setup

A command that checks whether GitHub Copilot CLI is installed, signed in, and ready to use. GitHub Copilot CLI is a terminal-based coding assistant.

In plain words
What is it for?
Run it to check the installed version, test authentication, and receive next steps when Copilot CLI is missing or not ready.
Why use it?
It finds installation, version, or authentication problems before delegation is attempted.

Command

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 commands/santiquiroz/copilot-plugin-cc/setup
Clone the repo
git clone --depth 1 https://github.com/santiquiroz/copilot-plugin-cc
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 463 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 $0.00016 $0.00463
Opus 5 $0.00008 $0.00231
Sonnet 5 $0.00003 $0.00093
Haiku 4.5 $0.00002 $0.00046

Measured yesterday against content hash 7bd7e74bfc12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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.

commands/setup.md · 39 lines

What it actually says

Run these checks in order and report a single consolidated status at the end.

Step 1 — Installed?

Run:

copilot --version
  • If the command is not found and npm is available: use AskUserQuestion exactly once with two options — Install GitHub Copilot CLI (Recommended) and Skip for now. If the user chooses install, run npm install -g @github/copilot, then rerun copilot --version.
  • If the command is not found and npm is unavailable: report the official install docs (https://docs.github.com/en/copilot/how-tos/set-up/install-copilot-cli) and stop.

Step 2 — Version gate

  • If the reported version is lower than 1.0.67: warn that multi-model selection (--model) is unsupported on this version and recommend npm update -g @github/copilot. Continue with the remaining checks.

Step 3 — Authentication probe

Run:

copilot -p "Reply with exactly one word: ready" -s --deny-tool=shell --deny-tool=write
  • Output contains ready → authenticated and working.
  • Output shows an authentication error → instruct the user to either run copilot interactively and use /login, or set the COPILOT_GITHUB_TOKEN environment variable with a token that has Copilot access. NEVER print or echo the token value.
  • Output contains "rate limit" (case-insensitive) → report that the Copilot quota is currently exhausted; delegation is unavailable until it resets.

Step 4 — Consolidated report

Summarize in one short block: install state, version (and whether it meets the 1.0.67 floor), auth state, and model options — pin with --model <name> or the COPILOT_MODEL environment variable for deterministic behavior; omit (or use --model auto) to allow Auto-selection, which carries a billing discount on routine mechanical work.

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 · 39 lines · 16 tokens per session scan A 7bd7e74bfc12

Subscribe to this mod's changes

setup is a command published in the GitHub repository santiquiroz/copilot-plugin-cc (1 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 463 once invoked, about $0.0001 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.