100 production-grade multi-agent harnesses for GitHub Copilot CLI
This repository also configures its own agents. See what harness-100-copilot tells them →
Skill Claude CodeCodex
Use when you need to generate a complete test suite for a project — dispatches test-strategist, unit-test-writer, integration-test-writer, e2e-test-writer, and test-reviewer in sequence to produce strategy, implementation, and review artifacts. Covers test pyramid design, unit/integration/E2E implementation, coverage…
Skill Claude CodeCodex
Use when you need to define or improve test coverage metrics, set mutation testing targets, or analyze coverage reports — provides coverage threshold recommendations, mutation testing setup, and gap analysis patterns. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when you need reference patterns for structuring tests — provides Given/When/Then, test doubles taxonomy, test data builders, and common testing idioms for unit, integration, and E2E contexts. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when facilitating or reviewing an incident postmortem to ensure blameless culture principles are followed — detects blame language, applies psychological safety guidelines, and provides rewrite suggestions for action items and findings. Covers blameless language review, psychological safety coaching, Just Culture…
Skill Claude CodeCodex
Use when conducting a structured incident postmortem after a production outage, degradation, or SEV1–SEV4 event. Dispatches incident-analyst, root-cause-investigator, impact-assessor, and action-planner in sequence to reconstruct the timeline, identify root causes, quantify SLO/customer impact, and produce a…
Skill Claude CodeCodex
Use when designing and implementing cloud infrastructure as code — dispatches infra-architect, terraform-specialist, k8s-specialist, security-hardener, and infra-reviewer in sequence to produce a complete, hardened IaC stack. Covers multi-cloud architecture design through Terraform modules, Kubernetes manifests…
Skill Claude CodeCodex
Use when securing Kubernetes workloads and clusters — provides CIS Kubernetes Benchmark controls, Pod Security Standards configuration, NetworkPolicy templates, and RBAC hardening patterns. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when working with Terraform infrastructure code — provides module structure patterns, remote state configuration, workspace-per-environment guidance, and security scanning templates for checkov/tfsec. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when designing or building a data pipeline — dispatches pipeline-architect, ingestion-specialist, transformation-engineer, quality-monitor, and pipeline-reviewer in sequence to deliver a complete, production-ready data pipeline design. Covers batch and streaming architectures, ETL/ELT transformation with dbt and…
Skill Claude CodeCodex
Use when configuring data quality monitoring — provides quality dimension definitions, Great Expectations patterns, data contract templates, and dbt test configurations for comprehensive data validation. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when implementing data transformation pipelines — provides ELT vs ETL decision framework, dbt project structure best practices, Spark optimization patterns, and incremental processing strategies. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when you need OWASP Top 10 2021 reference data — provides detailed descriptions, code examples, and mitigations for all 10 categories (A01–A10). Supporting skill for the security-audit harness. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when performing a comprehensive security audit of a codebase, application, or system — dispatches threat-modeler, code-security-analyst, dependency-auditor, and config-reviewer in a pipeline, then synthesizes findings into a prioritized security report with CVSS scoring and remediation roadmap. Covers threat…
Skill Claude CodeCodex
Use when scoring, classifying, or prioritizing security vulnerabilities — provides CVSS v3 scoring guide, severity classification criteria, patch SLA framework, and exploitability assessment methodology. Supporting skill for the security-audit harness. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when measuring or optimizing Core Web Vitals — provides LCP/INP/CLS targets, measurement tool configurations, and optimization techniques for each vital metric. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when optimizing database query performance -- provides EXPLAIN plan interpretation patterns, index tuning strategies, N+1 query detection and fixes, and query rewrite patterns for PostgreSQL, MySQL, and common ORMs. Also triggers on: re-run, update, revise, supplement.
Skill Claude CodeCodex
Use when optimizing application or system performance — dispatches profiling-analyst, frontend-optimizer, backend-optimizer, infra-tuner, and performance-reviewer to identify bottlenecks, implement optimizations, and validate improvements with ROI estimation. Covers full-stack performance from Core Web Vitals through…
Skill Claude CodeCodex
Use when launching a new open source project or formalizing an existing private repo as OSS — dispatches oss-strategist, readme-writer, ci-setup-specialist, and community-planner in sequence to produce a complete OSS launch kit. Covers license selection, governance, all community health files, GitHub Actions CI/CD…
Skill Claude CodeCodex
Use when validating an open source project launch readiness or verifying license compatibility — provides a comprehensive OSS launch checklist, license compatibility matrix, and community health file inventory. Extends the open-source-launcher harness and can be used standalone. Also triggers on: re-run, update…
Skill Claude CodeCodex
Use when you need to create a new multi-agent harness for a domain not yet covered in this repository, or when asked to 'build a harness', 'design an agent team', or 'create agents for [domain]'. Analyzes the domain, selects one of 6 architectural patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: