Multi-Agent Pipeline

8-phase AI development pipeline for Claude Code & Copilot CLI. Issue → analysis → plan → TDD → review → commit → PR in one command.

Drives a Jira issue or GitHub URL to a merged PR in one command (v11.5.0). 8 phases: Init · Analysis · Planning (approval gate) · TDD dev · CLI-aware parallel review (Fable + Sonnet on Claude Code, GPT + Opus + Sonnet on Copilot CLI, then Fable triage) · Test · Commit + PR · Report (PR body, Jira, Wiki, Confluence). Every loop is bounded and evidence-gated: deterministic gates before AI review, a 'passed' claim needs a log behind it, blocking findings can be confirmed by an auto-written repro test, and retry loops hard-stop at 3. Multi-repo orchestration with per-repo worktrees, per-phase cost ledger, cross-session learnings memory. Stack skills ship as versioned marketplace plugins. Runs natively on Claude Code and Copilot CLI — macOS / Linux / Windows. Full version history in the repo CHANGELOG.

Private RepositoryThis is a private repository. You need collaborator access to view the source code on GitHub.

Phases

Commands

220+

Skills

Sub-agents

Stable

Status

Tech Stack

Node.jsClaude CodeCopilot CLI221 Skills8 Sub-AgentsJSON Schemas

How It Works

Setup

🔑

Keychain

11 services · servicePatMap per identity

👤

Git Identity

identities[] · servicePatMap ownership

🔍

Repo Discovery

Local + Bitbucket + GitHub 90-day

🗺

Identity Routing

URL glob → identity auto-pick

📋

Stack Detect

iOS · Android · Backend · Frontend

🔒

Pre-commit

Secret scanning

Inputs (5 types)

GitHub Issue#316

GitHub URLgithub.com/.../issues/N

Jira IDPROJ-1234

Jira URLjira.../browse/...

Free Text"Fix dark mode bug"

Launch Modes (8 dispatch variants)

Claude/multi-agent "#316"Copilotmulti-agent "#316"

Normal0→1→2→3→4→5→6→7— All 8 phases, full review + Report

Claude/multi-agent "PROJ-1234"Copilotmulti-agent "PROJ-1234"

Jira0→1→2→3→4→5→6→7— All 8 phases, full review + Report

Claude/multi-agent:dev "#316"Copilotmulti-agent-dev "#316"

dev0→3→6→7— Init → Dev → Commit → Report (Opus)

Claude/multi-agent:autopilot "#316"Copilotmulti-agent-autopilot "#316"

autopilot0→1→2→3→4→5→6→7— Skip confirmations, auto-commit & PR

Claude/multi-agent:dev-autopilot "#316"Copilotmulti-agent-dev-autopilot "#316"

dev-autopilot0→3→6→7— Fastest: zero interaction

Claude/multi-agent:local "#316"Copilotmulti-agent-local "#316"

local0→1→2→3→4→5→6→7— No worktree, work on current branch

Claude/multi-agent:dev-local "#316"Copilotmulti-agent-dev-local "#316"

dev + local0→3→6→7— No worktree, work on current branch

Claude/multi-agent:dev-local-autopilot "#316"Copilotmulti-agent-dev-local-autopilot "#316"

dev-autopilot + local0→3→6→7— Fastest: zero interaction

Claude/multi-agent:local-autopilot "#316"Copilotmulti-agent-local-autopilot "#316"

autopilot + local0→1→2→3→4→5→6→7— Full pipeline + local + autopilot

Helper Commands

setup

Keychain token + Git identity onboarding

jira

Browse your open Jira issues → pick → launch

issue

Browse unassigned GitHub issues → pick → launch

status

List tasks across all projects

log #N

Show task log

resume #N

Resume a stopped task

kill #N

Delete worktree, logs preserved

review

Review only the current diff

refactor

Autonomous refactoring with TDD safety net

channels

Multi-channel reporter — PR · Jira · Confluence · Wiki (multi-select, humanizer, v5.7+ replaces enrich)

test

UI Bug Hunter (simulator/emulator auto-detect)

stack [platform]

Swap platform skills on-the-fly

language [en|tr]

Toggle outputLanguage (assistant explanations). Picker prompts stay English.

scan

Skill security (4-tier · warn-only · CI strict)

search

Log full-text search (smart ranking · ripgrep)

sync

6-target sync (incl. plan-driven figma source pull)

update

Upgrade: git pull + install + migrate

clear-logs

Clean global log directory

purge

Full reset (double confirmation)

help

Usage guide and examples

UI Testing (Standalone)

🧪

test

Full simulator test - screenshot all screens

🌙

test "dark mode"

Dark mode bug test

♿

test "accessibility"

Accessibility audit - labels, tap targets, contrast

🔤

test "dynamic type"

Large text size test

📦

test "store-ready"

Full audit: visual + accessibility + archive compliance

🔐

test "biometric"

Face ID / Touch ID flow test

⚡

test "performance"

Launch time + scroll performance test

Stack Swap

Swap platform skills on-the-fly

stack iosstack androidstack backendstack mobilestack all

Skills (60+)

Pluggable knowledge modules injected into agents

🍎iOS · SwiftUI · UIKit · CoreData

🤖Android · Compose · Hilt · Room

⚙FastAPI · NestJS · Docker · CI/CD

🌐React · Next.js · Tailwind · Vue

✓Clean Code · TDD · Architecture · Security

🔧Git Actions · Figma · ASO · Audit Scripts

Pipeline Phases

Init

Multi-select picker

Identity routing

Fetch-fail 4-opt

N worktrees (serial)

Branch collision auto -v2

Step 0 language (en/tr)

Analysis

Parallel Explore

Opus model

Codebase scan

Planning

Task breakdown

Architecture

User approval

Todo repo tagging

Dev

TDD: Red→Green→Refactor

Per-repo worktree switch

Build verify

Max 3 retry

component → figma-to-component skill delegate

Review

Deterministic gates BEFORE AI review

Combined diff (repo headers)

crossRepo findings

Claude: Opus + Sonnet · Copilot: + GPT-5.4 → triage

Test

UI Bug Hunter

Dark/Light test

A11y audit

Simulator boot

Commit

Per-repo commit + push

Push-must-succeed (5 retries)

Cross-linked sibling PRs

Never auto-closes issues (4 approvals)

Report

Step 1: Channels dispatch — PR · Jira · Confluence · Wiki (multi-select, humanizer)

Autopilot ALWAYS pauses — 30-min timeout → session ends (resumable)

Step 2: agent-log · Quality & Metrics · telemetry

Step 3: Knowledge base + memory

Phase 0 - Interactive Init (8 Steps)

PARSE

Parse input, fetch from Jira/GitHub

→

PROJECT

Multi-select picker · recentGroups

→

BRANCH

TTL filter · collision auto -v2/-v3 · fetch-fail 4-opt

→

DESIGN?

Figma URL / screenshot (optional)

→

BRANCH NAME

Shared name · kebab rules · 50-char

→

IDENTITY

platformIdentityRouting · per-repo lookup

→

INSTRUCTION

Auto-detect .instructions/ directory

→

WORKSPACE

Multi-repo: N worktrees · serial · rollback

Sub-Agents (6)

🔍

Code Reviewer

Security, architecture, quality

🗺

Explorer

Codebase scan, patterns, impact areas

🍎

iOS Architect

Design decisions, patterns, modules

🤖

Android Architect

Design decisions, patterns, modules

⚙

Backend Architect

API design, data modeling, architecture

🛡

Security Auditor

Vulnerabilities and compliance

Component Pipeline (Figma → SwiftUI)

Figma URL detect→

Token extraction→

Config + View→

Modifiers→

Code Connect→

3-layer tests→

14-item review

Key Features

⚙ Phase 7 Report (Jira → Wiki+Figma → Confluence → Log → Knowledge)⚙ Skill Security Scanner (tiered · warn-only · CI strict · /multi-agent:scan)⚙ Log Search (smart ranking · filters · ripgrep · /multi-agent:search)⚙ Generic Figma-to-Component (iOS + Android)⚙ 4-Adapter Wiki (submodule / in-repo / github-wiki / separate-repo)⚙ Issue → Jira → Wiki Triad (autopilot-aware)⚙ Corporate Hosts in Setup (Jira / Confluence / Bitbucket inline prompt)⚙ Live Progress-Line Contract (quiet/normal/verbose)⚙ Plan-Driven Upstream Sync (--plan → review → apply)⚙ Overlay Protection (local-overlay: true frontmatter)⚙ Cross-CLI Parity (26 cmds + 37 figma skills identical)⚙ Build queue serialized with lock file⚙ Auto-detects iOS/Python/Node/Docker/Go⚙ Deterministic gates BEFORE AI review⚙ Multi-Repo Orchestration⚙ Platform Identity Routing⚙ Push-Must-Succeed (5 retries)⚙ Fetch-Fail 4-Option Flow⚙ Never auto-closes issues (4 approvals)⚙ PAT Audit Logging (SHA-256)⚙ 49 Smoke Suites (~870 assertions)⚙ Lazy file loading for token efficiency⚙ Pre-commit secret detection hook⚙ Autopilot Phase 2 Safety Classifier (v7.0.G · default-on · score≥50 → pause)⚙ Dynamic Trigger-Based Skill Loading (v7.0.I · 193-entry index · install.js --index-only)⚙ Per-Persona Model Routing (v6.1.D · preferredModel frontmatter · explorer → sonnet)⚙ OpenTelemetry Span Emission (v6.1.C · MULTI_AGENT_OTEL_SPANS=1 · JSONL)⚙ Phase 4 Disagreement Round (v6.1.B · opt-in · mixed-verdict rebuttal pass)⚙ Cost Summary in PR Body (v6.1.J · per-phase tokens + est. USD)⚙ Per-Repo File-System Memory Layer (v6.2.E · .multi-agent/memory/ · opt-in)⚙ Golden-Task Eval Harness (v6.2.F · 2 seed fixtures · wired to npm test)⚙ Skill Manifest Signing + Verify (v6.2.H · 193 SHA-256 · install-time warn-only)

Output

✓

Reviewed PR

Per-repo PRs · cross-linked siblings

📊

Report

Quality & Metrics · token rollup

🧠

Knowledge

Cross-session memory

📦

Components

Config + View + Tests

📁

Logs

~/.claude/logs/multi-agent/{project}/{task-id}/

Live Replay — watch commands run end-to-end

Mode

Input

claude-code · /multi-agent PROJ-1234

▊

Tracker

8 phases · 2-model review · Report delivery

○0Init

○1Analysis

○2Planning

○3Dev

○4Review

○5Test

○6Commit

○7Report

running… · line 0/42

Simulated replay — actual pipeline emits the same progress-line shape (`→ verb object target`) at immediate flush.

Features

8-Phase Pipeline

Issue → analysis → plan (approval gate) → TDD dev → parallel review + triage → test → commit/PR → report. Every retry loop is bounded (hard-stop at 3).

CLI-Aware Parallel Review + Fable Triage

2 models on Claude Code (Fable + Sonnet), 3 on Copilot CLI (GPT + Opus + Sonnet); Fable triage filters false positives. Blocking findings can be confirmed by an auto-written repro test (verify-by-test).

Deterministic Safety Gates

Build/lint/test/secret gates before AI review; a 'passed' claim needs a log behind it (default-FAIL evidence gate); diff risk scoring flags risky files and shrinking tests (immutable-test backstop).

Multi-Repo Orchestration

Per-repo worktrees, platform identity routing, integration builds, and file-based state so tasks resume across sessions and machines.

Cost & Telemetry

Per-phase token ledger, end-of-run cost breakdown naming the top cost driver, budget ceilings, and a model fallback contract (fable → opus → sonnet).

Cross-Session Memory

Persistent learnings ledger (rejected review preferences never get re-flagged), triage memory, and structured handoff blocks so long runs re-enter from durable artifacts, not conversation memory.

Available Commands

Claude Code (colon-form)	Copilot CLI (dash-form)	Category	Description
`/multi-agent "task"`	`multi-agent "task"`	Full pipeline	Full 8-phase pipeline with worktree + interactive confirmations.
`/multi-agent:autopilot "task"`	`multi-agent-autopilot "task"`	Full pipeline	Same pipeline, zero confirmations - fire and forget.
`/multi-agent:dev "task"`	`multi-agent-dev "task"`	Fast mode	Skips analysis/planning/review gates - Init → Dev(Opus) → Commit → Report.
`/multi-agent:jira`	`multi-agent-jira`	Interactive	Browse your open Jira issues in a terminal picker and launch.
`/multi-agent:issue`	`multi-agent-issue`	Interactive	Browse unassigned GitHub issues, auto-assign, and launch.
`/multi-agent:review`	`multi-agent-review`	Ops	Standalone parallel review on a branch diff or PR, with triage.
`/multi-agent:resume [#id]`	`multi-agent-resume [#id]`	Ops	Resume a paused/failed task from its last completed phase (file-based state).
`/multi-agent:setup`	`multi-agent-setup`	Meta	First-run wizard - tokens, Git identity, per-project routing.
`/multi-agent:help`	`multi-agent-help`	Meta	Bilingual usage guide - all 36 commands, modes matrix, preferences.

Back to overview