Documentation

PipelineIQ

A closed-loop development pipeline built as Claude Code slash commands. Spec → Plan → Implement → Audit → Fix → Merge — fully orchestrated, with artifact traceability at every phase.

What PipelineIQ Does

PipelineIQ is a collection of Claude Code slash commands (markdown prompt files) that automate the full development lifecycle. A natural-language description of a feature is taken through structured planning, code generation in an isolated git worktree, independent auditing against the original spec, automated error correction, and a clean fast-forward merge — producing timestamped artifacts at each step.

There is no build step, no runtime, and no dependencies. The deliverables are markdown files in commands/ that Claude Code executes as slash commands.

End-to-End Automation

From English description to merged code. Each phase is a specialized subagent with a focused scope and isolated context.

🔍

Independent Auditing

A separate agent — with no knowledge of the plan — verifies the implementation against the original spec.

Self-Correcting

Audit errors feed into an automated fix loop (up to 2 cycles). Process friction is logged for continuous improvement.

Installation

Install via the Claude Code plugin system (recommended) or manually copy the command files. The pipeline validates that all reference files are present at startup.

Via Claude Code Plugin (Recommended)

# Step 1: Add the PipelineIQ marketplace /plugin marketplace add MarioEpkOne/PipelineIQ # Step 2: Install the plugin /plugin install pipelineiq@pipelineiq-marketplace # Step 3: Verify — these commands should be available: # /pipeline, /pipeline-team, /spec, /impl-plan, /impl, # /audit-implementation, /fix, /spec-splitter

Manual Install (Alternative)

# Option 1: Global install (available in all projects) cp -r commands/ ~/.claude/commands/ # Option 2: Per-repo install cp -r commands/ <your-repo>/.claude/commands/ # Verify: both reference subdirectories must be present ls ~/.claude/commands/references/pipeline/ # 6 phase files ls ~/.claude/commands/references/pipeline-team/ # 2 files

Directory Structure

Artifact directories (specs/, Implementation Plans/, Working Logs/) are created automatically in the main repo root, never inside worktrees. All artifacts are gitignored.

Command Reference

Each command can be invoked standalone or is called internally by the pipeline orchestrator.

Command Purpose Input Output
/pipeline Run the full 6-phase pipeline for a single feature Description or spec path Merged code + all artifacts
/pipeline-team Run multiple specs in parallel with dependency-aware scheduling Pre-written specs in specs/team/ Batch summary + per-spec artifacts
/spec Interactive spec generation via structured interview Feature description specs/spec--*.md
/impl-plan Create a step-by-step implementation plan + worktree Spec file Implementation Plans/impl--*.md
/impl Execute a plan: write code, run tests, log results Implementation plan Working Logs/wlog--*.md
/audit-implementation Independent verification of implementation vs. spec Working log Working Logs/audit-impl--*.md
/fix Address actionable errors found by the auditor Audit report Working Logs/fixer-log--*.md
/spec-splitter Decompose a large spec into parallelizable child specs Spec file N child specs in specs/team/
Phase-by-Phase Execution

/pipeline "add feature X" orchestrates all six phases. Each phase runs as a subagent with its own reference prompt template, and produces a timestamped artifact that feeds the next phase.

1
Spec Generation /spec

Runs an interactive interview covering goals, trade-offs, edge cases, constraints, and testing strategy. Produces a structured specification document. Can also accept an existing spec file to skip this phase.

Produces
spec--*.md
2
Implementation Planning /impl-plan

A planning agent reads the spec and the current codebase, then writes a self-contained implementation plan: files to touch, code for each change, verification checklist, and a draft commit message. Creates a git worktree on a dedicated branch for isolated work.

Consumes
spec--*.md
Produces
impl--*.md git worktree
3
Implementation /impl

Follows the plan step-by-step inside the worktree: writes code, runs build/lint/test after each step, and retries failures (up to 3 attempts per step). Every change, error, and deviation is logged.

Consumes
impl--*.md
Produces
wlog--*.md committed code
4
Audit /audit-implementation

A fresh, independent agent that has never seen the plan or working log reads the original spec and inspects the codebase directly. Verifies each goal, categorizes failures (spec drift, incomplete tasks, build/test failures, rule violations), and produces a numbered list of actionable errors for the fix phase.

Consumes
spec--*.md wlog--*.md
Produces
audit-impl--*.md
5
Fix Loop /fix max 2 cycles

If the audit found actionable errors, a fix agent parses the error list, applies targeted fixes, and re-runs tests. A re-audit then verifies the fixes. This loop runs up to 2 cycles; decreasing error counts indicate progress. Errors requiring human judgment are flagged and skipped.

Consumes
audit-impl--*.md
Produces
fixer-log--*.md
6
Merge & Summary

The worktree is rebased onto main and merged with --ff-only (guaranteeing linear history). A summary of all artifacts and remaining errors is produced. Process observations are appended to learnings.md — a continuously growing record of pipeline friction and suggested improvements. The worktree and its branch are then cleaned up.

Produces
merged code on main learnings.md entry
Output Files & Directories

All artifacts are timestamped markdown files stored in the main repo root (never inside worktrees). Each artifact references its predecessors, forming a traceable chain from requirement to merged code.

Specification

specs/spec--*.md
Structured requirements: Goal, Decisions, Technical Design, Edge Cases, Constraints, Testing Strategy. Moves to specs/applied/ once planning begins.

Implementation Plan

Implementation Plans/impl--*.md
Step-by-step build instructions: files to touch, code to write, verification checklist, draft commit message. Self-contained — the implementer agent needs nothing else.

Working Log

Working Logs/wlog--*.md
Execution record: every file change, error encountered (with retry counts), deviation from plan, and verification results.

Audit Report

Working Logs/audit-impl--*.md
Independent verdict on spec compliance. Contains categorized failures, actionable errors with suggested fixes, and proposed process improvements.

Fixer Log

Working Logs/fixer-log--*.md
Records which audit errors were fixed, which were skipped (not actionable or requiring human judgment), and which failed.

Learnings

learnings.md
Append-only process knowledge base. Tracks pipeline friction with severity tiers, occurrence counts, and concrete improvement suggestions (including diffs).

Spec Lifecycle

specs/ is the inbox. specs/applied/ is the archive (spec has been planned or split). specs/team/ is the batch staging area (ready for /pipeline-team). A spec moves to applied/ only after planning begins or after /spec-splitter generates child specs from it.

Batch Mode with /pipeline-team

For multi-spec efforts, /pipeline-team orchestrates up to 5 concurrent pipelines with automatic dependency detection, sequential merge ordering, and failure recovery.

/pipeline-team Pre-flight Validate environment, discover specs in specs/team/ | Dependency Extract keywords from spec titles, build dependency graph Analysis Detect cycles, propose execution waves, wait for confirmation | Wave Execution Spawn up to 5 parallel pipelines (each runs /pipeline SKIP_MERGE) | Each teammate works in its own git worktree | Reports PIPELINE_COMPLETE or PIPELINE_FAILURE on finish | Merge Queue Process completed work sequentially: | rebase onto main → merge --ff-only → cleanup worktree | Broadcast MASTER_ADVANCED to active teammates | Failure Spawn repair agents for failed specs Handling Escalate to user if repair fails (retry / skip / abort) | Summary Write batch summary, aggregate learnings

Spec Splitter

/spec-splitter analyzes a large spec for complexity and, if warranted, decomposes it into independent child specs with shared foundations. Dependencies are wired via keyword embedding so /pipeline-team's automatic detection works correctly.

Dependency Detection

Keywords are extracted from spec titles (words > 4 chars, minus stopwords). Two or more matching keywords between specs creates a dependency edge. Cycles are detected and reported before execution begins.

Single vs. Batch Comparison

/pipeline /pipeline-team
Input One spec (interactive or pre-written) Multiple pre-written specs
Parallelism Sequential phases Up to 5 concurrent pipelines
Dependencies N/A Automatic keyword-based graph
Merge Immediate rebase + ff-only Sequential merge queue
Error handling Fix loop (2 cycles) Fix loop + repair agent + user escalation
Design Principles

Key architectural decisions and the reasoning behind them.

Independent Auditor

The audit agent has never seen the plan or working log. It reads only the original spec and the current code. This prevents confirmation bias — it cannot be influenced by what the implementer intended.

Git Worktree Isolation

Every implementation runs in a git worktree (a separate working directory on its own branch). The main branch is never modified until the explicit merge phase. Batch runs can have 5 worktrees active simultaneously.

Fast-Forward Only Merges

Worktrees are rebased before merging with --ff-only. This guarantees perfectly linear git history, making bisection and rollback straightforward.

Append-Only Learnings

Every pipeline run appends process observations to learnings.md, building a knowledge base of recurring friction. Each entry includes the affected phase, occurrence count, and a concrete suggested fix with a diff.

Reference Files as Templates

Each pipeline phase has a reference file (commands/references/pipeline/phase*.md) that serves as a prompt template with [VARIABLE] placeholders. The orchestrator substitutes values before passing to subagents. These are not documentation.

Artifact Isolation

All artifact directories exist only in the main repo root, never in worktrees. Subagents use absolute [MASTER_REPO_PATH] paths. This ensures every phase can find prior artifacts regardless of which worktree it runs in.

Artifact Chain

Every artifact references its predecessors. Any piece of code on main can be traced back to the spec decision that motivated it.

spec--*.md Structured requirements document | Goals, decisions, technical design v impl--*.md Step-by-step build plan | Files, code, verification checklist v wlog--*.md Execution record | Changes, errors, retries, deviations v audit-impl--*.md Independent verification | Goal 1: MET | Goal 2: UNMET | Actionable Error #1: ... v fixer-log--*.md Error resolution record | Error #1: FIXED | Error #2: SKIPPED v main branch Clean fast-forward merge, linear history