ShaheerKhawaja

60 mods across 1 repository, 8 stars between them.

productionos

02

ShaheerKhawaja/ProductionOS

Plugin Claude Code

AI engineering OS for Claude Code and Codex — 80 agents, 41 commands, 18 hooks.

8 4mo ago A tokens not measured original MIT

agentic-eval

03

ShaheerKhawaja/ProductionOS

Command Claude Code

Niche-agnostic agentic evaluator using CLEAR v2.0 framework — 6-domain assessment, 8 analysis dimensions, 6-tier source prioritization, evidence strength ratings, and decision trees. Evaluates any plan, codebase, or research output.

8 4mo ago A 58 tokens original MIT

auto-mode

04

ShaheerKhawaja/ProductionOS

Command Claude Code

Idea-to-running-code lifecycle orchestration. 10-phase pipeline with 5 hard decision gates, wave-based parallelism, and STATE.json resumability. Composes /deep-research, /auto-swarm-nth, /production-upgrade, /security-audit, and /ship into a single end-to-end flow.

8 4mo ago A 68 tokens original MIT

auto-optimize

05

ShaheerKhawaja/ProductionOS

Command Claude Code

Self-improving agent optimization — generates challenger variants of any agent/command, benchmarks against baseline, promotes winners, logs learnings to instincts. Inspired by Karpathy's autoresearch pattern.

8 4mo ago A 42 tokens original MIT

auto-swarm-nth

06

ShaheerKhawaja/ProductionOS

Command Claude Code

Nth-iteration agent swarm — spawns parallel agent waves, evaluates strictly per wave, re-swarms gaps until 100% coverage and 10/10 quality. Can invoke any ProductionOS skill or command within waves.

8 4mo ago A 51 tokens original MIT

auto-swarm

07

ShaheerKhawaja/ProductionOS

Command Claude Code

Distributed agent swarm orchestrator — spawns parallel subagent clusters for any task with configurable depth, swarm size, and convergence criteria.

8 4mo ago A 29 tokens original MIT

autoloop

08

ShaheerKhawaja/ProductionOS

Command Claude Code

Autonomous recursive improvement loop for a single target. Runs gap analysis, recursive refinement, evaluation, and convergence checks until the target reaches quality threshold or converges.

8 4mo ago A 36 tokens original MIT

brainstorming

09

ShaheerKhawaja/ProductionOS

Command Claude Code

Idea exploration before building — understand the problem, propose approaches, present design, get approval. HARD-GATE: no implementation until design is approved.

8 4mo ago A 33 tokens original MIT

browse

10

ShaheerKhawaja/ProductionOS

Command Claude Code

Headless browser for QA testing, site inspection, and interaction verification. Navigate, screenshot, click, fill forms, capture snapshots.

8 4mo ago A 28 tokens original MIT

build-productionos

11

ShaheerKhawaja/ProductionOS

Command Claude Code

ProductionOS smart router — single entry point that routes to the right pipeline based on intent. The ONLY command new users need to know.

8 4mo ago A 31 tokens original MIT

context-engineer

12

ShaheerKhawaja/ProductionOS

Command Claude Code

Context engineering agent — researches context window optimization from arxiv, builds token-efficient context packages for downstream agents, manages cross-session persistence via MetaClaw.

8 4mo ago A 34 tokens original MIT

debug

13

ShaheerKhawaja/ProductionOS

Command Claude Code

Systematic debugging with hypothesis tracking — reproduce, hypothesize, test, narrow, fix. Never guess-and-check.

8 4mo ago A 25 tokens original MIT

deep-research

14

ShaheerKhawaja/ProductionOS

Command Claude Code

8-phase autonomous research pipeline with multi-source discovery, 4-layer citation verification, hypothesis generation, and PIVOT/REFINE/PROCEED decision loops. Confidence-gated — loops until 95%+ confidence.

8 4mo ago A 49 tokens original MIT

designer-upgrade

15

ShaheerKhawaja/ProductionOS

Command Claude Code

Full UI/UX redesign pipeline — audits design, creates design systems, generates interactive HTML mockups, launches local browser for user interaction. Fuses /production-upgrade rigor with design agency methodology.

8 4mo ago A 43 tokens original MIT

devtools

16

ShaheerKhawaja/ProductionOS

Command Claude Code

ProductionOS Mission Control — launch Claude DevTools, show session dashboard with eval convergence, agent dispatches, cost tracking, and hot file intelligence.

8 4mo ago A 32 tokens original MIT

document-release

17

ShaheerKhawaja/ProductionOS

Command Claude Code

Post-ship documentation update — reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped.

8 4mo ago A 42 tokens original MIT

frontend-upgrade

18

ShaheerKhawaja/ProductionOS

Command Claude Code

Full-stack frontend upgrade pipeline — fuses /production-upgrade iterative audit with /plan-ceo-review vision and /plan-eng-review rigor. Deploys parallel auto-swarm agents for iterative audit and execution. Enriched with /deep-research for competitive parity.

8 4mo ago A 56 tokens original MIT

learn-mode

19

ShaheerKhawaja/ProductionOS

Command Claude Code

Interactive code tutor — breaks down codebase logic, explains complexities, translates technical concepts for the user. Ideal after /btw commands. Teaches the WHY behind the code, not just the WHAT.

8 4mo ago A 43 tokens original MIT

logic-mode

20

ShaheerKhawaja/ProductionOS

Command Claude Code

Business idea → production-ready plan pipeline. User provides an idea or business plan, agent researches market, competitors, existing solutions, challenges assumptions, identifies flaws, and builds a comprehensive execution plan with auto-document population.

8 4mo ago A 45 tokens original MIT

max-research

21

ShaheerKhawaja/ProductionOS

Command Claude Code

Nuclear-scale autonomous research — deploys 500-1000 agents in ONE massive simultaneous wave for exhaustive topic saturation. Deep-research methodology × auto-swarm scale = maximum parallel intelligence. WARNING: Extreme resource consumption.

8 4mo ago A 48 tokens original MIT

omni-plan-nth

22

ShaheerKhawaja/ProductionOS

Command Claude Code

Nth-iteration omni-plan — recursive orchestration that chains ALL ProductionOS skills and agents, evaluates strictly per iteration, and loops until 10/10 is achieved. Each iteration can invoke any command or skill in the system.

8 4mo ago A 51 tokens original MIT

omni-plan

23

ShaheerKhawaja/ProductionOS

Command Claude Code

ProductionOS flagship — 13-step orchestrative pipeline with tri-tiered evaluation, recursive convergence, CEO/Eng/Design review chain, CLEAR framework evaluation, multi-model judge tribunal, and autonomous PIVOT/REFINE/PROCEED decisions. Targets 100% production-ready output.

8 4mo ago A 62 tokens original MIT

plan-ceo-review

24

ShaheerKhawaja/ProductionOS

Command Claude Code

CEO/founder-mode plan review — rethink the problem, find the 10-star product, challenge premises. Four modes: SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, SCOPE REDUCTION.

8 4mo ago A 52 tokens original MIT