[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-github-copilot-power-en":3,"seo:pack:github-copilot-power:en":94},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":93},"github-copilot-power","🐙","#24292E","new","New · this week","GitHub Copilot Beyond Autocomplete","You've used Copilot for ghost-text suggestions. Now plug in custom instructions, agent mode, GitHub MCP, and the official customization collection — the 2026 surface area most devs never touch.",[16,28,38,45,52,60,67,76,85],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},98,"1e571d3c-6269-4037-afde-db332bdab08a","github-copilot-official-customization-collection-1e571d3c","GitHub Copilot — Official Customization Collection","Official GitHub Copilot customization: agents, skills, instructions, plugins, hooks, and agentic workflows. Plus documentation.","GitHub",224,0,"en","skill","Skill",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":34,"view_count":35,"vote_count":24,"lang_type":25,"type":36,"type_label":37},3162,"cf2dfc89-8d63-4b7d-8810-9ae8189ce6b4","awesome-copilot-agents-instructions-prompts-mcps","Awesome Copilot Agents — Instructions, Prompts & MCPs","Awesome Copilot Agents is a curated list of Copilot instructions, prompts, skills, MCPs, and agent files to bootstrap stronger repo workflows.","Prompt Lab",58,"prompt","Prompt",{"id":39,"uuid":40,"slug":41,"title":42,"description":43,"author_name":44,"view_count":24,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3161,"1368ef7b-1ee3-42e8-86fb-c31edbb9d7b4","security-investigator-copilot-security-investigation-kit","Security Investigator — Copilot Security Investigation Kit","Security Investigator is an investigation system combining Copilot\u002FAgent Skills with security tooling to triage suspicious changes and threats faster.","Script Depot",{"id":46,"uuid":47,"slug":48,"title":49,"description":50,"author_name":34,"view_count":51,"vote_count":24,"lang_type":25,"type":36,"type_label":37},3639,"70286cc7-edee-5e85-a244-68e8508fa0a1","ai-prompts-prompt-rules-for-cursor-copilot-cline","ai-prompts — Prompt Rules for Cursor\u002FCopilot\u002FCline","ai-prompts is an open-source prompts\u002Frules repo for AI coding tools; verified 1,039★ and documents Cursor `.cursor\u002Frules\u002F` and Copilot instruction files.",89,{"id":53,"uuid":54,"slug":55,"title":56,"description":57,"author_name":58,"view_count":59,"vote_count":24,"lang_type":25,"type":26,"type_label":27},517,"c3338e8d-2ef8-4d72-8d2a-43e7518555fd","lnai-unified-ai-config-claude-cursor-copilot-more-c3338e8d","lnai — Unified AI Config for Claude, Cursor, Copilot & More","Define AI tool configs once in a .ai\u002F directory and auto-sync to Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, and Windsurf native formats.","AI Open Source",170,{"id":61,"uuid":62,"slug":63,"title":64,"description":65,"author_name":34,"view_count":66,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3158,"df9b812d-1db1-437b-a9ec-8aed4c8c12a9","ruleforge-generate-ai-assistant-rules-from-repo","RuleForge — Generate AI Assistant Rules from Repo","RuleForge is a CLI that scans a repo and generates rule files (CLAUDE.md, .cursorrules, Copilot instructions) so agents follow consistent boundaries.",12,{"id":68,"uuid":69,"slug":70,"title":71,"description":72,"author_name":44,"view_count":73,"vote_count":24,"lang_type":25,"type":74,"type_label":75},3071,"d2596447-aaf5-4338-98b0-6a1993c62980","caliber-auto-refresh-claude-md-and-rules","Caliber — Auto-Refresh CLAUDE.md and Rules","Caliber keeps CLAUDE.md, Cursor rules, AGENTS.md, and Copilot instructions accurate by regenerating them from your current repo state. Bootstrap via npx.",7,"script","Script",{"id":77,"uuid":78,"slug":79,"title":80,"description":81,"author_name":22,"view_count":82,"vote_count":24,"lang_type":25,"type":83,"type_label":84},393,"679a2650-b97b-4e8e-af6e-b51bafcbf610","github-mcp-server-official-github-ai-integration-679a2650","GitHub MCP Server — Official GitHub AI Integration","GitHub's official MCP server that lets AI assistants manage repos, issues, PRs, Actions, and code search through the Model Context Protocol.",182,"mcp","MCP",{"id":86,"uuid":87,"slug":88,"title":89,"description":90,"author_name":91,"view_count":92,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4400,"05ac37b6-aadf-476f-887f-66a21653f731","claude-code-agent-launchdarkly-flag-cleanup-05ac37b6","Claude Code Agent: Launchdarkly Flag Cleanup","A specialized GitHub Copilot agent that uses the LaunchDarkly MCP server to safely automate feature flag cleanup workflows. This agent determines removal readiness, identifies...","TokRepo精选",22,"tokrepo install pack\u002Fgithub-copilot-power",{"pageType":95,"pageKey":8,"locale":25,"title":96,"metaDescription":97,"h1":98,"tldr":99,"bodyMarkdown":100,"faq":101,"schema":117,"internalLinks":122,"citations":135,"wordCount":148,"generatedAt":149},"pack","GitHub Copilot Beyond Autocomplete — The 2026 Power-User Pack","You bought Copilot for ghost-text suggestions. The 2026 surface includes Chat, Edits, agent mode, custom instructions, GitHub MCP, and a curated extensions list. Nine assets that flip Copilot from a typing helper into a real coding partner.","GitHub Copilot Beyond Autocomplete — Custom Instructions, Agent Mode, MCP","Most teams pay for Copilot and use 10% of it. This pack covers the other 90%: the official customization collection, the awesome-copilot list, ai-prompts rule library, lnai unified config, RuleForge \u002F Caliber to keep rules fresh, the official GitHub MCP server, an agent-mode security investigator, and a Copilot-driven LaunchDarkly cleanup agent. Install in order; finish with a Copilot setup that pulls its weight in PRs, not just inside the editor.","## What's in this pack\n\nGitHub Copilot in 2026 is not the 2021 product. The ghost-text completion you signed up for is now one tab in a larger surface: **Copilot Chat** (ask questions about the file or repo), **Copilot Edits** (multi-file refactors with diff preview), **Copilot agent mode** (lets Copilot plan, run shell commands, iterate on failing tests until they pass), **Copilot Extensions** (third-party skills you can `@invoke`), **MCP servers** (tool access via Model Context Protocol), and **custom instructions** (a project-scoped file Copilot reads every turn — same idea as `CLAUDE.md` or `.cursor\u002Frules`).\n\nMost devs paying $10–39\u002Fmonth touch the first two and stop there. This pack is for the developer who's ready to drop the autocomplete-only mental model: nine assets that turn Copilot into a real coding partner, with the same rigor you'd give Claude Code or Cursor.\n\nWho this is for: a working developer with a Copilot Pro \u002F Business \u002F Enterprise seat, on VS Code or a JetBrains IDE, who has never opened `.github\u002Fcopilot-instructions.md` and isn't sure what agent mode actually does.\n\n## Install in this order\n\n1. **GitHub Copilot — Official Customization Collection** — Start at the source. The official `github\u002Fawesome-copilot` collection ships instructions, prompt files, skills, agentic workflows, and the customization patterns that GitHub itself maintains. Read the README, skim the categories. This is your reference index for everything else in the pack.\n2. **Awesome Copilot Agents — Instructions, Prompts & MCPs** — The community-curated companion list. Where the official collection is conservative, this one is comprehensive: third-party agents, niche instructions, MCP server pairings, and patterns the docs don't cover yet. Bookmark; visit monthly.\n3. **ai-prompts — Prompt Rules for Cursor\u002FCopilot\u002FCline** — A multi-tool rules library. Even if you live in Copilot, ai-prompts has high-quality `copilot-instructions.md` templates organized by stack (Next.js, Python, Rust, Go). Copy the one that matches your repo, edit to taste, commit it to `.github\u002F`.\n4. **lnai — Unified AI Config for Claude, Cursor, Copilot & More** — If you use more than one AI coding tool (or your team does), stop maintaining four config files. lnai lets you define instructions once in a `.ai\u002F` directory and auto-syncs to `.github\u002Fcopilot-instructions.md`, `.cursor\u002Frules\u002F`, `CLAUDE.md`, `AGENTS.md`, Gemini CLI, Codex. One source of truth.\n5. **RuleForge — Generate AI Assistant Rules from Repo** — Don't write instructions from a blank page. RuleForge scans your repo (stack, conventions, file layout) and generates a starter `copilot-instructions.md` plus Cursor \u002F Claude variants. Treat its output as draft v0; edit it; commit.\n6. **Caliber — Auto-Refresh CLAUDE.md and Rules** — Instructions go stale the moment your tech stack drifts. Caliber regenerates Copilot instructions, CLAUDE.md, Cursor rules, and AGENTS.md from your current code on a schedule (or pre-commit hook). Set it up once; never have a Copilot session run against a 6-month-old config again.\n7. **GitHub MCP Server — Official GitHub AI Integration** — The official `github\u002Fgithub-mcp-server` lets any MCP-aware client — including Copilot in agent mode — read PRs, file issues, comment on diffs, trigger Actions, and search code. This is the single highest-leverage MCP you can install. Copilot's agent mode lights up dramatically with it.\n8. **Security Investigator — Copilot Security Investigation Kit** — A real agent-mode workload. Plug this skill in and Copilot can triage suspicious dependencies, review a CVE's blast radius across your repo, and produce a structured incident note — agent mode running for minutes, not seconds, calling tools, iterating. The kind of task that justifies the seat price.\n9. **Claude Code Agent: LaunchDarkly Flag Cleanup** — Despite the \"Claude Code\" name, this is explicitly written as a GitHub Copilot agent that drives the LaunchDarkly MCP server to clean up stale feature flags safely. A worked example of the agent + MCP combo on a real production chore most teams do badly.\n\n## How they fit together\n\nThink of Copilot 2026 as four layers, and this pack populates each one:\n\n```\nCopilot Chat \u002F Edits  ← what you already use (autocomplete + Q&A)\n        │\nCustom instructions   ← #3 ai-prompts, #5 RuleForge (seed), #6 Caliber (keep fresh)\n        │\nUnified config        ← #4 lnai (one source of truth across tools)\n        │\nMCP servers           ← #7 GitHub MCP (the foundation)\n        │\nAgent mode workloads  ← #8 Security Investigator, #9 LaunchDarkly cleanup\n        │\nReference \u002F discovery ← #1 official collection, #2 awesome-copilot\n```\n\n**Chat \u002F Edits \u002F Custom instructions \u002F Agent mode \u002F MCP** are the five named surfaces. Items #1 and #2 teach you the surface area; #3–#6 own the *custom instructions* layer; #7 plugs MCP in; #8 and #9 are real agent-mode workloads you can copy.\n\nThe load-bearing wall is **custom instructions + GitHub MCP**. Install #3 (or #5, generated), wire up #7, and your next agent-mode session is already 10× better grounded than baseline. Everything else is upgrades.\n\n## Tradeoffs you'll hit\n\n- **Copilot vs Claude Code \u002F Cursor** — Copilot wins on three things: deepest GitHub.com \u002F PR \u002F Actions integration (no other tool sees your PR threads natively), seat licensing your security team already approved, and stable VS Code \u002F JetBrains support without third-party installs. Claude Code wins on raw capability and terminal-native workflow. Cursor wins on UX polish and `.cursor\u002Frules` ergonomics. **Use Copilot when**: PR review, GitHub-native workflows, regulated enterprises where Anthropic\u002FCursor aren't approved, JetBrains shops. **Reach for Claude Code or Cursor when**: long autonomous coding sessions, terminal-heavy work, prototyping outside a GitHub repo.\n- **Custom instructions vs prompt files** — Copilot supports both `.github\u002Fcopilot-instructions.md` (read every turn, project-wide) and discrete `.github\u002Fprompts\u002F*.prompt.md` files (invoked explicitly). Default to instructions for *standing context* (stack, conventions, hard NOs) and prompt files for *named workflows* (\"write a migration,\" \"file a bug report\"). Don't pile everything into instructions — token budget matters.\n- **Official collection (#1) vs awesome-copilot (#2)** — Overlap is real. Official is conservative and curated by GitHub; awesome-copilot is comprehensive and community-driven. Treat #1 as docs, #2 as discovery. Skim #1 once end-to-end; revisit #2 monthly.\n- **lnai (#4) vs maintaining four config files** — Skip lnai if you only use Copilot. Adopt it the moment you also use Claude Code or Cursor — config drift between tools is a real source of \"why did this work yesterday?\"\n- **Agent mode vs Chat for the same task** — Chat is conversational, fast, single-turn. Agent mode plans, runs commands, iterates on failures, can take minutes. Use Chat for \"explain this function\"; reach for agent mode when the task requires running tests, calling MCP tools, or chaining steps.\n\n## Common pitfalls\n\n- **Copilot instructions too long** — Same trap as CLAUDE.md. 30–100 lines is the sweet spot. Copilot reads instructions every turn; bloated files burn context budget and slow latency.\n- **Forgetting `.github\u002Fcopilot-instructions.md` exists** — The file lives under `.github\u002F`, not the repo root. It's invisible in many file trees and easy to miss. Check `git ls-files .github\u002F` after install.\n- **Mixing prompt files into instructions** — Putting a long \"write a migration\" prompt inside instructions means it runs *every turn*, even when you're just asking what a function does. Move named workflows to `.github\u002Fprompts\u002F`.\n- **Skipping the org admin step for MCP** — On Copilot Enterprise \u002F Business, MCP servers may need org-level approval before agent mode can call them. If GitHub MCP \"doesn't work,\" check org policy before debugging the server.\n- **Treating agent mode as autocomplete with extra steps** — Agent mode is for tasks with a clear success criterion the agent can verify (tests passing, lint clean, flag deleted). Give it open-ended \"refactor this nicely\" tasks and you'll watch it spin. Pair every agent run with a concrete check.\n- **Never refreshing instructions** — Caliber (#6) exists because nobody updates `copilot-instructions.md` manually after the first week. Schedule it. Or hook it to your dependency-update PRs.",[102,105,108,111,114],{"q":103,"a":104},"I just use Copilot for autocomplete. Do I really need nine more things?","No — autocomplete-only is a legitimate use of Copilot. This pack is for the moment after that, when you've noticed Copilot suggesting things that violate your team's conventions on every other line, or you've heard about agent mode but never tried it. If you're happy with ghost text, keep going. If you're frustrated that Copilot writes generic React when your team has strict patterns, install #3 or #5 today — custom instructions alone fix most of those complaints.",{"q":106,"a":107},"Which three would you install if I only have 20 minutes?","ai-prompts (#3) for a templated `copilot-instructions.md` you can commit immediately, GitHub MCP (#7) so agent mode actually talks to your repo, and the official customization collection (#1) as your reference index. With those three, your Copilot setup outperforms 80% of teams; the rest of the pack is depth.",{"q":109,"a":110},"Why install RuleForge AND Caliber? Don't they overlap?","Different jobs at different times. RuleForge (#5) is a one-shot generator — point it at a fresh repo, get a starter `copilot-instructions.md`. Caliber (#6) is a long-running refresher — keeps that file accurate as your stack drifts (new deps, new conventions, deleted services). Use RuleForge to bootstrap; use Caliber to maintain. Skip RuleForge if you'd rather hand-write the first version.",{"q":112,"a":113},"Is Copilot agent mode actually competitive with Claude Code or Cursor's agent?","Honest answer: capability gap exists today but is narrowing fast. Claude Code and Cursor still win on long-horizon autonomous work and raw model headroom. Copilot agent mode wins on integration: it lives where your PRs live, your security team already approved the seat, and JetBrains support is first-class. For a developer already on Copilot, the right move in 2026 is to make agent mode work well rather than chase a second tool — until you hit a workflow Copilot genuinely can't do.",{"q":115,"a":116},"Does any of this work on Copilot Individual, or do I need Business \u002F Enterprise?","Most of it works on Copilot Pro \u002F Individual: custom instructions, prompt files, Chat, Edits, agent mode, MCP servers in VS Code. The Enterprise-only pieces are knowledge bases tied to your GitHub org, certain policy controls, and organization-managed MCP approvals. If you're a solo dev or small team on Pro, this entire pack runs. The org-policy footnote in pitfalls only applies if your admin has locked things down.",{"@context":118,"@type":119,"name":13,"description":120,"numberOfItems":121,"inLanguage":25},"https:\u002F\u002Fschema.org","ItemList","Nine assets that move a GitHub Copilot user from autocomplete-only into custom instructions, agent mode, MCP, and the full 2026 surface area.",9,[123,127,131],{"url":124,"anchor":125,"reason":126},"\u002Fen\u002Ffeatured","Featured assets on TokRepo","After the Copilot pack, browse the broader curated catalog",{"url":128,"anchor":129,"reason":130},"\u002Fen\u002Ftopics","Browse other topic packs","Adjacent packs include Claude Code Onboarding, AI Code Editor Showdown, MCP Server Stack",{"url":132,"anchor":133,"reason":134},"\u002Fen\u002Fai-tools-for\u002Fcoding","AI tools for coding","See how GitHub Copilot compares to Claude Code, Cursor, Codex CLI, and Cline",[136,140,144],{"claim":137,"source_name":138,"source_url":139},"GitHub Copilot in 2026 includes Chat, Edits, agent mode, custom instructions, prompt files, MCP servers, and extensions","GitHub Copilot documentation","https:\u002F\u002Fdocs.github.com\u002Fen\u002Fcopilot",{"claim":141,"source_name":142,"source_url":143},"Copilot reads `.github\u002Fcopilot-instructions.md` as project-scoped custom instructions","GitHub Docs — About custom instructions for GitHub Copilot","https:\u002F\u002Fdocs.github.com\u002Fen\u002Fcopilot\u002Fcustomizing-copilot\u002Fabout-customizing-github-copilot-chat-responses",{"claim":145,"source_name":146,"source_url":147},"The official GitHub MCP server is maintained at github\u002Fgithub-mcp-server","github\u002Fgithub-mcp-server","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgithub-mcp-server",1340,"2026-05-22T00:00:00Z"]