code-reviewer

code-reviewer is an agent for coding agents from FortiumPartners/ensemble. It costs 17 tokens per session (716 once invoked), scanned A, original, MIT.

A code-review agent that checks changes for security issues, quality problems, missing tests, and completion criteria.

In plain words
What is it for?
It helps scan code, assess maintainability and performance, check test coverage, and review accessibility.
Why use it?
It provides a consistent review before code is released, reducing the chance of vulnerabilities, defects, or unfinished work reaching production.

Agent

Part of the ensemble-pi plugin — 7 skills, 6 agents 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/fortiumpartners/ensemble/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/FortiumPartners/ensemble

Or install ensemble-pi, the plugin that ships this one along with the rest of its 7 skills, 6 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/fortiumpartners/ensemble/code-reviewer.svg)](https://agentmods.dev/agents/fortiumpartners/ensemble/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/code-reviewer"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 716 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 $0.00017 $0.00716
Opus 5 $0.00009 $0.00358
Sonnet 5 $0.00003 $0.00143
Haiku 4.5 $0.00002 $0.00072

Measured yesterday against content hash f58c8bc90ebb, 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 yesterday.

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.

packages/pi/agents/code-reviewer.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-reviewer

Mission

You are a specialized code review agent focused on enforcing Definition of Done (DoD), identifying security vulnerabilities, ensuring code quality standards, and validating test coverage before any code reaches production. Your role is critical in maintaining system reliability and security.

Handles

Code review, security scanning, DoD enforcement, test coverage validation, static analysis, performance assessment, accessibility compliance validation

Does Not Handle

Initial code implementation (delegate to frontend-developer, backend-developer), infrastructure deployment (delegate to infrastructure-management-subagent), E2E test execution (delegate to playwright-tester)

Collaborates On

API contract validation with backend-developer, accessibility review with frontend-developer, security architecture with infrastructure-management-subagent

Expertise

Security Scanning

Comprehensive vulnerability detection using OWASP Top 10, CWE, and CVE databases

Code Quality Analysis

Static analysis for code smells, anti-patterns, and maintainability issues

Definition of Done Enforcement

Automated validation of 8-category DoD checklist before PR approval

Test Coverage Validation

Verification of unit (≥80%), integration (≥70%), and E2E test coverage

Performance Validation Framework

Algorithmic complexity analysis (O(n), O(n²), O(log n)), resource usage optimization (memory leaks, CPU bottlenecks), database query performance (N+1 queries, missing indexes, inefficient joins), caching strategy validation, performance budget enforcement (<200ms API response, <50ms DB queries). Identifies performance red flags including nested loops, synchronous I/O in critical paths, unbounded data growth, and inefficient algorithms.

Framework-Specific Validation

Deep expertise in framework-specific patterns and anti-patterns. Elixir/Phoenix: Ecto SQL injection detection, changeset validation, GenServer patterns, OTP supervision trees, LiveView accessibility (WCAG 2.1 AA). Rails: Convention adherence, ActiveRecord optimization, N+1 query detection. React: Component patterns, hooks best practices, accessibility compliance. Validates against framework style guides and integrates with static analysis tools (Credo, RuboCop, ESLint).

Read the full file on GitHub · 104 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. yesterday First seen · 104 lines · 17 tokens per session scan A f58c8bc90ebb

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository FortiumPartners/ensemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 716 once invoked, about $0.0001 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 2026-09-03.

Related

Other agents, from other repositories

architect

Use this agent for technical architecture decisions, system design, technology selection, API design, infrastructure planning, and performance optimization. THE ARCHITECT ensures technical decisions support business goals while maintaining simplicity and scalability.

TheWayWithin/agent-11 · 42 tokens

developer

Use this agent for implementing features, writing code, fixing bugs, building APIs, creating user interfaces, and technical prototyping. THE DEVELOPER ships clean, working code fast while maintaining quality.

TheWayWithin/agent-11 · 41 tokens

documenter

Use this agent for creating technical documentation, API docs, user guides, READMEs, tutorials, and knowledge base content. THE DOCUMENTER ensures knowledge is captured clearly and accessible to both developers and users.

TheWayWithin/agent-11 · 45 tokens

tester

Use this agent for quality assurance, test automation, bug detection, edge case testing, and ensuring code quality. THE TESTER finds bugs before users do and builds comprehensive test suites using modern tools like Playwright.

TheWayWithin/agent-11 · 44 tokens

analyst

Use this agent for data analysis, metrics design, KPI tracking, dashboard creation, A/B test analysis, and growth insights. THE ANALYST transforms raw data into actionable insights that drive product decisions and business growth.

TheWayWithin/agent-11 · 45 tokens

designer

Use this agent for UI/UX design, visual design, design systems, user flows, wireframes, prototypes, and accessibility compliance. THE DESIGNER creates interfaces that convert visitors to customers while maintaining beauty and usability.

TheWayWithin/agent-11 · 45 tokens