create-issue

A guide for creating structured GitHub issues with the GitHub CLI. An issue is a GitHub record used to describe a bug, request, investigation, or other project work.

In plain words
What is it for?
Use it to create a new issue from supplied text or from relevant points in a conversation, including technical investigations and proposed refactoring.
Why use it?
It helps turn a rough request or technical discussion into a clear record with background, requirements, risks, and possible approaches. This gives future contributors enough context to act on it.

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/liam-hq/liam/create-issue
Clone the repo
git clone --depth 1 https://github.com/liam-hq/liam

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 404 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 $0.00007 $0.00404
Opus 5 $0.00003 $0.00202
Sonnet 5 $0.00001 $0.00081
Haiku 4.5 $0.00001 $0.00040

Measured 2d ago against content hash ad832ecc6b11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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/create-issue.md · 40 lines

What it actually says

Task

Create a new issue in a GitHub repository using the GitHub CLI.

Process

  1. Analyze the request: First, understand the context and technical implications
  2. Gather information: If the issue involves technical implementation, think through:
    • Current state vs desired state
    • Technical requirements and dependencies
    • Potential implementation approaches
    • Impact and risks
  3. Structure the issue: Create a well-structured issue with:
    • Clear title
    • Detailed body with background, requirements, and technical considerations
    • Use proper markdown formatting

Arguments

$ARGUMENTS

Argument Handling:

  • When arguments are provided: Create an issue based on the given content
  • When arguments are empty: Detect technical discussions from recent conversation and suggest creating an issue based on that context
  • When instructed to "create from conversation": Analyze conversation history to generate an issue

Best Practices

  • Argument validation: When arguments are empty, first analyze available conversation context
  • Conversation history utilization: Auto-detect technical investigations, bug discoveries, refactoring proposals
  • Research integration: Use code investigation and search results as evidence for the issue
  • Structured issues: Include the following sections:
    • Overview (problem summary)
    • Current state (technical current situation)
    • Investigation results (detailed research findings)
    • Action items (specific work to be done)
    • Impact analysis (risks and benefits)
    • Technical considerations (implementation notes)
  • Evidence documentation: Include specific file paths, line numbers, and search results
  • Cross-repository references: When referencing PRs or issues from repositories other than the target repository, use the full format repository#number (e.g., liam-hq/liam#2991) instead of just #number to ensure proper GitHub linking
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 · 40 lines · 7 tokens per session scan A ad832ecc6b11

Subscribe to this mod's changes

create-issue is a command published in the GitHub repository liam-hq/liam (5,100 stars, last pushed 4d ago), licensed Apache-2.0. It adds 7 tokens to every session and 404 once invoked, about $0.0000 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.