gh-workflow

gh-workflow is a skill for Claude Code from nasrulhazim/claude. It costs 248 tokens per session (14,970 once invoked), scanned A, original, MIT.

A set of workflows for GitHub, a service for hosting code and coordinating software work, using GitHub's command-line tool. It covers issues, pull requests, automated jobs, releases, projects, labels, secrets, and direct API requests.

In plain words
What is it for?
Use it to create and manage issues and pull requests, run or debug Actions, manage repositories, releases, labels, secrets, and project boards, and generate repository reports.
Why use it?
It keeps common repository and project-management tasks in one repeatable workflow instead of requiring separate manual steps in GitHub's website. It also helps inspect and troubleshoot GitHub Actions, which are automated jobs run by a repository.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the claude-toolkit plugin — 36 skills, 12 commands, 20 agents shipped together

Good fit Use it to create and manage issues and pull requests, run or debug Actions, manage repositories, releases, labels, secrets, and project boards, and generate repository reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nasrulhazim/claude/gh-workflow
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.

Any agent
npx skills add nasrulhazim/claude --skill gh-workflow
Clone the repo
git clone --depth 1 https://github.com/nasrulhazim/claude

Made for: Claude Code.

Or install claude-toolkit, the plugin that ships this one along with the rest of its 36 skills, 12 commands, 20 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gh-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/nasrulhazim/claude/gh-workflow/github.svg)](https://agentmods.dev/skills/nasrulhazim/claude/gh-workflow)
Your own site
<a href="https://agentmods.dev/skills/nasrulhazim/claude/gh-workflow"><img src="https://agentmods.dev/badge/skills/nasrulhazim/claude/gh-workflow/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gh-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/nasrulhazim/claude/gh-workflow"><img src="https://agentmods.dev/badge/skills/nasrulhazim/claude/gh-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 248 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 14,970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 780
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 783
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 784
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 789
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 5.1 $0.00248 $0.14970
Opus 5 $0.00124 $0.07485
Sonnet 5 $0.00050 $0.02994
Haiku 4.5 $0.00025 $0.01497

Measured 9d ago against content hash 43b549eccdc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gh-workflow 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 9d 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.

skills/gh-workflow/SKILL.md · 1,817 lines

How it starts

The opening of the file, as written. The whole thing — 1,817 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub CLI Workflow

Automate GitHub operations — from issue tracking to release management — using the gh CLI. Assumes gh auth login has been completed.

Command Reference

Command Description
/gh issue Create, list, search, triage, and close issues
/gh pr Create PRs, request reviews, check status, merge
/gh actions List, trigger, watch, and debug workflow runs
/gh repo Create, clone, fork repos; manage settings and visibility
/gh release Create releases with assets, manage downloads
/gh labels Scaffold and sync label sets across repositories
/gh secrets Manage repository and environment secrets and variables
/gh project Create and manage GitHub Projects — boards, custom fields, views, multi-repo tracking
/gh report Generate repository and project reports in HTML, JSON, or Markdown format
/gh api Raw GitHub API calls for advanced operations

1. /gh issue — Issue Management

Create, list, search, and triage GitHub issues.

Create an Issue

gh issue create \
  --title "Bug: login fails with SSO" \
  --body "$(cat <<'EOF'
## Description
Login fails when using SSO provider.

## Steps to Reproduce
1. Click "Login with SSO"
2. Complete SSO flow
3. Redirected back with 500 error

## Expected Behaviour
User should be logged in and redirected to dashboard.

## Environment
- Laravel 12.x
- PHP 8.4
- Production
EOF
)" \
  --label "bug,priority:high" \
  --assignee "@me"

List and Filter Issues

# List open issues assigned to me
gh issue list --assignee "@me" --state open

# Search issues with filters
gh issue list --label "bug" --state open --limit 50

# Search across repos with query
gh search issues "login SSO" --repo owner/repo --state open

# JSON output for scripting
gh issue list --json number,title,labels,assignees --jq '.[] | "\(.number) \(.title)"'

Triage Workflow

# Add labels to an issue
gh issue edit 123 --add-label "priority:high,bug"

# Assign an issue
gh issue edit 123 --add-assignee "username"

# Add to a milestone
gh issue edit 123 --milestone "v2.0"

# Add a comment
gh issue comment 123 --body "Investigating — likely related to #120"

# Close with reason
gh issue close 123 --reason "completed" --comment "Fixed in #125"

Read the full file on GitHub · 1,817 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 1,817 lines · 248 tokens per session scan A 43b549eccdc5

Subscribe to this mod's changes

gh-workflow is a skill published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 6d ago), licensed MIT. It adds 248 tokens to every session and 14,970 once invoked, 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 2026-08-30.