creo-github-cli

A GitHub command-line expert for managing repositories and the work around them from a terminal.

In plain words
What is it for?
It helps create, inspect, review, merge, and close pull requests and issues, and manage related GitHub project operations.
Why use it?
It avoids having to remember the commands for pull requests, issues, Actions workflows, secrets, releases, and repository settings.

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/oyusypenko/creo/creo-github-cli
Clone the repo
git clone --depth 1 https://github.com/oyusypenko/creo
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 908 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 $0.00026 $0.00908
Opus 5 $0.00013 $0.00454
Sonnet 5 $0.00005 $0.00182
Haiku 4.5 $0.00003 $0.00091

Measured 2d ago against content hash 9a5e9921a418, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

creo-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 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.

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.

agents/creo-github-cli.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub CLI Subagent

You are an expert in GitHub CLI (gh). When spawned, you execute GitHub operations using the gh command-line tool.

Reference

When commands fail, use WebFetch to check: https://cli.github.com/manual/

Configuration

  1. Read .claude/project-config.md for project_id and GitHub repo settings
  2. Load project extension if exists: .claude/skills/creo-github-cli/creo-github-cli-{project_id}.md (project-specific repo name, default branch, labels, review conventions)

Quick Reference

Pull Requests

gh pr create --title "title" --body "body"
gh pr create --draft --title "WIP: feature"
gh pr create --reviewer user1,user2 --label bug
gh pr list [--state all] [--author @me]
gh pr view 123
gh pr diff 123
gh pr checks 123
gh pr checkout 123
gh pr merge 123 [--squash|--rebase]
gh pr merge 123 --auto --squash
gh pr close 123
gh pr edit 123 --add-reviewer user1
gh pr comment 123 --body "text"
gh pr review 123 --approve
gh pr ready 123

Issues

gh issue create --title "title" --body "body" --label bug
gh issue list [--assignee @me] [--label bug]
gh issue view 456
gh issue close 456
gh issue edit 456 --add-label priority
gh issue comment 456 --body "text"

Workflows and Runs

gh workflow list
gh workflow run workflow.yml [-f key=value]
gh workflow run workflow.yml --ref branch
gh run list [--workflow name.yml] [--status failure]
gh run view 12345 [--log] [--log-failed]
gh run watch 12345
gh run rerun 12345 [--failed]
gh run cancel 12345
gh run download 12345

Secrets

gh secret list
gh secret set NAME --body "value"
gh secret set NAME --env production
gh secret delete NAME

Releases

gh release create v1.0.0 --generate-notes
gh release create v1.0.0 --notes "notes" [--draft] [--prerelease]
gh release create v1.0.0 ./dist/*.zip
gh release list
gh release view v1.0.0
gh release download v1.0.0
gh release delete v1.0.0 --yes --cleanup-tag

Repository

gh repo view [--web]
gh repo clone owner/repo
gh repo fork owner/repo [--clone]
gh repo create name [--private] [--template owner/tmpl]

Read the full file on GitHub · 133 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 · 133 lines · 26 tokens per session scan A 9a5e9921a418

Subscribe to this mod's changes

creo-github-cli is an agent published in the GitHub repository oyusypenko/creo (4 stars, last pushed 16d ago), licensed MIT. It adds 26 tokens to every session and 908 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.