By Alex-Kopylov
Assistant setup, instruction hygiene, memory capture, skill improvement, harness adaptation, and markdown/prompt maintenance.
Use when adapting skills for AI Assistant Harness Adaptation, using an assistant harness action matrix, or making explicitly named target skills harness-agnostic.
Audit and improve AGENTS.md files in repositories. Use when user asks to check, audit, update, improve, or fix AGENTS.md files. Scans for all AGENTS.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "AGENTS.md maintenance" or "project memory optimization".
Use this skill when the user says "/ai-insights-hunter", "extract insights from conversation", "harvest this session", "what should we remember from this chat", "save insights from this conversation", or provides a path to an AI Assistant conversation log and wants to capture decisions, patterns, and preferences for future sessions. This skill reads a full conversation log (or finds it automatically), extracts valuable insights using parallel agents, interviews the user about what to keep, then stores the chosen insights in the right places to improve future AI Assistant interactions. Use PROACTIVELY when a long or complex session is wrapping up and the user wants to preserve learnings.
This skill should be used when the user asks to "audit my setup", "check my CLAUDE.md/AGENTS.md", "check my instruction files", "review my AI config", "clean up my instructions", "find conflicts in my setup", "optimize my agent setup", or mentions reviewing instruction files, skills folders, context files, or preferences for contradictions, redundancy, or dead weight.
Use when revising an existing skill from eval feedback, trigger misses, output regressions, bloat, overfitting, or repeated manual work across skill runs.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Simple, robust, and versatile marketplace for agent plugins, forged for the chaos of the AI world.
It collects practical tools for Codex and Claude Code across LLM observability, API exploration, development workflows, assistant operations, research notes, cloud storage, local automation, runtime app verification, and job-search workflows.
flowchart TB
subgraph RowOne[" "]
direction LR
Langfuse["`**langfuse**
Trace exploration, datasets,
evaluators, dashboards, and experiments`"]:::langfuse
OpenAPITools["`**openapi-tools**
List and inspect OpenAPI endpoints
on running services`"]:::openapi
LLMApplicationDev["`**llm-application-dev**
Agent pattern selection and
schema-guided reasoning`"]:::llm
PythonDevWorkflow["`**python-dev-workflow**
Pytest, Redis test patterns,
Celery, and unit-test review agents`"]:::python
DevWorkflow["`**dev-workflow**
Commits, PRs, tickets, releases,
and review-comment workflows`"]:::dev
end
subgraph RowTwo[" "]
direction LR
WorkSessionTools["`**work-session-tools**
Daily notes, task tracking,
interviews, and team planning`"]:::session
AIAssistantOps["`**ai-assistant-ops**
Assistant setup audits, skill improvement,
harness adaptation, and Markdown cleanup`"]:::ops
OSTools["`**os-tools**
Local macOS automation utilities
for assistant workflows`"]:::os
CloudStorageTools["`**cloud-storage-tools**
User-file storage workflows for
Dropbox, Drive, OneDrive, and MEGA`"]:::storage
JobHuntToolkit["`**job-hunt-toolkit**
Versioned job applications with
resume tailoring and PDF checks`"]:::job
end
subgraph RowThree[" "]
direction LR
RunAndVerifyApp["`**run-and-verify-app**
Launch apps, verify runtime behavior,
and record run recipes`"]:::runverify
MermaidDiagrams["`**mermaid-diagrams**
Mermaid generation,
syntax references, and linting`"]:::mermaid
end
Langfuse ~~~ OpenAPITools ~~~ LLMApplicationDev ~~~ PythonDevWorkflow ~~~ DevWorkflow
WorkSessionTools ~~~ AIAssistantOps ~~~ Research ~~~ OSTools ~~~ CloudStorageTools ~~~ JobHuntToolkit
RowOne ~~~ RowTwo
RowTwo ~~~ RowThree
RunAndVerifyApp ~~~ MermaidDiagrams
classDef langfuse fill:#dff7ff,stroke:#0284c7,stroke-width:2px,color:#0f172a;
classDef openapi fill:#dcfce7,stroke:#16a34a,stroke-width:2px,color:#052e16;
classDef llm fill:#fef3c7,stroke:#d97706,stroke-width:2px,color:#451a03;
classDef python fill:#ede9fe,stroke:#7c3aed,stroke-width:2px,color:#2e1065;
classDef dev fill:#fee2e2,stroke:#dc2626,stroke-width:2px,color:#450a0a;
classDef runverify fill:#e0f2fe,stroke:#0369a1,stroke-width:2px,color:#082f49;
classDef session fill:#ccfbf1,stroke:#0f766e,stroke-width:2px,color:#042f2e;
classDef ops fill:#fce7f3,stroke:#db2777,stroke-width:2px,color:#500724;
classDef research fill:#fef9c3,stroke:#ca8a04,stroke-width:2px,color:#422006;
classDef os fill:#e0e7ff,stroke:#4f46e5,stroke-width:2px,color:#1e1b4b;
classDef storage fill:#ecfccb,stroke:#65a30d,stroke-width:2px,color:#1a2e05;
classDef job fill:#ffedd5,stroke:#ea580c,stroke-width:2px,color:#431407;
classDef mermaid fill:#f0fdf4,stroke:#059669,stroke-width:2px,color:#052e16;
style RowOne fill:transparent,stroke:transparent,color:transparent;
style RowTwo fill:transparent,stroke:transparent,color:transparent;
style RowThree fill:transparent,stroke:transparent,color:transparent;
Use this README when you want to install the marketplace, install a plugin, or
choose what each plugin is for. Developer and maintenance notes live in
AGENTS.md.
Add the marketplace:
codex plugin marketplace add Alex-Kopylov/zweihander
Install a plugin:
codex plugin add langfuse@zweihander
List available plugins:
codex plugin list
Update the installed marketplace:
codex plugin marketplace upgrade zweihander
Add the marketplace from inside Claude Code:
/plugin marketplace add Alex-Kopylov/zweihander
Install a plugin:
/plugin install langfuse@zweihander
Update the installed marketplace:
/plugin marketplace update zweihander
For scripts or automation, use the non-interactive CLI:
claude plugin marketplace add Alex-Kopylov/zweihander
claude plugin install langfuse@zweihander
claude plugin marketplace update zweihander
plugin@zweihander, for example
langfuse@zweihander.langfuseUse when: you need to inspect Langfuse data, create or update evaluation assets, compare experiment runs, or manage dashboard widgets.
Skills
npx claudepluginhub alex-kopylov/zweihander --plugin ai-assistant-opsGenerate and validate Mermaid diagrams with synced syntax references.
Skills for listing and inspecting OpenAPI endpoints on running services.
Python-specific pytest, Redis test patterns, Celery, and unit-test review/execution agents.
LLM application design, agent pattern selection, and schema-guided reasoning patterns.
Research knowledge-base and Obsidian vault workflows for agent-maintained notes.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.