claudeOps.elixpo: Command for Claude Code

.claude/commands/review.md

review is a command for Claude Code from elixpo/claudeOps.elixpo. It costs 0 tokens per session (546 once invoked), scanned A, original, MIT.

A code-review command for checking a change or pull request for real problems. It focuses on security, Cloudflare Edge runtime and D1 database correctness, error handling, and unrelated changes.

In plain words
What is it for?
Use it to review pull requests and code changes, especially projects using Cloudflare Workers, the Edge runtime, or D1, Cloudflare's SQL database.
Why use it?
It helps reviewers find bugs and security risks without spending time praising working code or suggesting cosmetic rewrites. It also gives the review a consistent format and clear merge decision.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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/review.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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/elixpo/claudeops.elixpo/review/github.svg)](https://agentmods.dev/commands/elixpo/claudeops.elixpo/review)
Your own site
<a href="https://agentmods.dev/commands/elixpo/claudeops.elixpo/review"><img src="https://agentmods.dev/badge/commands/elixpo/claudeops.elixpo/review/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 review

Your own site · 80×15
<a href="https://agentmods.dev/commands/elixpo/claudeops.elixpo/review"><img src="https://agentmods.dev/badge/commands/elixpo/claudeops.elixpo/review.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 546 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 $0.00546
Opus 5 $0.00000 $0.00273
Sonnet 5 $0.00000 $0.00109
Haiku 4.5 $0.00000 $0.00055

Measured 10d ago against content hash 5e3e748c0d5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review 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 10d 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/review.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a PR or code change.

Focus on what needs improving, not what's already fine.

What to look at

  • Security: auth/authz, input validation, SQL injection, XSS, CSRF, secret exposure, rate limiting on public endpoints.
  • Edge-runtime correctness: export const runtime = 'edge', no Node built-ins, no Buffer misuse, no top-level nodemailer.
  • D1 correctness: parameterized queries, no RETURNING * on multi-row, transaction boundaries, indexes on new WHERE/JOIN columns.
  • Error handling: do errors leak D1 internals to clients? Are failures logged with enough context to debug?
  • Scope drift: unrelated changes that should be in a separate PR.

Don't

  • Praise code that's fine.
  • Repeat what the PR description already says.
  • Hedge ("I think", "maybe", "might want to").
  • Suggest stylistic rewrites unless they catch a real bug.
  • Block on "consider adding a test" without saying what test.

Output format

Every review body MUST end with a merge-readiness verdict line. Use this structure:

## Issues
- [src/path/file.ts:42] <one-line problem + why it matters>
- [src/path/file.ts:88] <same pattern>

## Suggestions
- <one-line improvement, optional>
- <another>

## Security
- <only if there's something; omit section otherwise>

---
**Merge-readiness: READY** — <one line on why>

The last line is the verdict. Use one of:

  • **Merge-readiness: READY** — submit with gh pr review --approve
  • **Merge-readiness: NEEDS CHANGES** — submit with gh pr review --request-changes
  • **Merge-readiness: BLOCKED** — submit with gh pr review --request-changes and link the blocker

Bullets only. Link specific lines. Under 200 words unless the PR is genuinely large.

One-shot-per-invocation

Within this invocation, submit EXACTLY ONE gh pr review --approve|--request-changes|--comment --body "..." (or ONE gh pr comment), then END. The command returns empty/short stdout on success — that is success. Do NOT retry. Do NOT submit a second review "for completeness".

Read the full file on GitHub · 54 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. 10d ago First seen · 54 lines · 0 tokens per session scan A 5e3e748c0d5e

Subscribe to this mod's changes

review 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 546 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.