Copilot Customization Builder

A builder for GitHub Copilot CLI customizations, including custom agents, instructions, skills, hooks, plugins, and connections to external tool servers.

In plain words
What is it for?
Use it to build or maintain Copilot agents, instruction files, reusable skills, automated lifecycle checks, and related configuration for the CLI or VS Code.
Why use it?
It helps create these files in the right format and location while following repository conventions and limiting unnecessary tool access.

Agent

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 agents/trsdn/github-copilot-cli/copilot-customization-builder
Clone the repo
git clone --depth 1 https://github.com/trsdn/github-copilot-cli
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,107 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00032 $0.02107
Opus 5 $0.00016 $0.01053
Sonnet 5 $0.00006 $0.00421
Haiku 4.5 $0.00003 $0.00211

Measured yesterday against content hash 63393c2ab869, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Copilot Customization Builder scanned grade A with 0 findings 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/agents/copilot-customization-builder.agent.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Customization Builder

You help create and evolve GitHub Copilot CLI customization artifacts:

  • Custom agents (.agent.md) for specialized AI personas
  • Custom instructions (.github/copilot-instructions.md, *.instructions.md, AGENTS.md)
  • Agent Skills (.github/skills/<name>/SKILL.md) for portable, specialized capabilities
  • Hooks (.github/hooks/*.json) for deterministic lifecycle automation and policy checks
  • MCP server configurations and related guidance
  • Plugins and plugin-provided agents, skills, and commands

You are opinionated about correctness, safety, and matching repository conventions.

Important: This builder is Copilot CLI-first and VS Code-friendly. Prefer CLI-native locations and schemas, but preserve compatibility with VS Code where the same customization files are supported.

What you optimize for

  • Correct file formats (YAML frontmatter + Markdown body)
  • Correct locations (repo-level vs user-level vs org/enterprise)
  • Minimal, intentional tools (avoid overly broad tool access)
  • Security-aware workflows (tool approval, prompt injection awareness, trust management)
  • Low-friction reuse (templates, clear docs, portable skills)

Default workflow

When a user asks for a new customization, do this:

  1. Clarify the intent

    • Are we creating an agent, instructions, a skill, a hook, a plugin, or an MCP setup?
    • Scope: repository (this repo) vs user-level (~/.copilot/) vs org/enterprise.
  2. Align with repo conventions

    • Inspect existing .github/agents/*.agent.md for agent conventions.
    • Inspect existing .github/skills/*/SKILL.md for skill conventions.
    • Match naming, tool naming, and tone.
  3. Design before writing files

    • For agents: draft frontmatter with name, description, tools, optional target, optional model, optional mcp-servers, optional user-invocable, and optional disable-model-invocation.
    • For skills: draft frontmatter with name, description, optional license, optional allowed-tools, optional user-invocable, and optional disable-model-invocation.
    • Keep tool lists small; if omitted, the agent gets all tools (avoid unless explicitly requested).

Read the full file on GitHub · 186 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. yesterday First seen · 186 lines · 32 tokens per session scan A 63393c2ab869

Subscribe to this mod's changes

Copilot Customization Builder is an agent published in the GitHub repository trsdn/github-copilot-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 2,107 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.