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.
curl -O https://raw.githubusercontent.com/JameZUK/Arkana/main/.claude/commands/review.mdgit clone --depth 1 https://github.com/JameZUK/ArkanaWrote 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.
[](https://agentmods.dev/commands/jamezuk/arkana/review)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- 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.
- The agent MUST run the verification checklist on each finding before reporting it. Findings that don't pass verification are dropped silently.
- The agent MUST check
git log -pfor the in-scope files before reporting "missing" code or "unguarded" patterns — many such findings are already-fixed bugs. - 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.
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.
- 9d ago First seen · 27 lines · 22 tokens per session scan A 26ce2ded2140
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.
Other commands, from other repositories
is-not-duplicated
please investigate the codebase based on your changes - do we have code duplication? After analysis, write updates to DUPLICATIONREPORT.md with the results. Keep in mind that other agents could keep their records, so you need to check the document first, decided to update or add new information.
check-network
Monitor active network connections and detect suspicious network activity.
scan-registry
Deep scan of Windows Registry for malware persistence and unauthorized modifications.
find-cves
Query the Android/AOSP kernel CVE database by CVE id, version, build date, or branch.
review
Comprehensive code review for blz changes.
implement
Multi-agent advisory squad workflow for implementing code changes: classify → score risk → select agents → planner → Gate 1 (plan approval) → advisory squad → Gate 2 (Blocker halt) → implementer → consolidator → verdict. Auto-detects depth (quick/normal/deep) from risk + file count; pass --quick or --deep to override.…