github-cli

A rule for using GitHub CLI, the terminal program for working with GitHub, when old or invalid token variables may interfere with its saved login.

In plain words
What is it for?
Use it before commands such as creating pull requests, managing issues, or checking workflow runs; it explains how to remove conflicting token variables and verify the login.
Why use it?
It prevents avoidable authentication errors caused by GH_TOKEN or GITHUB_TOKEN values in the shell overriding a valid keyring login.

Cursor rule for Cursor

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 rules/metagit-ai/metagit-cli/github-cli
Clone the repo
git clone --depth 1 https://github.com/metagit-ai/metagit-cli

Made for: Cursor.

Per session 240 This file is loaded in full into every session.
When invoked 240 The same file — it is already loaded in full.
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 $0.00240 $0.00240
Opus 5 $0.00120 $0.00120
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured yesterday against content hash d249be7094e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-cli 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.

.cursor/rules/github-cli.mdc · 25 lines

What it actually says

GitHub CLI authentication

Before any gh command (gh pr create, gh issue, gh run, etc.), unset stale token environment variables that override the keyring login:

env -u GH_TOKEN -u GITHUB_TOKEN gh <subcommand> ...

Why

An invalid or expired GH_TOKEN / GITHUB_TOKEN in the shell environment causes HTTP 401: Bad credentials even when gh auth status shows a valid keyring account (with "Active account: false" on the keyring entry).

Checklist for PRs

  1. Push branch: git push -u origin HEAD (SSH/git creds are separate from gh).
  2. Create PR: env -u GH_TOKEN -u GITHUB_TOKEN gh pr create ...
  3. If auth still fails: gh auth status then gh auth login if needed.

Do not export GH_TOKEN for local gh unless intentionally using that token for the session.

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 · 25 lines · 240 tokens per session scan A d249be7094e7

Subscribe to this mod's changes

github-cli is a cursor rule published in the GitHub repository metagit-ai/metagit-cli (2 stars, last pushed 3d ago), licensed MIT. It adds 240 tokens to every session, about $0.0012 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.