create-github-issue

A command that turns a request into a structured GitHub issue. It examines the codebase and existing issues when relevant, then chooses labels and creates the issue with the GitHub CLI.

In plain words
What is it for?
Creating bug, feature, enhancement, or documentation issues with titles, descriptions, context, reproduction steps, and suitable labels.
Why use it?
It removes the repetitive work of finding context, writing reproduction details, checking related issues, and selecting labels.

Command for Claude Code

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/abians/code-recall/create-github-issue
Clone the repo
git clone --depth 1 https://github.com/AbianS/code-recall

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 625 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 $0.00000 $0.00625
Opus 5 $0.00000 $0.00313
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00063

Measured yesterday against content hash 534d1c5cf6fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-github-issue 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.

.claude/commands/create-github-issue.md · 91 lines

What it actually says

Create a GitHub issue based on: $ARGUMENTS

Follow these steps:

  1. Parse the request

    • Analyze the provided description to determine issue type (bug, feature, enhancement, docs, etc.)
    • Extract key information: title, description, context, reproduction steps (if bug)
  2. Gather context

    • If the issue references specific code, search the codebase to understand the current implementation
    • Identify relevant files, functions, or components that should be mentioned
    • Check for related existing issues using gh issue list --search "<keywords>"
  3. Determine issue labels

    • Use gh label list to see available labels
    • Select appropriate labels based on issue type:
      • bug - Something isn't working correctly
      • enhancement - Improvement to existing functionality
      • feature - New functionality request
      • documentation - Documentation improvements
      • good first issue - Suitable for new contributors
      • help wanted - Extra attention needed
  4. Create the issue with proper formatting Use gh issue create with a well-structured body:

    For bugs:

    ## Description
    [Clear description of the bug]
    
    ## Steps to Reproduce
    1. [Step 1]
    2. [Step 2]
    3. [Step 3]
    
    ## Expected Behavior
    [What should happen]
    
    ## Actual Behavior
    [What actually happens]
    
    ## Environment
    - OS: [e.g., macOS, Linux]
    - Version: [relevant version info]
    
    ## Additional Context
    [Screenshots, logs, relevant code references]
    

    For features/enhancements:

    ## Summary
    [Brief description of the proposed change]
    
    ## Motivation
    [Why is this change needed? What problem does it solve?]
    
    ## Proposed Solution
    [How should this be implemented?]
    
    ## Alternatives Considered
    [Other approaches that were considered]
    
    ## Additional Context
    [Any other relevant information]
    
  5. Create the issue

    gh issue create \
      --title "<descriptive title>" \
      --body "<formatted body>" \
      --label "<appropriate labels>"
    
  6. Confirm creation

    • Display the created issue URL
    • Show issue number for reference

Example usage:

  • /create-github-issue Add dark mode support to the dashboard
  • /create-github-issue Bug: Events not being grouped correctly when fingerprint is null
  • /create-github-issue Improve error messages in the ingestion endpoint

Notes:

  • Keep titles concise but descriptive (under 72 characters)
  • Use imperative mood for feature titles ("Add...", "Fix...", "Update...")
  • Include code references using file:line format when relevant
  • Link to related issues or PRs if applicable
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 · 91 lines · 0 tokens per session scan A 534d1c5cf6fc

Subscribe to this mod's changes

create-github-issue is a command published in the GitHub repository AbianS/code-recall (4 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 625 tokens. 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.