Plugin Claude Code
PipelineIQ pipeline commands for Claude Code.
Plugin Claude Code
PipelineIQ pipeline commands for Claude Code.
Plugin Claude Code
Closed-loop spec -> plan -> implement -> audit -> fix -> merge pipeline for Claude Code.
Instructions file
Instructions for MarioEpkOne/PipelineIQ, covering pipelineiq — context for claude, what this project does, invariants, contracts and gotchas.
Agent
Audits an implementation against its spec and plan. Use when code changes have been made and need independent review for correctness, completeness, and spec compliance.
Agent
Fixes errors listed in an audit document. Use when an audit has identified actionable errors that need to be resolved in the implementation.
Agent
Implements an existing implementation plan. Use when a plan file exists and code changes need to be executed step by step in a worktree.
Agent
Plans implementation of a spec. Use when a spec needs to be turned into an actionable implementation plan with steps, file scope, and verification criteria.
Agent
Verifies that a fixer's changes resolved errors from a prior audit. Use after a fix phase to check whether audit findings have been addressed.
Agent
Repairs a failed pipeline implementation. Use when a pipeline teammate reports PIPELINEFAILURE and the implementation needs minimum-viable fixing before re-audit.
Command
(Scoped to this directory only. See root CLAUDE.md for project-wide context.).
Command
POST-IMPLEMENTATION AUDIT — analyzes what the implementing agent did wrong and why, proposes specific changes to CLAUDE.md / impl.md / impl-plan.md for approval, and appends new patterns to learnings.md.
Command
TARGETED FIX — reads an audit document's "Actionable Errors" section and fixes each error. Can be used standalone or invoked by the pipeline.
Command
PLAN ONLY — reads a spec, orients in the codebase, creates a worktree, and writes a self-contained implementation plan. Manual handoff: you open a new session and run /impl yourself.
Command
EXECUTE PLAN — reads an existing implementation plan and runs all steps autonomously, verifies each step, writes a working log, and prompts to commit.
Command
Review learnings.md, classify each entry as universal or project-specific, route approved entries to commands/.md or project KB files, curate existing KB entries, and archive everything to promotion-log.md.
Command
Orchestrates the full implementation pipeline (impl-plan -> impl -> audit -> fix -> merge) across multiple pre-written specs simultaneously using Claude Code's agent teams feature. Specs run in parallel where dependencies allow; merges are serialized through the lead to preserve the worktree invariant. Replaces the…
Command
CLOSED-LOOP PIPELINE -- runs the complete spec -> impl-plan -> impl -> audit -> fix loop -> summary workflow. The spec phase is interactive (inline). Each subsequent phase runs as an isolated subagent with clean context. If errors are found during audit, a fix->re-audit loop runs automatically (max 2 cycles).
Command
SPEC SPLITTER -- analyzes a spec for context window pressure, proposes a decomposition, and generates self-contained child specs optimized for parallel /pipeline-team execution.
Command
You investigate what the user wants to build, orient yourself in the codebase, then interview the user in depth to produce a complete specification.