Plugin

claude-apd

Name: claude-apd
Author: zstevovich

By zstevovich

Agent Pipeline Development — enforced multi-agent pipelines with mechanical guardrails

Component Overview

Commands

Agents

apd-audit, apd-brainstorm +6

Skills

PreCompact, PreToolUse +11

Hooks

MCP Servers

LSP Servers

Output Styles

Themes

apd-session-context

Monitors

Install

npx claudepluginhub zstevovich/claude-apd --plugin claude-apd

Setup Configuration

This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.

stack

Backend stack: nodejs, php, python, dotnet, go, java

${user_config.stack}

author_name

Author name for git commits (no AI signatures)

${user_config.author_name}

project_name

Your project name (e.g., MyCRM, TaskFlow)

${user_config.project_name}

Component Details

Skills (8)

apd-audit

/apd-audit

Use when you need to verify APD is correctly configured in the current project. Qualitative audit of agents, hooks, CLAUDE.md, pipeline, and guardrails — goes deeper than verify-apd.

apd-brainstorm

/apd-brainstorm

Use when the user's task is vague, broad, or has multiple possible approaches — before writing the APD spec card. Triggers on unclear scope, ambiguous requirements, or "improve X" style requests.

apd-debug

/apd-debug

Use when encountering any bug, test failure, build failure, or unexpected behavior during APD pipeline. MANDATORY before re-dispatching builder after verifier failure or critical review finding.

apd-finish

/apd-finish

Use when a successful APD pipeline commit has just completed and a push/PR/keep decision is needed. MANDATORY after every pipeline commit.

apd-github

/apd-github

Use when the project has GitHub Projects configured and you need to sync pipeline tasks with the board. Creates issues for specs, moves cards through columns, closes on completion.

apd-miro

/apd-miro

Use when the project has a Miro board configured and you need to update the pipeline dashboard. Visualizes current status, completed tasks, and metrics.

apd-setup

/apd-setup

Use when setting up APD in a new project or maintaining an existing one. Generates CLAUDE.md, agents, rules, memory, verify-all.sh. Also runs gap analysis and fixes missing pieces on existing projects.

apd-tdd

/apd-tdd

Use when implementing any feature or fixing any bug as a Builder agent. Write failing test first, then minimal code to pass. MANDATORY for all APD builder dispatches.

Hooks (1)

Review workflow modifications before installing

13 hooks across 8 events

Monitors (1)

Runs unsandboxed at plugin trust level

apd-session-context

Load APD project context and run self-healing checks

README

Enforced multi-agent pipelines with mechanical guardrails for AI-assisted software development.
Works with Claude Code and OpenAI Codex.

Getting Started · Interactive Demo · Pipeline Runs · Changelog

v6.0.3 · MIT · macOS + Linux

APD Demo

What is APD?

APD enforces a disciplined workflow where specialised agents build code through a gated pipeline. Every step is mechanically enforced — hooks block violations, not documentation.

Spec → Builder → Reviewer → [Adversarial] → Verifier → Commit

Agent — work divided among specialised agents with scoped permissions
Pipeline — gated flow with mechanical enforcement at every step
Development — one feature = one pipeline cycle = one commit

Quick start

Claude Code:

/plugin marketplace add zstevovich/claude-apd          # one time
/plugin install claude-apd@zstevovich-plugins          # per project
/apd-setup                                             # configure
bash .claude/bin/apd verify                            # check setup

Codex (OpenAI) — preferred, via plugin marketplace (validated on Codex 0.124):

# Prerequisites: brew install uv jq   (codex_hooks is stable on 0.124, no feature flag needed)
codex plugin marketplace add zstevovich/claude-apd             # one time, pulls latest main
printf '\n[plugins."apd@codex-apd"]\nenabled = true\n' >> ~/.codex/config.toml   # enable
cd <your-project> && codex                                     # open TUI in target project
# On first user prompt in the fresh session, APD auto-scaffolds
# .codex/ + .apd/ + AGENTS.md and MCP tools become available
# (apd_ping, apd_doctor, apd_guard_write, ...).

Codex — alternative, direct-drop (no marketplace):

git clone https://github.com/zstevovich/claude-apd ~/apd && \
    export PATH="$HOME/apd/bin:$PATH"                  # live source at ~/apd
apd cdx init                                           # scaffold .codex/ + .apd/ + AGENTS.md
apd cdx agents add code-reviewer                       # populate agents
apd cdx agents add backend-builder src/ config/
apd cdx skills install                                 # symlink phase skills into ~/.codex/skills/
apd cdx doctor                                         # audit setup
codex                                                  # start session; "run apd_ping"

Upgrading

Claude Code:

/plugin update claude-apd@zstevovich-plugins                  # pulls latest from main
# Restart the CC session — skill slash commands re-register on session start

Codex — marketplace install (Git source):

codex plugin marketplace upgrade codex-apd                    # pulls latest main, replaces cache atomically
# Open a new TUI session — first user prompt picks up the new version

To pin the upgrade to a specific tag or branch (e.g. for pre-release testing):

codex plugin marketplace remove codex-apd
codex plugin marketplace add zstevovich/claude-apd@v6.0.3     # or @<branch> for a feature branch

Codex — direct-drop install:

bash .codex/bin/apd update                                    # git pull --ff-only + idempotent re-init
# --check-only      # dry-run, don't pull or write
# --skip-pull       # only re-run install-codex-config locally

Codex SessionStart quirk (upstream). Per openai/codex#15269, Codex 0.124 fires the TUI SessionStart hook when the user submits the first prompt, not at banner display. Practically: gap-analysis runs on first turn, not at open. MCP tools are available immediately.

See Getting Started for both walkthroughs.

Five roles

Role	Model	Effort	Responsibility
Orchestrator	opus	max	Coordinates pipeline, writes spec, dispatches agents, commits
Builder	sonnet	xhigh	Implements code per spec, scoped to specific files
Reviewer	opus	max	Finds bugs, security issues, edge cases (read-only)
Adversarial Reviewer	sonnet	max	Context-free review — no spec knowledge, fresh perspective
Verifier	—	—	Script: build + test + spec traceability check

Pipeline flow

APD Pipeline: Spec → Plan → Builder → Reviewer → Adversarial → Verifier → ✓

Pipeline commands

View full README on GitHub

Similar Plugins

claude-code-toolkit

1.4k

Complete developer toolkit for Claude Code

Stats

Version6.0.3

Stars4

MaintenanceExcellent

LicenseMIT

Last CommitApr 27, 2026

AddedApr 8, 2026

Actions

View on GitHub View README Plugin Marketplace JSON Homepage

Available In

zstevovich-plugins4

Safety Signals

Critical

Matches all tools

Hooks run on every tool call, not just specific ones

Caution

Executes bash commands

Hook triggers when Bash tool is used

Modifies files

Hook triggers on file write and edit operations

What is APD?

APD enforces a disciplined workflow where specialised agents build code through a gated pipeline. Every step is mechanically enforced — hooks block violations, not documentation.

Spec → Builder → Reviewer → [Adversarial] → Verifier → Commit

Agent — work divided among specialised agents with scoped permissions
Pipeline — gated flow with mechanical enforcement at every step
Development — one feature = one pipeline cycle = one commit

Quick start

Claude Code:

/plugin marketplace add zstevovich/claude-apd          # one time
/plugin install claude-apd@zstevovich-plugins          # per project
/apd-setup                                             # configure
bash .claude/bin/apd verify                            # check setup

Codex (OpenAI) — preferred, via plugin marketplace (validated on Codex 0.124):

# Prerequisites: brew install uv jq   (codex_hooks is stable on 0.124, no feature flag needed)
codex plugin marketplace add zstevovich/claude-apd             # one time, pulls latest main
printf '\n[plugins."apd@codex-apd"]\nenabled = true\n' >> ~/.codex/config.toml   # enable
cd <your-project> && codex                                     # open TUI in target project
# On first user prompt in the fresh session, APD auto-scaffolds
# .codex/ + .apd/ + AGENTS.md and MCP tools become available
# (apd_ping, apd_doctor, apd_guard_write, ...).

Codex — alternative, direct-drop (no marketplace):

git clone https://github.com/zstevovich/claude-apd ~/apd && \
    export PATH="$HOME/apd/bin:$PATH"                  # live source at ~/apd
apd cdx init                                           # scaffold .codex/ + .apd/ + AGENTS.md
apd cdx agents add code-reviewer                       # populate agents
apd cdx agents add backend-builder src/ config/
apd cdx skills install                                 # symlink phase skills into ~/.codex/skills/
apd cdx doctor                                         # audit setup
codex                                                  # start session; "run apd_ping"

Upgrading

Claude Code:

/plugin update claude-apd@zstevovich-plugins                  # pulls latest from main
# Restart the CC session — skill slash commands re-register on session start

Codex — marketplace install (Git source):

codex plugin marketplace upgrade codex-apd                    # pulls latest main, replaces cache atomically
# Open a new TUI session — first user prompt picks up the new version

To pin the upgrade to a specific tag or branch (e.g. for pre-release testing):

codex plugin marketplace remove codex-apd
codex plugin marketplace add zstevovich/claude-apd@v6.0.3     # or @<branch> for a feature branch

Codex — direct-drop install:

bash .codex/bin/apd update                                    # git pull --ff-only + idempotent re-init
# --check-only      # dry-run, don't pull or write
# --skip-pull       # only re-run install-codex-config locally

Codex SessionStart quirk (upstream). Per openai/codex#15269, Codex 0.124 fires the TUI SessionStart hook when the user submits the first prompt, not at banner display. Practically: gap-analysis runs on first turn, not at open. MCP tools are available immediately.

See Getting Started for both walkthroughs.

Five roles

Role	Model	Effort	Responsibility
Orchestrator	opus	max	Coordinates pipeline, writes spec, dispatches agents, commits
Builder	sonnet	xhigh	Implements code per spec, scoped to specific files
Reviewer	opus	max	Finds bugs, security issues, edge cases (read-only)
Adversarial Reviewer	sonnet	max	Context-free review — no spec knowledge, fresh perspective
Verifier	—	—	Script: build + test + spec traceability check

Pipeline flow

APD Pipeline: Spec → Plan → Builder → Reviewer → Adversarial → Verifier → ✓

claude-apd

Component Overview

Install

Setup Configuration

Component Details

Skills (8)

Hooks (1)

Monitors (1)

README

What is APD?

Quick start

Upgrading

Five roles

Pipeline flow

Pipeline commands

Similar Plugins

claude-code-toolkit

claude-apd

Component Overview

Install

Setup Configuration

Component Details

Skills (8)

Hooks (1)

Monitors (1)

README

What is APD?

Quick start

Upgrading

Five roles

Pipeline flow

Pipeline commands

Similar Plugins

claude-code-toolkit

claude-buddy

beads

superpowers