microsoft

1,423 mods in 44 plugins, 141 repositories, 1268k stars between them.

microsoft/mcp-dotnet-samples

Instructions file CodexOpenCode ✓ vendor

Instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.

196 7d ago A 2,417 tokens original MIT

awesome-copilot

602

microsoft/mcp-dotnet-samples

MCP server Claude CodeCodexCursor +2 ✓ vendor

MCP server "awesome-copilot" as configured in microsoft/mcp-dotnet-samples. Runs in Docker (ghcr.io/microsoft/mcp-dotnet-samples/awesome-copilot:1.0.2026082702).

196 7d ago A tokens not measured original MIT

v8-jsi AGENTS.md

603

microsoft/v8-jsi

Instructions file CodexOpenCode ✓ vendor

AGENTS.md instructions for microsoft/v8-jsi, covering v8-jsi — project guide, environment, build, testing and source layout.

189 9d ago A 2,767 tokens

v8-jsi CLAUDE.md

604

microsoft/v8-jsi

Instructions file ✓ vendor

Claude Code instructions for microsoft/v8-jsi, a project described as: React Native V8 JSI adapter.

189 9d ago A 5 tokens

review

606

microsoft/Agents-for-net

Agent ✓ vendor

Local reviewer-vs-challenger loop that reproduces the GitHub Copilot PR review dynamic before you open the PR. Invokes reviewer-github (a different model) to emulate GitHub's findings, then disputes or resolves each one, giving a per-finding verdict — Fix / Push back / Needs judgment. Read-only.

177 5d ago A 69 tokens original MIT

reviewer-github

607

microsoft/Agents-for-net

Agent ✓ vendor

Emulates GitHub Copilot code review locally. Runs on a different model from the challenger to reproduce the genuine divergence you get from GitHub's own reviewer. Loads the SAME instruction files GitHub reads and produces PR-style findings. Read-only. Invoked by the review agent.

177 5d ago A 63 tokens original MIT

microsoft/Agents-for-net

Instructions file GitHub Copilot ✓ vendor

Instructions for microsoft/Agents-for-net, covering copilot instructions for agents-for-net, project overview, build and test, build entire solution and build via top-level project (includes all libraries).

177 5d ago A 2,253 tokens original MIT

microsoft/Agents-for-net

Instructions file ✓ vendor

Instructions for microsoft/Agents-for-net: See .github/copilot-instructions.md for build commands, architecture, conventions, and coding guidelines for this repository.

177 5d ago A 39 tokens original MIT

microsoft/msagljs

Instructions file GitHub Copilot ✓ vendor

Instructions for microsoft/msagljs, covering copilot instructions for msagl-js, project overview, build, test, and lint, architecture and core data model (@msagl/core).

175 14d ago A 924 tokens original MIT

msagljs

617

microsoft/msagljs

Skill Claude CodeCodex ✓ vendor

Use MSAGL-JS (Microsoft Automatic Graph Layout) to lay out and visualize networks in JavaScript or TypeScript. Use for graph and network layout, DOT/JSON/JGF parsing, live embedded SVG or WebGL graphs, Sugiyama/MDS/IPSepCola layouts, edge routing, and exporting SVG, PDF, PNG, EPS, or PostScript figures for LaTeX and…

175 14d ago A 87 tokens original MIT

microsoft/AutoSaddler

Instructions file GitHub Copilot ✓ vendor

Instructions for microsoft/AutoSaddler, covering github copilot instructions (repo-wide), environment & command execution (important), examples, dependency management and documentation & consistency (important).

165 +15 9d ago A 764 tokens original MIT

capability-patch

619

microsoft/AutoSaddler

Skill Claude CodeCodex ✓ vendor

Selected during the capability phase — adds new tools, exposes new parameters, fixes tool implementations, or removes infrastructure limitations to expand what the agent can do.

165 +15 9d ago A 34 tokens original MIT

diagnose

620

microsoft/AutoSaddler

Skill Claude CodeCodex ✓ vendor

Use to systematically diagnose why scenarios fail — identifies root causes by analyzing agent traces, codebase, and behavioral patterns.

165 +15 9d ago A 25 tokens original MIT

history-analysis

621

microsoft/AutoSaddler

Skill Claude CodeCodex ✓ vendor

Use to systematically analyze the full evolution history without output truncation — produces a structured summary of what matters for the current iteration.

165 +15 9d ago A 27 tokens original MIT

patch-verification

622

microsoft/AutoSaddler

Skill Claude CodeCodex ✓ vendor

Use after applying any patch to thoroughly verify the agent codebase has no bugs — checks syntax, imports, runtime behavior, docstrings, templates, hooks, and logical correctness.

165 +15 9d ago A 38 tokens original MIT

steering-patch

623

microsoft/AutoSaddler

Skill Claude CodeCodex ✓ vendor

Selected during the steering phase — refines agent behavior by modifying prompts, tool descriptions, or hook reminders without changing executable code.

165 +15 9d ago A 29 tokens original MIT

causal-diagnosis

624

microsoft/AutoSaddler

Skill Claude CodeCodex ✓ vendor

Use before proposing a mutation to diagnose measured failures from evaluator outcomes, traces, history, and the controlling candidate surfaces.

165 +15 9d ago A 29 tokens original MIT

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: