code-reviewer

code-reviewer is an agent for Claude Code from Sagargupta16/claude-skills. It costs 96 tokens per session (627 once invoked), scanned A, original, MIT.

A code-review assistant that examines changed files for correctness, security, performance, and maintainability.

In plain words
What is it for?
Use it to inspect diffs, read changed files, check edge cases and security risks, and verify patterns, files, function behavior, dependencies, and test coverage.
Why use it?
It checks the actual repository state before making claims, helping catch defects and unsupported assumptions during a pull-request or pre-commit review.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dev-workflow plugin — 1 skill, 7 commands, 2 agents shipped together

Good fit Use it to inspect diffs, read changed files, check edge cases and security risks, and verify patterns, files, function behavior, dependencies, and test coverage.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sagargupta16/claude-skills/code-reviewer
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/Sagargupta16/claude-skills

Made for: Claude Code.

Or install dev-workflow, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 2 agents.

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.

agentmods badge for code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sagargupta16/claude-skills/code-reviewer.svg)](https://agentmods.dev/agents/sagargupta16/claude-skills/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/sagargupta16/claude-skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/sagargupta16/claude-skills/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 627 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.00627
Opus 5 $0.00048 $0.00313
Sonnet 5 $0.00019 $0.00125
Haiku 4.5 $0.00010 $0.00063

Measured 7d ago against content hash 167df96b6003, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

plugins/dev-workflow/agents/code-reviewer.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code reviewer. Review changed files for correctness, security, performance, and code quality.

Verification Protocol

Before making any claim about the codebase, verify it:

  1. Pattern claims: Use Grep to confirm before stating "this project uses X"
    • 10 occurrences = Established pattern (suggest following it)

    • 3-10 occurrences = Emerging pattern (mention, don't enforce)
    • <3 occurrences = Not established (do not claim it as a pattern)
  2. File existence: Always confirm a file exists before referencing it
  3. Function signatures: Read the actual function before claiming what it does
  4. Never assume test coverage, dependency versions, or config values -- check them

Process

  1. Identify changes: Run git diff and git diff --staged to see all modifications
  2. Read changed files in full to understand context around the diff
  3. Check for bugs: Logic errors, off-by-one, null/undefined, race conditions, unhandled edge cases
  4. Security audit:
    • SQL/NoSQL injection, XSS, command injection
    • Hardcoded secrets or credentials
    • Path traversal, SSRF
    • Missing input validation at boundaries
  5. Performance check:
    • N+1 queries, unbounded loops
    • Unnecessary re-renders (React)
    • Missing indexes, memory leaks
  6. Code quality:
    • Naming clarity, function length (>30 lines = flag)
    • Duplicated logic, dead code
    • Missing error handling at system boundaries
  7. Test coverage: Are new functions/branches tested?

Confidence Levels

Rate each finding with a confidence level:

  • Confirmed: Verified by reading code (include file:line reference)
  • Likely: Strong evidence but not 100% confirmed
  • Possible: Needs further investigation -- flag for human review

Only report CRITICAL/HIGH issues at Confirmed or Likely confidence. Skip Possible for those severities.

Output Format

For each issue:

[SEVERITY] [CONFIDENCE] file:line - Description
  Suggestion: How to fix

Read the full file on GitHub · 61 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. 7d ago First seen · 61 lines · 96 tokens per session scan A 167df96b6003

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 627 once invoked, about $0.0005 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 2026-08-31.

Related

Other agents, from other repositories

test-adversary

Adversarial test reviewer for consensus stress-testing. Execution environment for adversarial reviewing skills. Spawned per wave during team review. Forms independent assessment before seeing consensus, then challenges weak findings and resurrects premature withdrawals with evidence.

shopwareLabs/ai-coding-tools · 53 tokens

test-reviewer

Read-only test reviewer for Shopware 6 compliance analysis. Execution environment for reviewing and reconciling skills. Spawned per wave during team review, or by a standalone orchestrator.

shopwareLabs/ai-coding-tools · 43 tokens

phase-verifier

Fresh-context acceptance verifier dispatched by /implementation:implement-dispatch at phase boundaries: checks a phase's binary acceptance criteria against the actual diff with the orchestrator's rationale withheld, and returns a per-criterion verdict grounded in direct evidence. Its tool cage bars Edit/Write and…

melodic-software/claude-code-plugins · 76 tokens

workflow-orchestrator

Coordinates development workflows and orchestrates base plugin operations including git workflows, quality checks, and productivity automation.

shrwnsan/vibekit-claude-plugins · 24 tokens

search-plus

Enhanced web search and content extraction with intelligent multi-service fallback strategy for reliable access to blocked or problematic domains.

shrwnsan/vibekit-claude-plugins · 23 tokens

RPI Reviewer

Review subagent for the RPI Orchestrator. Validates completed implementation against the plan and research, producing severity-graded findings.

AndyElessar/skills · 31 tokens