Two RECON outputs are durable, visible artifacts rather than steps an orchestrator has to remember — so they hold up under any runtime, including a Codex agent that skims prose.
Leads are established by a deterministic scan, not from memory. scripts/sj scan resolves the product / engineering / design leads (a project-specific override or the bundled fallback), the gate roles, and the available capabilities; writes the mapping into <target>/.smokejumper/repo-knowledge.md; emits a leads_established event to the sprint log; and prints a banner:
=== SmokeJumper — Leads Established ===
Product lead: smokejumper-product-lead [BUNDLED]
Engineering lead: smokejumper-engineering-lead [BUNDLED]
Design lead: smokejumper-design-lead [BUNDLED]
Gates resolved: designReviewer=null thesisGuardian=null reviewIntegrity=null firstUseCritic=null qualityControl=null
Capabilities: asyncLoop=no codex=yes metaswarm=no bugsweep=no tracker=beads
Design skills: review=design-review consult=design-consultation a11y=accessibility-wcag frontend=frontend-design (plugin)
Design system: tailwind.config.js,src/theme.css,.storybook/
Functional health: HEALTHY → design posture: WEIGHTED
Product context: MISSING — run Setup before DECIDE
=======================================
npx claudepluginhub shanemhamilton/smokejumper --plugin smokejumperConsolidate CLAUDE.md / AGENTS.md / GEMINI.md into one canonical file per directory via symlinks, with a drift-proof pre-commit guard, so Claude Code, Codex, Cursor, and Gemini share one source of truth.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.