jmagly/aiwg

Plugin marketplace

AIWG - Modular agentic framework for SDLC, marketing automation, and workflow orchestration. 200+ agents, 67+ CLI commands, 400+ deployable agent/skill/command/rule artifacts.

GitHub stars: 229
plugins: 40
last updated: Nov 11, 2026

View on GitHub

Add marketplace

/plugin marketplace add jmagly/aiwg

Run it inside Claude Code, then install plugins from it with /plugin.

Plugins

1agent-loopIterative AI coding loops with automatic recovery - iteration beats perfection2026.11.4version

2agent-persistenceHuman-in-the-loop (HITL) gate definitions for agent operations. Provides reusable YAML gates for destructive-action authorization, false-positive override, and recovery escalation. Loaded by agent loops and orchestrators that need bounded human checkpoints.2026.11.4version

3agentic-installerStructured YAML manifests for reproducible, agent-driven software installation across platforms. Scripts are the primary artifact; agentic instructions handle adaptation and recovery.2026.11.4version

4aiwg-devDeveloper tooling for building AIWG itself and AIWG addons/frameworks. Not for end users — install explicitly with `aiwg use aiwg-dev`.2026.11.4version

5aiwg-evalsAutomated evaluation framework for agent quality, based on KAMI benchmark methodology and ReAct patterns2026.11.4version

6auto-memoryAutomatic memory seed templates for AIWG projects2026.11.4version

7browser-controlDrive a real, user-installed Chromium-derived browser from an AIWG agent. Wraps @playwright/mcp with a setup wizard, health-check doctor, allow-list enforcement, and an opinionated agent persona that respects authorization and audit boundaries.2026.11.4version

8color-paletteColor palette selection and review tooling with color theory fundamentals, current trend research, and accessibility analysis.2026.11.4version

9compound-memoryGoverned orchestration across AIWG line memory, semantic memory, and llm-wiki.2026.11.4version

10context-curatorContext curation and distractor filtering for production-grade agent reliability2026.11.4version

11daemonPersistent daemon session capabilities: Concierge front-end, session memory, scheduler integration2026.11.4version

12doc-intelligenceDocumentation intelligence addon for scraping, extraction, analysis, and generated-docs auditing.2026.11.4version

13droid-bridgeMCP server bridging Claude Code to Factory Droid for batch operations and automated fixes2026.11.4version

14forensicsDigital forensics and incident response framework with 14 specialized agents covering target profiling, evidence acquisition, log/memory/container/cloud analysis, IOC extraction, and reporting.2026.11.4version

15guided-implementationBounded iteration control for autonomous issue-to-code implementation2026.11.4version

16hooksClaude Code hooks for workflow tracing and observability.2026.11.4version

17knowledge-baseKnowledge-base / wiki framework with skills for ingestion, query, and lint. Build a structured, citable corpus with cross-references and concept pages.2026.11.4version

18line-memoryBounded, plain-text project memory with least-recently-used retention.2026.11.4version

19llm-wikiLLM-maintained markdown wiki that compounds as sources are ingested. Thin topology declaration on the semantic memory kernel — ships schema profiles and page templates, no custom mechanics.2026.11.4version

20marketingMarketing automation framework with 37 specialized agents for campaign management.2026.11.4version

21media-curatorMedia archive management framework with 7 specialized agents for source discovery, acquisition (yt-dlp / Internet Archive / Bandcamp), quality assessment, metadata tagging, and provenance tracking.2026.11.4version

22nlp-prodTools, skills, and CLI extensions for designing and productionizing LLM inference pipelines. Pattern-guided, slim by default, eval-first.2026.11.4version

23opsOperational infrastructure framework with 12 specialized agents covering incident response, runbook execution, fleet inventory, certificate lifecycle, and disaster recovery planning.2026.11.4version

24prose-integrationTools for reading, parsing, validating, and executing OpenProse programs from AIWG workflows2026.11.4version

25researchResearch workflow framework with 9 specialized agents for discovery, acquisition, synthesis, citation management, GRADE quality assessment, and OAIS-compliant archival.2026.11.4version

26rlmRLM-inspired recursive context decomposition for processing arbitrarily large codebases and document corpora through programmatic sub-agent delegation2026.11.4version

27sdlcComplete SDLC framework with 180+ specialized agents for software development lifecycle management.2026.11.4version

28security-engineeringApplied security framework for cryptographic primitive selection, chain-of-trust design, authentication factor analysis, supply-chain trust, and physical-threat modeling. Complements OWASP-style application audits.2026.11.4version

29semantic-memoryTopology-agnostic semantic memory operations: ingest, lint, query-capture, and structured event logging. Consumers declare a memory topology in their manifest.json; kernel skills read that contract to parameterize behavior.2026.11.4version

30skill-factoryBuild, enhance, validate, and package Claude skills end-to-end. Coordinates skill-builder, skill-enhancer, quality-checker, and skill-packager via the skill-architect agent.2026.11.4version

31star-promptTasteful prompt to encourage users to star the repository after successful command completion2026.11.4version

32testing-qualityEvidence-bound test conformance, platform protocols, normalization transactions and research-guided testing workflows2026.11.4version

33trainingCorpus-to-dataset pipeline for AI training data curation. Ingests sources, synthesizes examples, generates DPO/KTO preference pairs, applies decontamination, and exports to Alpaca/ShareGPT/ChatML/JSONL/Parquet with provenance. Optional Python runtime (aiwg-training CLI) for scale.1.0.0version

34twelve-factorDesign-time and audit-time workflows for Twelve-Factor and modern 12+ Factor cloud-native application practices.2026.11.4version

35uat-mcpAgent-executable acceptance testing via MCP connections — generate, execute, and report on UAT plans that validate MCP tool surfaces.2026.11.4version

36utilsCore AIWG utilities for context regeneration and workspace management.2026.11.4version

37validation-completeValidation Complete for AIWG2026.11.4version

38verbalized-samplingTraining-free prompting technique that improves output diversity by 1.6-2.1x through verbalized probability distributions, addressing RLHF mode collapse2026.11.4version

39voiceVoice profile system for consistent, authentic writing.2026.11.4version

40writingWriting quality validation and AI pattern detection.2026.11.4version

Details

Repository: github.com/jmagly/aiwg
Categories: productivity, sdlc, development
Listed since: Jan 13, 2026