Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add promptadvisers/claudex/plugin install claudexWrote 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/promptadvisers/claudex/review)<a href="https://agentmods.dev/commands/promptadvisers/claudex/review"><img src="https://agentmods.dev/badge/commands/promptadvisers/claudex/review.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00288 |
| Opus 5 | $0.00012 | $0.00144 |
| Sonnet 5 | $0.00005 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/claudex:review
You are running claudex review mode. The Stop hook will fire when you end your turn and run a Codex adversarial review against the current diff. Findings + proposed fixes get written to reviews/.
Procedure
- Run start-loop.sh in review mode:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/start-loop.sh" review
-
The script sets up state. Read the printed instructions.
-
End your turn immediately. Do NOT write any code or analysis in this turn. The Stop hook fires and runs the Codex review automatically.
v1 limitations
- Single-shot. The review runs once. There is no auto-iteration in v1.
- Read-only. Codex produces findings + proposed-fix patches. Claudex does NOT auto-apply them. Apply manually after the review.
v2 will add auto-apply with branch isolation. See docs/V2_DESIGN.md.
Important
- Concurrent loops are refused. If a
/claudex:planloop is active, finish it before starting a review. - To abort:
/claudex:cancel - To force-clean stale state:
/claudex:rollback
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.
- 7d ago First seen · 34 lines · 24 tokens per session scan A b46fe93f8871
review is a command published in the GitHub repository promptadvisers/claudex (119 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 288 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.