Arkana: Command for Claude Code

.claude/commands/review.md

review is a command for Claude Code from JameZUK/Arkana. It costs 22 tokens per session (405 once invoked), scanned A, original, MIT.

A command that reviews code changes that have not yet been committed. It uses a dedicated code-review agent to check the affected files and report verified problems.

In plain words
What is it for?
Use it for staged or unstaged changes, or provide a specific file or commit range to review. It produces a short report grouped by severity, including no findings when the code is clean.
Why use it?
It helps catch bugs or risky patterns before changes are committed or merged. Requiring quoted code, checks, and review of file history helps avoid reports based on guesses or already-fixed issues.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is JameZUK/Arkana's own configuration. It tells Claude Code how to work on Arkana 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 Arkana configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JameZUK/Arkana. 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/JameZUK/Arkana/main/.claude/commands/review.md
Clone the repo
git clone --depth 1 https://github.com/JameZUK/Arkana

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/jamezuk/arkana/review/github.svg)](https://agentmods.dev/commands/jamezuk/arkana/review)
Your own site
<a href="https://agentmods.dev/commands/jamezuk/arkana/review"><img src="https://agentmods.dev/badge/commands/jamezuk/arkana/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/jamezuk/arkana/review"><img src="https://agentmods.dev/badge/commands/jamezuk/arkana/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 405 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 $0.00022 $0.00405
Opus 5 $0.00011 $0.00202
Sonnet 5 $0.00004 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured 9d ago against content hash 26ce2ded2140, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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 · 27 lines

What it actually says

Use the arkana-code-reviewer agent (defined in .claude/agents/arkana-code-reviewer.md) to review code changes.

Default scope: unstaged + staged changes from git diff HEAD. Run that first to discover the in-scope files. If the user specified a scope in the slash command arguments — e.g. /review arkana/mcp/tools_pe.py or /review last 3 commits — use that instead.

Hard requirements for the review:

  1. The agent MUST follow the quote-before-claim discipline in its system prompt — every finding must include verbatim quoted code from a file the agent actually read in this session.
  2. The agent MUST run the verification checklist on each finding before reporting it. Findings that don't pass verification are dropped silently.
  3. The agent MUST check git log -p for the in-scope files before reporting "missing" code or "unguarded" patterns — many such findings are already-fixed bugs.
  4. A short verified report is the gold standard. Do NOT pad with speculation. If the code is clean, the report says "Reviewed N files. No findings."

After the agent returns, present the findings to the user grouped by severity (CRITICAL → HIGH → MEDIUM → LOW → DOCSTRING). For each finding, show:

  • File:line reference
  • Quoted code (from the agent's report — do NOT re-fetch and risk drift)
  • One-paragraph problem statement
  • Concrete fix suggestion

If the user wants you to apply the fixes, ask which findings to address (default: all CRITICAL + HIGH). Make the edits, run pytest tests/ and ruff check, then commit with a descriptive message.

Do not commit without explicit approval — review findings often require human judgment about whether they're worth fixing.

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. 9d ago First seen · 27 lines · 22 tokens per session scan A 26ce2ded2140

Subscribe to this mod's changes

review is a command published in the GitHub repository JameZUK/Arkana (218 stars, last pushed 16d ago), licensed MIT. It adds 22 tokens to every session and 405 once invoked, about $0.0001 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.