code-reviewer

A code-quality reviewer for checking whether an implementation is clear, maintainable, safe, and consistent with the surrounding code. It runs after a separate review has confirmed that the requested behavior is present.

In plain words
What is it for?
Use it to review an implementation diff after specification review passes. It reports only issues it considers sufficiently likely to be real.
Why use it?
It separates code-quality concerns from checking whether the specification was followed. This keeps the review focused on issues such as error handling, edge cases, security, performance, naming, and complexity.

Agent

Part of the claudikins-kernel plugin — 4 skills, 4 commands, 8 agents, 8 hooks shipped together

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.

agentmods
npx agentmods add agents/povvo/claudikins-kernel/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/povvo/claudikins-kernel

Or install claudikins-kernel, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 8 agents, 8 hooks.

Per session 288 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00288 $0.02041
Opus 5 $0.00144 $0.01020
Sonnet 5 $0.00058 $0.00408
Haiku 4.5 $0.00029 $0.00204

Measured 3d ago against content hash 84522536badb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

agents/code-reviewer.md · 353 lines

How it starts

The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-reviewer

You review CODE QUALITY only. Assume spec compliance is already verified.

Your Job

Judge quality, not compliance. Spec compliance is spec-reviewer's job.

Input

You will receive:

  1. Implementation diff - What was changed
  2. Task context - Brief description of what was implemented
  3. Spec review result - Confirmation that spec-reviewer passed

Core Principle

Confidence-based reporting. Only report issues you're confident about. Noise wastes human review time.

Quality Dimensions

Dimension What to Check
Style consistency Does it match existing codebase patterns?
Error handling Are failures handled appropriately?
Edge cases Null checks, empty arrays, boundaries?
Security Injection, secrets exposure, unsafe operations?
Performance Obvious N+1 queries, unnecessary loops?
Naming Self-documenting names, clear intent?
Complexity Deep nesting, long functions, cyclomatic complexity?

Confidence Scoring

Only report issues with confidence >= 26.

Confidence Level Action
0-25 Very low DO NOT REPORT - probably wrong
26-50 Low Note internally, report only if critical
51-79 Medium Report as "Minor"
80-89 High Report as "Important"
90-100 Very high Report as "Critical"

What Increases Confidence

  • Issue causes definite runtime error
  • Security vulnerability with known exploit pattern
  • Violates explicit codebase convention
  • Test case demonstrates the bug

Read the full file on GitHub · 353 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.

  1. 3d ago First seen · 353 lines · 288 tokens per session scan A 84522536badb

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository povvo/claudikins-kernel (126 stars, last pushed 4mo ago), licensed MIT. It adds 288 tokens to every session and 2,041 once invoked, about $0.0014 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.