A command that sends the current code changes to a reviewer agent for inspection.

Use it to review the current Git working-tree changes and report whether they are acceptable or need fixes.

It helps find correctness, design, security, performance, and maintainability problems before the changes are accepted. It does not change files itself.

review — Command for Claude Code and OpenCode by Surjal/dev-agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/Surjal/dev-agent

Made for: Claude Code, OpenCode.

Or install dev-agent, the plugin that ships this one along with the rest of its 4 commands, 16 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/surjal/dev-agent/review/github.svg)](https://agentmods.dev/commands/surjal/dev-agent/review)

Your own site

<a href="https://agentmods.dev/commands/surjal/dev-agent/review"><img src="https://agentmods.dev/badge/commands/surjal/dev-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/surjal/dev-agent/review"><img src="https://agentmods.dev/badge/commands/surjal/dev-agent/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 120 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.

Model	Per session	Once invoked
Fable 5.1	$0.00009	$0.00120
Opus 5.5	$0.00004	$0.00048
Sonnet 5.5	$0.00002	$0.00024
Haiku 4.5	$0.00001	$0.00012

Measured 2mo ago against content hash dd524942bbde, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.opencode/commands/review.md · 11 lines

What it actually says

Use the task tool with agent dev-agent-reviewer to review the current diff (git diff, plus any staged/committed changes relevant to the task below) for correctness, architecture, security, performance, and maintainability.

$ARGUMENTS

Report the reviewer's verdict verbatim to the user. Do not modify any files based on the result -- if it's CHANGES REQUIRED, report the issues and ask whether to send them to the dev-agent-developer agent to fix.

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.

2mo ago First seen · 11 lines · 9 tokens per session scan A dd524942bbde

Subscribe to this mod's changes

review is a command published in the GitHub repository Surjal/dev-agent (2 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 120 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-31.

Claude Code Code review ai-agent automation claude-code-plugin developer-tools opencode

review next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reviewSurjal/dev-agent	Command	2	2mo ago	MIT	A	9	Claude Code, OpenCode
initazrtydxb/procoder	Command	211	11d ago	Apache-2.0	A	16	Claude Code
gitazrtydxb/procoder	Command	211	11d ago	Apache-2.0	A	20	Claude Code
fec-smellbovinphang/frontend-craft	Command	22	yesterday	MIT	A	21	Claude Code
extendlugassawan/swe-workbench	Command	3	3d ago	MIT	A	35	Claude Code
security-reviewlugassawan/swe-workbench	Command	3	3d ago	MIT	A	43	Claude Code
esp-hardenmathisk2095/jko-claude-plugins	Command	3	24d ago	MIT	A	17	Claude Code