claudeOps.elixpo: Command for Claude Code

.claude/commands/respond-to-issue.md

respond-to-issue is a command for Claude Code from elixpo/claudeOps.elixpo. It costs 0 tokens per session (949 once invoked), scanned A, original, MIT.

A command for handling GitHub issues that mention a specific account or carry the ELIXPO label. It loads the project context, classifies the issue, and follows the project’s rules for answering, implementing changes, or asking for clarification.

In plain words
What is it for?
Use it to respond to matching GitHub issues, decide whether an issue needs discussion or implementation, and follow the project’s prescribed context and review workflow.
Why use it?
It provides a defined issue-response procedure, including when to answer with one comment and when to create a code change. This helps prevent repeated commands or unnecessary repository work.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

This is elixpo/claudeOps.elixpo's own configuration. It tells Claude Code how to work on claudeOps.elixpo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claudeOps.elixpo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to elixpo/claudeOps.elixpo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/elixpo/claudeOps.elixpo/main/.claude/commands/respond-to-issue.md
Clone the repo
git clone --depth 1 https://github.com/elixpo/claudeOps.elixpo

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 respond-to-issue

README.md
[![agentmods](https://agentmods.dev/badge/commands/elixpo/claudeops.elixpo/respond-to-issue/github.svg)](https://agentmods.dev/commands/elixpo/claudeops.elixpo/respond-to-issue)
Your own site
<a href="https://agentmods.dev/commands/elixpo/claudeops.elixpo/respond-to-issue"><img src="https://agentmods.dev/badge/commands/elixpo/claudeops.elixpo/respond-to-issue/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for respond-to-issue

Your own site · 80×15
<a href="https://agentmods.dev/commands/elixpo/claudeops.elixpo/respond-to-issue"><img src="https://agentmods.dev/badge/commands/elixpo/claudeops.elixpo/respond-to-issue.svg" alt="Reviewed on agentmods" width="80" 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 949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00949
Opus 5 $0.00000 $0.00475
Sonnet 5 $0.00000 $0.00190
Haiku 4.5 $0.00000 $0.00095

Measured 12d ago against content hash 0720b5b69fb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

respond-to-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 12d 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/respond-to-issue.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Respond to an issue triggered by @elixpoo mention or the ELIXPO label.

Step 1 — Load context

  • Read .elixpo-context/context.md ONCE. Don't ls/find/tree to rediscover what's there.
  • gh issue view <n> --comments ONCE. Don't repeat with different --json flags.
  • Do NOT re-read README.md or CLAUDE.md unless the context snippet is truncated.

Step 2 — Classify the request

Look at what the user actually asked. Pick ONE:

  • QUESTION / DISCUSSION / LGTM — user wants an answer, not a code change. → Go to Step 3 (answer path).
  • IMPLEMENTATION — user asked for a fix, feature, refactor, or any code change. → Go to Step 4 (implement path).
  • UNCLEAR — the ask is too vague to act on (missing scope, conflicting requirements). → Go to Step 5 (clarify path).

Step 3 — Answer path

Post ONE comment on the issue. That's it. No branch, no PR.

gh issue comment <n> --body "<your answer>"

Within this invocation, stop after one successful comment. The command returns empty/short stdout on success — that IS success. Do NOT retry, do NOT post a second comment "to add more", do NOT follow up with another gh call. If the user wants more, they'll ping @elixpoo again — each new trigger is a fresh invocation.

Answer rules:

  • Bullets over paragraphs. <150 words.
  • Link specific files/lines (src/lib/jwt.ts:42) instead of describing.
  • No "I think" / "maybe". Either it's true or it's not.
  • If the question has a definitive answer in AGENTS.md or the code, quote/link it.

Step 4 — Implement path

Before touching code, check for an existing linked PR:

gh pr list --search "linked:issue-<n>" --state open --json number,headRefName,title

4a. Open PR exists

Someone (possibly you, earlier) already has a PR open for this issue.

  • git fetch origin && git checkout <headRefName> && git pull
  • Make changes on that branch.
  • Follow .claude/commands/commit-push-pr.md Step 2 (commit + push). Do NOT open a new PR.
  • Comment on the issue: pushed more changes to #<pr-n>.

Read the full file on GitHub · 87 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. 12d ago First seen · 87 lines · 0 tokens per session scan A 0720b5b69fb5

Subscribe to this mod's changes

respond-to-issue is a command published in the GitHub repository elixpo/claudeOps.elixpo (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 949 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.