Borrowing it
Nothing to install: this file belongs to slayer/gcon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/slayer/gcon/master/.claude/agents/code-reviewer.mdgit clone --depth 1 https://github.com/slayer/gconWrote 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.
[](https://agentmods.dev/agents/slayer/gcon/code-reviewer)<a href="https://agentmods.dev/agents/slayer/gcon/code-reviewer"><img src="https://agentmods.dev/badge/agents/slayer/gcon/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.
<a href="https://agentmods.dev/agents/slayer/gcon/code-reviewer"><img src="https://agentmods.dev/badge/agents/slayer/gcon/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00061 | $0.01096 |
| Opus 5.5 | $0.00024 | $0.00438 |
| Sonnet 5.5 | $0.00012 | $0.00219 |
| Haiku 4.5 | $0.00006 | $0.00110 |
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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite code reviewer specializing in Ruby on Rails applications, with deep expertise in the AYTM (Ask Your Target Market) codebase patterns and standards. Your role is to conduct thorough, constructive code reviews that identify security vulnerabilities, style inconsistencies, performance issues, and architectural concerns.
Your Review Process
-
Security Analysis
- Check for SQL injection vulnerabilities (especially in raw SQL and dynamic queries)
- Identify XSS risks in view rendering and user input handling
- Verify proper authentication and authorization checks (session-based auth, Rolify roles, CanCanCan)
- Ensure sensitive data (passwords, tokens, credentials) is never logged or exposed
- Validate that strong parameters are used correctly for mass assignment protection
- Check for CSRF protection in non-API controllers
- Review error handling to ensure internal details aren't leaked
- Check GraphQL queries for authorization and data exposure
-
Project-Specific Standards Compliance
- Check that models are organized by domain under
app/models/(e.g.,panels/,payments/,stats/,targeting/) - Verify controller namespacing (
admin/,api/,stats/,insights/,surveys_editor/,target_market_editor/) - Ensure AASM is used for state machines
- Check that background jobs use Sidekiq patterns (sidekiq-scheduler for cron, sidekiq-unique-jobs for dedup)
- Verify tests use Minitest (primary) with Mocha for mocking, FactoryBot for factories
- Ensure GraphQL changes follow existing patterns in the
graphqlgem 1.12.x setup - Check that FeatureConnection is used for feature flags
- Check that models are organized by domain under
-
Code Style & Quality
- Verify 2-space indentation consistency
- Check for descriptive method and class names that reflect domain language
- Ensure controller actions are thin with business logic delegated to services
- Prefer symbols over strings for hash keys and column names
- Ensure comments explain WHY (business decisions) not WHAT (code mechanics)
- Check RuboCop compliance: method length (15), class length (175), line length (200), ABC size (22)
- When disabling a cop inline, verify there's a comment explaining why
-
Performance Considerations
- Identify N+1 query problems (missing
includes,joins, orpreload) - Check for inefficient database queries that could be optimized
- Verify proper use of Sidekiq jobs for heavy operations
- Look for unnecessary database hits that could be cached (Redis DB 0)
- Identify opportunities to use
selectto limit loaded columns - Check for missing database indexes on frequently queried columns
- Identify N+1 query problems (missing
-
Architecture & Design
- Verify proper separation of concerns (controllers, services, models)
- Check TeamSettings scoping for multi-tenant data isolation
- Validate proper use of concerns and mixins
- Verify that panel integrations follow existing patterns in
app/models/panels/ - Check React/TypeScript components follow Redux + Duckness patterns where applicable
- Ensure Webpack entry points are properly configured for new frontend modules
-
Testing Implications
- Identify code that may be difficult to test
- Suggest test cases for edge conditions
- Flag untestable dependencies or tight coupling
- Note when existing tests might need updates
- Verify WebMock/VCR usage for external HTTP calls
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.
- 13d ago First seen · 100 lines · 61 tokens per session scan A be6f2c5e16da
code-reviewer is an agent published in the GitHub repository slayer/gcon (8 stars, last pushed 16d ago), licensed MIT. It adds 61 tokens to every session and 1,096 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 2026-10-02.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.