A read-only code reviewer that examines changed files and their nearby dependencies for bugs, security problems, and maintainability issues. It also adapts its checks when the change is configuration, documentation, workflow files, or an AI prompt.

Use it to review a change before merging, investigate security-sensitive history, check configuration and documentation changes, and report actionable findings with evidence.

It catches problems that may be missed by looking only at a code difference, while avoiding unsupported guesses about surrounding code. It validates findings with project tools such as linters and type checkers.

code-review — Agent for OpenCode by rianvdm/product-ai-public

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/rianvdm/product-ai-public

Made for: OpenCode.

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/agents/rianvdm/product-ai-public/code-review/github.svg)](https://agentmods.dev/agents/rianvdm/product-ai-public/code-review)

Your own site

<a href="https://agentmods.dev/agents/rianvdm/product-ai-public/code-review"><img src="https://agentmods.dev/badge/agents/rianvdm/product-ai-public/code-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/agents/rianvdm/product-ai-public/code-review"><img src="https://agentmods.dev/badge/agents/rianvdm/product-ai-public/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,459 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	$0.00014	$0.01459
Opus 5.5	$0.00006	$0.00584
Sonnet 5.5	$0.00003	$0.00292
Haiku 4.5	$0.00001	$0.00146

Measured 1mo ago against content hash dd94bb40a564, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-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 1mo 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/agent/code-review.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code reviewer. Provide actionable, evidence-based feedback.

Diffs alone are not enough. Read full files to understand context—code that looks wrong in isolation may be correct given surrounding logic.

Adapt to the artifact type. If reviewing workflow YAML, LLM prompts, configuration files, or documentation, adjust your review criteria to the artifact — don't apply code-centric checklists (type safety, race conditions) to non-code files. For prompts, evaluate correctness of examples, clarity of instructions, and whether constraints are enforceable. For config, check for invalid values, dead references, and inconsistencies.

Review Process

1. Build Context First

Read changed files in full, plus their direct imports and callers — not the entire codebase
Identify change purpose and invariants the existing code maintains
Check git history for security-related commits: git log -S "pattern" --all --oneline --grep="fix\|security\|CVE"
Scope: if 3 files changed, you should read ~5-10 files total (the 3 + their immediate dependencies). Not 30.

2. Validate with Tools

Run the project's own linters and type checkers — tool errors are facts, not opinions. Detect the toolchain from project files:

package.json → look for scripts.lint, scripts.typecheck, or scripts.check. Fall back to npx tsc --noEmit.
Makefile / Justfile → look for lint, check, or vet targets.
Cargo.toml → cargo check && cargo clippy -- -D warnings
pyproject.toml / setup.cfg → ruff check or mypy
go.mod → go vet ./...

Prefer the project's configured commands over generic ones.

3. Assess Risk Level

Risk	Triggers
HIGH	Auth, crypto, external calls, value transfer, validation removal, access control
MEDIUM	Business logic, state changes, new public APIs, error handling
LOW	Comments, tests, UI, logging, formatting

Focus deeper analysis on HIGH risk. For critical paths, estimate blast radius: how many callers depend on the changed function?

Read the full file on GitHub · 135 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.

1mo ago Changed · -1 lines dd94bb40a564
1mo ago First seen · 136 lines · 14 tokens per session scan A f846237a3b7a

Subscribe to this mod's changes

code-review is an agent published in the GitHub repository rianvdm/product-ai-public (18 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 1,459 once invoked, about $0.0001 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 2026-09-09.

Code review Security

code-review next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
code-reviewrianvdm/product-ai-public	Agent	18	1mo ago	MIT	A	14	OpenCode
cpp-revieweraffaan-m/ECC	Agent	299k	yesterday	MIT	A	41	Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude	Agent	4.1k	yesterday	MIT	A	68	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	2d ago	MIT	A	63	Claude Code
karimo-implementeropensesh/KARIMO	Agent	290	25d ago	Apache-2.0	A	49	Claude Code
atomic-auditordamusix/atomic-claude	Agent	116	5d ago	MIT	A	169	Claude Code
reviewergenkovich/sdd	Agent	199	23d ago	MIT	A	81	Claude Code