start-issue

start-issue is a command for Claude Code from nimble-giant/ailloy. It costs 0 tokens per session (481 once invoked), scanned A, original, Apache-2.0.

A command that retrieves a GitHub issue and starts implementing its requirements. A GitHub issue is a tracked work request containing details and acceptance criteria.

In plain words
What is it for?
Use it with an issue number or URL to read the request, plan the tasks, implement the changes, and use the issue context for commits.
Why use it?
It turns the issue into a task list and keeps the work focused on that issue instead of unrelated requests.

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/nimble-giant/ailloy/start-issue
Clone the repo
git clone --depth 1 https://github.com/nimble-giant/ailloy

Made for: Claude Code.

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 start-issue

README.md
[![agentmods](https://agentmods.dev/badge/commands/nimble-giant/ailloy/start-issue.svg)](https://agentmods.dev/commands/nimble-giant/ailloy/start-issue)
Your own site
<a href="https://agentmods.dev/commands/nimble-giant/ailloy/start-issue"><img src="https://agentmods.dev/badge/commands/nimble-giant/ailloy/start-issue.svg" alt="Measured on agentmods" height="20"></a>
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 481 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 $0.00481
Opus 5 $0.00000 $0.00241
Sonnet 5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured 4d ago against content hash 19a6072acfec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start-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 4d 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/start-issue.md · 59 lines

What it actually says

Start Issue

Fetch a GitHub issue and begin implementation.

Usage

/start-issue <issue-number>
/start-issue <issue-url>

Examples

  • /start-issue 1234 - Start work on issue #1234
  • /start-issue https://github.com/your-org/your-repo/issues/1234 - Start work using full URL

Workflow

When this command is used, Claude will:

  1. Fetch the issue details using gh issue view <issue-number> --json title,body,author,state,labels,assignees,milestone,number,url,comments

  2. Create a todo list with tasks derived from the issue requirements

  3. Begin implementation following the issue requirements and acceptance criteria

  4. Use issue context to inform commit messages and implementation approach

Scope Boundaries

IMPORTANT: Stay focused on the specified issue ONLY.

  • Do NOT search for, fetch, or work on related issues, sub-issues, parent issues, or adjacent issues
  • Do NOT follow #XXXX references in the issue body to other issues
  • Do NOT use gh issue list or gh issue search to discover other issues
  • If the issue description mentions other issues for context, note them but do NOT expand scope to include their requirements
  • All work should be scoped strictly to what the specified issue describes

Manual GitHub Issue Commands

Fetching Issue Details

IMPORTANT: Always use --json to avoid GitHub Projects (classic) deprecation errors.

gh issue view <URL or issue-number> --json title,body,author,state,labels,assignees,milestone,number,url,comments

Examples:

  • gh issue view 1234 --json title,body,author,state,labels,assignees,milestone,number,url,comments
  • gh issue view https://github.com/your-org/your-repo/issues/1234 --json title,body,author,state,labels,assignees,milestone,number,url,comments

Notes

  • Authentication handled through user's GitHub CLI login
  • Use #<issue-number> format in commit messages
  • Focus on rapid implementation of the single issue
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. 4d ago First seen · 59 lines · 0 tokens per session scan A 19a6072acfec

Subscribe to this mod's changes

start-issue is a command published in the GitHub repository nimble-giant/ailloy (10 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 481 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.