What is productionos?

An AI engineering toolkit for Claude Code and Codex that provides many specialized agents, commands, and hooks for software projects.

Use it for tasks such as architecture, code review, database checks, security analysis, research, browser work, and multi-agent development.

It brings recurring engineering activities into a shared workflow instead of requiring each task to be organized from scratch.

productionos — Plugin for Claude Code by ShaheerKhawaja: An AI engineering toolkit for Claude Code and Codex…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add ShaheerKhawaja/ProductionOS

agentmods

npx agentmods add plugins/shaheerkhawaja/productionos/productionos

Clone the repo

git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOS

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/shaheerkhawaja/productionos/productionos.svg)](https://agentmods.dev/plugins/shaheerkhawaja/productionos/productionos)

Your own site

<a href="https://agentmods.dev/plugins/shaheerkhawaja/productionos/productionos"><img src="https://agentmods.dev/badge/plugins/shaheerkhawaja/productionos/productionos.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 4 skills, 41 commands, 11 agents cost 2,217 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

productionos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/plugin.json · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "productionos",
  "description": "AI engineering OS for Claude Code and Codex — 80 agents, 41 commands, 18 hooks.",
  "version": "2.0.0-beta.1",
  "author": {
    "name": "Shaheer Khawaja",
    "url": "https://github.com/ShaheerKhawaja"
  },
  "license": "MIT",
  "homepage": "https://github.com/ShaheerKhawaja/ProductionOS",
  "repository": "https://github.com/ShaheerKhawaja/ProductionOS",
  "keywords": [
    "productionos",
    "claude-code-plugin",
    "codex-plugin",
    "agentic-dev",
    "multi-agent",
    "recursive-improvement"
  ],
  "agents": [
    "./agents/adversarial-reviewer.md",
    "./agents/aiml-engineer.md",
    "./agents/api-contract-validator.md",
    "./agents/approval-gate.md",
    "./agents/architecture-designer.md",
    "./agents/asset-generator.md",
    "./agents/browser-controller.md",
    "./agents/business-logic-validator.md",
    "./agents/code-reviewer.md",
    "./agents/comms-assistant.md",
    "./agents/comparative-analyzer.md",
    "./agents/complexity-analyzer.md",
    "./agents/context-retriever.md",
    "./agents/convergence-monitor.md",
    "./agents/database-auditor.md",
    "./agents/db-creator.md",
    "./agents/debate-tribunal.md",
    "./agents/decision-loop.md",
    "./agents/deep-researcher.md",
    "./agents/density-summarizer.md",
    "./agents/dependency-scanner.md",
    "./agents/design-system-architect.md",
    "./agents/designer-upgrade.md",
    "./agents/discuss-phase.md",
    "./agents/document-parser.md",
    "./agents/documentation-auditor.md",
    "./agents/dynamic-planner.md",
    "./agents/e2e-architect.md",
    "./agents/ecosystem-scanner.md",
    "./agents/frontend-designer.md",
    "./agents/frontend-scraper.md",
    "./agents/gap-analyzer.md",
    "./agents/gitops.md",
    "./agents/guardrails-controller.md",
    "./agents/infra-setup.md",
    "./agents/intake-interviewer.md",
    "./agents/llm-judge.md",
    "./agents/merge-conflict-resolver.md",
    "./agents/metaclaw-learner.md",
    "./agents

Read the full file on GitHub · 109 lines

Contents

What it installs

The manifest is a name and a version. 4 skills, 41 commands, 11 agents travel with it, and installing the plugin installs all of them — 2,217 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 1.4 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 109 lines scan A 5c0667f1aec8

Subscribe to this mod's changes

productionos is a plugin published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Multi-Agent agentic-development claude-code claude-code-plugin llm-judge prompt-engineering

fellowship

Multi-quest orchestrator for Claude Code. Coordinates parallel quests via agent teams, with structured research-plan-implement lifecycles and isolation via worktrees.

justinjdev/fellowship · not measured

context-ledger

Structured product development methodology with traceable evidence, explicit decisions, and constrained spec generation. Forces auditability through semantic IDs, quality gates, and impact-aware updates.

synaptiai/synapti-marketplace · not measured

agent-harness

Multi-agent harness for Claude Code: Planner→Generator→Evaluator sprints executed as background dynamic workflows (Agent-tool fallback), fable/opus/sonnet/haiku model routing with per-role reasoning effort, harness-engineering framework for design/diagnosis, and Anthropic 2026-04-04 P-G-E pattern.

bouob/agent-harness · not measured

lead-dev-os

Spec & context-driven framework for Claude Code development. Structured skills for product planning, spec writing, task scoping, and context-aware implementation.

CaptainMe-AI/lead-dev-os · not measured

manager

Product and project management discipline for the NVZver marketplace. Agents: product-manager — shapes vague ideas into structured draft pitches and returns their full content + pending human gates (writes no files); project-manager — stewards the roadmap, recommends what to build next with dependency/risk/value…

NVZver/claude-marketplace · not measured

hato

Carrier-pigeon messaging between Claude Code sessions — send messages and files, and get woken up by other sessions across your machines.

severzemlya/hato · not measured