copilot-customization-selector

A guide for choosing among GitHub Copilot customization types, including instruction files, prompt files, agents, skills, hooks, MCP servers, and plugins.

In plain words
What is it for?
Use it to decide whether a need belongs in an instructions file, reusable prompt, custom agent, portable skill, lifecycle hook, MCP configuration, or packaged plugin.
Why use it?
It explains the differences between these options so a recurring rule, task, specialist assistant, automation, or external connection gets the right format.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/trsdn/github-copilot-agent/copilot-customization-selector
Any agent
npx skills add trsdn/github-copilot-agent --skill copilot-customization-selector
Clone the repo
git clone --depth 1 https://github.com/trsdn/github-copilot-agent

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00067 $0.04091
Opus 5 $0.00034 $0.02046
Sonnet 5 $0.00013 $0.00818
Haiku 4.5 $0.00007 $0.00409

Measured 2d ago against content hash e99272a38569, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

copilot-customization-selector scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Block `rm -rf` and `DROP TABLE` commands
.github/skills/copilot-customization-selector/SKILL.md · 417 lines

How it starts

The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Customization Selector

This skill helps you decide which GitHub Copilot customization option to use for your specific needs.

When to use this skill

  • User asks "what type of customization should I create?"
  • User wants to understand differences between instructions, prompts, agents, and skills
  • User needs to choose the right approach for a new customization
  • User asks "should I use a prompt or an instruction file?"

Quick Decision Flowchart

What do you want to achieve?
│
├─► Define coding standards/rules that apply automatically?
│   └─► Use CUSTOM INSTRUCTIONS (.instructions.md)
│
├─► Create a reusable task template (e.g., "generate tests")?
│   └─► Use PROMPT FILES (.prompt.md)
│
├─► Create a specialized AI persona with specific tools?
│   └─► Use CUSTOM AGENTS (.agent.md)
│
├─► Build portable capabilities with scripts/resources?
│   └─► Use AGENT SKILLS (SKILL.md)
│
├─► Automate actions at agent lifecycle points?
│   └─► Use HOOKS (.github/hooks/*.json)
│
├─► Connect external services or APIs?
│   └─► Use MCP SERVERS (mcp.json)
│
└─► Install pre-packaged customizations?
    └─► Use AGENT PLUGINS (preview)

Decision Matrix

Feature Instructions Prompt Files Custom Agents Agent Skills Hooks MCP Plugins Tool Sets
File Extension .instructions.md .prompt.md .agent.md SKILL.md .json .json / YAML frontmatter plugin.json .jsonc
Location .github/instructions/ .github/prompts/ .github/agents/ .github/skills/<name>/ .github/hooks/ .vscode/mcp.json, agent mcp-servers, plugin .mcp.json plugin root tool-set file via VS Code
Triggers Auto (always or via glob) Manual (/name) Manual (switch agent) Auto (when relevant) Lifecycle events Tool/resource/prompt invocation Install/enable plugin Tool selection or #toolset
Can include scripts? No No No Yes Yes Server-dependent Yes No
Can specify tools? No Yes Yes No N/A Provides tools Bundles tools via agents/MCP Groups tools
Can specify model? No Yes Yes No N/A No Via bundled prompts/agents No
Portable across tools? VS Code/GitHub VS Code Partial Open standard Partial MCP standard Cross-tool (preview) VS Code
Status Stable Stable Stable (1.106+) Stable Preview Stable/Preview features Preview Stable/Preview

Read the full file on GitHub · 417 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 417 lines · 67 tokens per session scan C e99272a38569

Subscribe to this mod's changes

copilot-customization-selector is a skill published in the GitHub repository trsdn/github-copilot-agent (3 stars, last pushed 8d ago), licensed MIT. It adds 67 tokens to every session and 4,091 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

apm-issue-autopilot

Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…

microsoft/apm · 238 tokens

apm-review-panel

Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in…

microsoft/apm · 178 tokens

apm-triage-panel

Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.

microsoft/apm · 59 tokens

apm-spec-guardian

Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/.schema.json), or the conformance fixture seed…

microsoft/apm · 215 tokens

cli-logging-ux

Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (richsuccess, richwarning, richerror, richinfo, richecho), DiagnosticCollector, STATUSSYMBOLS, CommandLogger, or any…

microsoft/apm · 94 tokens

pr-description-skill

Use this skill to write the PR description (PR body) for any pull request opened against microsoft/apm. Produces one self-sufficient GitHub-Flavored Markdown artifact: TL;DR, Problem (WHY), Approach (WHAT), Implementation (HOW), 1-3 validated mermaid diagrams, explicit trade-offs, validation evidence, and a…

microsoft/apm · 131 tokens