submit-claude-code-github-issue

A guided command for filing an issue in the public GitHub repository for Claude Code. A GitHub issue is a report or request tracked by a project team.

In plain words
What is it for?
Use it to describe a bug or feature request, review closely related issues, and prepare a submission with meaningful context and issue names.
Why use it?
It searches open and closed issues first, reducing duplicate reports and helping clarify whether a similar issue already exists.

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/design-and-deliver/claude-code-autoconfig/submit-claude-code-github-issue
Clone the repo
git clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfig

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 852 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 $0.00852
Opus 5 $0.00000 $0.00426
Sonnet 5 $0.00000 $0.00170
Haiku 4.5 $0.00000 $0.00085

Measured 2d ago against content hash 36603d639f40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

submit-claude-code-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 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/submit-claude-code-github-issue.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

File a GitHub issue on the anthropics/claude-code repository, with due diligence.

Usage:

  • /submit-claude-code-github-issue - Start the workflow
  • /submit-claude-code-github-issue plan names should be meaningful - Start with context from arguments

Arguments: $ARGUMENTS

Workflow:

Phase 1: Understand the Issue

  1. Ask the user what the issue is about, OR use any context/description provided in the arguments
  2. Summarize the core request in 1-2 sentences to confirm understanding

Phase 2: Due Diligence — Search Existing Issues

  1. Search for similar/duplicate issues using multiple keyword variations:

    • gh search issues --repo anthropics/claude-code "<keywords>" --limit 15
    • Also search closed issues: gh search issues --repo anthropics/claude-code "<keywords>" --state closed --limit 10
  2. Categorize each result by match strength:

    • Exact — Same issue, same ask. Filing would be a duplicate.
    • Strong — Very similar issue, minor differences in scope or framing.
    • High — Related topic, but meaningfully different request or context.
    • Discard anything below High — don't show medium/low matches.
  3. Present findings in a markdown table:

    # Match Status Title URL
    1234 Exact Open Plan filenames should be descriptive https://...
    987 Strong Closed Allow custom names for plan files https://...
  4. Based on findings, offer options via AskUserQuestion:

    • If Exact match (open): Recommend upvote + optional comment. Options: "Upvote + Comment", "File new anyway", "Cancel"
    • If Exact match (closed): Note it was closed, recommend filing new if still relevant or commenting to reopen. Options: "File new", "Comment on closed issue", "Cancel"
    • If Strong/High matches only: Show table, note the differences, let user decide. Options: "File new", "Comment on existing", "Cancel"
    • If No matches: Proceed directly to Phase 3

Read the full file on GitHub · 63 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 · 63 lines · 0 tokens per session scan A 36603d639f40

Subscribe to this mod's changes

submit-claude-code-github-issue is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 852 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.