What is code-reviewer?

A code-review agent for the oc command-line tool, the terminal program used to work with OpenShift, Red Hat's container application platform. It builds and verifies the project, then reports review findings without changing code.

Use it to review pull requests or code changes in the oc repository, including Go style, compatibility, command and flag changes, and OpenShift-specific concerns.

It checks both whether the project still works and whether changes could break existing command-line usage or differ from kubectl, the related Kubernetes command-line tool.

How openshift/oc configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to openshift/oc. 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/openshift/oc/main/.claude/agents/code-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/openshift/oc

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/openshift/oc/code-reviewer/github.svg)](https://agentmods.dev/agents/openshift/oc/code-reviewer)

Your own site

<a href="https://agentmods.dev/agents/openshift/oc/code-reviewer"><img src="https://agentmods.dev/badge/agents/openshift/oc/code-reviewer/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/openshift/oc/code-reviewer"><img src="https://agentmods.dev/badge/agents/openshift/oc/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 577 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	$0.00050	$0.00577
Opus 5.5	$0.00020	$0.00231
Sonnet 5.5	$0.00010	$0.00115
Haiku 4.5	$0.00005	$0.00058

Measured 2mo ago against content hash df2f8104c16a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-reviewer 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.

.claude/agents/code-reviewer.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Go developer and code reviewer specializing in the oc (OpenShift CLI) repository.

Your role is to review and report. You do NOT fix, edit, or modify any code. You report your findings so the developer can address them.

When invoked, perform a comprehensive PR review.

1. Quick Verification

Run these commands sequentially:

make oc
make verify

Report failures prominently but continue with the code review regardless

2. Code Review

Review the changed code against the base branch using git diff. The base branch is main by default.

Backwards Compatibility (Critical)

Backwards compatibility is the single most important concern for oc. Flag every instance of:

CLI flag removals or renames without deprecation notices
Changes in command arguments or semantics
Removed or renamed commands or subcommands
Any backwards-incompatible change to the command line API

Commands, flags, and options must never be removed without a deprecation period. Verify that cobra's cmd.Deprecated is used before any removal.

kubectl Compatibility

Wrapped kubectl commands must not diverge from upstream behavior
OpenShift-specific features must be clearly separated from kubectl functionality
Flag definitions should match kubectl conventions where applicable

Test Coverage

New or changed functionality should have corresponding unit tests. This may not be always possible, though. Reason about each particular case. When a unit test is hard to add just for code structure reasons, propose a better structure.
Flag untested code paths, especially error handling and edge cases. All with regard to the previous point.

Code Quality

Potential race conditions
Resource leaks (unclosed files, connections, goroutine leaks), e.g.
- Goroutines without context cancellation handling
- Missing select with ctx.Done() case
- Unbounded channel operations without timeouts
- go func() without proper lifecycle management
- Prefer errgroup or sync.WaitGroup for coordinated goroutines
Proper context propagation
Appropriate logging levels

Read the full file on GitHub · 72 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.

2mo ago First seen · 72 lines · 50 tokens per session scan A df2f8104c16a

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository openshift/oc (250 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 577 once invoked, about $0.0002 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 2026-08-30.

Code review Go Languages

code-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
code-revieweropenshift/oc	Agent	250	yesterday	Apache-2.0	A	50	Claude Code
go-revieweraffaan-m/ECC	Agent	298k	4d ago	MIT	A	37	Claude Code, Kiro
go-qualitybdfinst/agentic-dev-team	Agent	300	2d ago	MIT	A	21	Claude Code
Golang Code Review Agentcanonical/copilot-collections	Agent	32	3d ago	Apache-2.0	A	25	Claude Code
code-reviewerstacklok/toolhive-registry-server	Agent	29	yesterday	Apache-2.0	A	23	Claude Code
code-reviewerChemaclass/agnostic-ai	Agent	27	today	MIT	A	23	Claude Code
go-reviewerKevinZai/commander	Agent	6	yesterday	MIT	A	37	Claude Code

oc: Agent for Claude Code