V1 Next — Development skill for Claude Code
Bootstrap the next v1.0 (#150) item — red tests first, then sample + CI contract, then implementation.
How to install V1 Next
Installs to ~/.claude/commands/rsicarelli-fakt-v1-next.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/rsicarelli/fakt/HEAD/.claude/commands/v1-next.md -o ~/.claude/commands/rsicarelli-fakt-v1-next.md Restart Claude Code, or start a new session, for it to be picked up.
What V1 Next does
description: Bootstrap the next v1.0 (#150) item — red tests first, then sample + CI contract, then implementation argument-hint: "[issue number, e.g. 164 — omit to take the next unchecked #150 item]"
Work the next item of the **v1.0 tracker #150** (issue **$ARGUMENTS**, or the first unchecked "Up next" item whose dependencies are merged when no argument is given).
Work **one step at a time**. Finish each step and show its evidence (command plus trimmed output) before you start the nex
Alternatives in Development
- Arstart — AgentRecall session opener — status board (no args), project loader ( ), or cold-start bootstrap 370 ★
- Cmux Fresh — Clear cmux's persisted session so the next launch opens with fresh/blank windows 107 ★
- Work Next — Get the next recommended work item to start based on dependencies and priority 62 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Coding Skill
Portable TDD-first coding-agent skill for Codex and Claude Code: clarify behavior first, write RED tests, impl
Xcindex Setup
Bootstrap xcindex in the current project — verifies the Swift binary, locates the Xcode project, optionally bu
Code Red
Emergency escalation — classify a situation as CODE RED, pause lower-priority work, activate the relevant orch
Review Checkpoint
A Claude Code skill that enforces structured, self-reviewing implementation workflows. Contract first, code se
Reload Session Bootstrap
The first thing an agent should do each session in Reload — load its shared-memory context, then find the mess
Relogin
Re-authenticate one Claude Max account (next/next2/next3/next4) through the automated ladder — headless refres
Related Agents
TDD Test Writer
Writes failing tests for a ledger item. NEVER writes production code. Reads the spec, writes the test, runs it
Shep Use Case Creator
Scaffolds a new application-layer use case with TDD (RED test file first, then minimal GREEN implementation),
Test Archaeologist
Writes tests for legacy code by first excavating its actual behavior contract — what the code really does, not