By lucianHymer
Take a plan/design doc all the way to a built, tested, reviewed product in two phases — plan→blueprint, then blueprint→build-to-green — with a human feedback gate between. A skill orchestrates two bundled workflows.
Like one-shotting, but better.
double-shot is a plugin for Claude Code that takes a plan document all the way to a built, tested, reviewed codebase. You write the plan and steer once at the blueprint; two background Claude Code workflows do the parallel building and adversarially verify their own work.
It works for any stack, but shines when your plan has a checkable invariant — a core property the build can mechanically prove it didn't break. Rust is a great fit: its type system can make the invariant structural, so a violation becomes a compile error and the adversarial verifier gets an objective answer.
A Claude Code plugin, straight from GitHub:
/plugin marketplace add lucianHymer/double-shot
/plugin install double-shot@double-shot
Write a detailed plan as a markdown file — with Claude Code, Claude Desktop, or however you like. The more concrete the better.
In Claude Code, point double-shot at it:
Use double-shot to implement
plan_xyz.md
That's it. The agent reads your plan, aligns with you on the open decisions, produces a blueprint and stops to show you, then — on your go — builds it to green and reports back with the diff.
GNU Affero General Public License v3.0. See LICENSE.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
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 claimPersistent memory for Claude Code - never forget what you learn
npx claudepluginhub lucianhymer/double-shot --plugin double-shotA growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses