issue

A command for taking a GitHub issue, which is a tracked bug, request, or task, from analysis through implementation and pull request. It follows GitHub Flow, a branch-and-review process for collaborative development.

In plain words
What is it for?
Use it with an issue number to research related work, choose a suitable development approach, create a branch, implement and test the fix, commit changes, and open a pull request.
Why use it?
It organizes the investigation, planning, coding, testing, and review steps so an issue does not remain an unfinished discussion.

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/awattar/claude-code-best-practices/issue
Clone the repo
git clone --depth 1 https://github.com/awattar/claude-code-best-practices

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,424 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 $0.00012 $0.01424
Opus 5 $0.00006 $0.00712
Sonnet 5 $0.00002 $0.00285
Haiku 4.5 $0.00001 $0.00142

Measured 2d ago against content hash 3856f910172b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.claude/commands/issue.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code User Command: Issue

This command helps you analyze and fix GitHub issues specified in $ARGUMENTS following GitHub flow best practices.

Usage

To analyze and fix the GitHub issue, just type:

/issue <issue-number>

What This Command Does

  1. Analyzes the GitHub issue specified in $ARGUMENTS using GitHub CLI (gh).
  2. Researches prior work and creates a development plan in a scratchpad.
  3. Selects appropriate workflow based on issue type (standard, exploration, test-first, or rapid prototyping).
  4. Creates a feature branch and implements the solution with incremental commits.
  5. Tests the changes and opens a PR for review.

Agents Used

This command leverages specialized agents based on issue type and complexity:

  • general-fullstack-developer - For end-to-end feature implementation spanning multiple layers
  • general-backend-developer - For API-focused issues and backend development
  • general-frontend-developer - For UI/UX issues and frontend implementation
  • general-qa - For comprehensive testing strategies and validation
  • general-purpose - For complex issue analysis and multi-step research

The appropriate agent is selected based on the issue requirements and project architecture. Each agent contributes specialized expertise to ensure thorough project analysis and high-quality documentation generation.

Follow these steps:

General

Follow these best practices and tools throughout the process:

  • Follow GitHub flow in the process whenever possible - https://docs.github.com/en/get-started/using-github/github-flow
  • Use the /commit command consistently throughout development to maintain high-quality commit messages and conventional commit standards
  • Consider using context7 (https://github.com/upstash/context7) via MCP to pull up-to-date, version-specific documentation for any libraries or frameworks involved in the issue. This keeps generated code aligned with current APIs instead of relying on stale training data.
  • Capture important context, decisions, and progress in the scratchpad/plan file for the issue (see the Plan section below) to maintain task continuity across sessions.
  • Identify the project's browser automation tool for UI testing. Ask if you're unsure whether to use puppeteer, playwright, selenium, or another tool.
  • Remember to use the GitHub CLI (gh) for all GitHub-related tasks.

Read the full file on GitHub · 140 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 · 140 lines · 12 tokens per session scan A 3856f910172b

Subscribe to this mod's changes

issue is a command published in the GitHub repository awattar/claude-code-best-practices (250 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 1,424 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 2026-08-30.