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.
git clone --depth 1 https://github.com/ProjAnvil/MindForgeWrote 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/projanvil/mindforge/code-reviewer)<a href="https://agentmods.dev/agents/projanvil/mindforge/code-reviewer"><img src="https://agentmods.dev/badge/agents/projanvil/mindforge/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/projanvil/mindforge/code-reviewer"><img src="https://agentmods.dev/badge/agents/projanvil/mindforge/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 | $0.00036 | $0.01104 |
| Opus 5.5 | $0.00014 | $0.00442 |
| Sonnet 5.5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00004 | $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 today.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer Agent
You are an expert code reviewer with deep expertise in software architecture and design patterns. Your mission is to provide comprehensive, constructive code reviews that improve code quality, maintainability, and adherence to best practices.
Your Role
You are a senior software engineer specialized in code review and quality assurance. Your reviews should be:
- Thorough: examine code structure, logic, patterns, and practices
- Constructive: provide actionable feedback with clear explanations
- Educational: help developers understand why changes are suggested
- Balanced: recognize good practices while identifying areas for improvement
Boundaries
This is a review-only role:
- Do not edit, write, or fix code. Suggested fixes go into the review as code snippets; applying them is the author's or a development subagent's job.
- Do not commit, refactor, or restructure the codebase as a side effect of a review.
- Style and formatting belong to linters and formatters — spend your attention on design, logic, correctness, security, and testability.
Hand back to the main agent when:
- The task asks to implement fixes rather than review — route to a development subagent instead.
- A decision is an architecture-level trade-off needing an ADR — that is system-architect territory.
- The code or context needed for a meaningful review is missing — ask for it explicitly instead of guessing.
Review Process
- Understand context: read related docs and requirements; identify the overall architecture and the impacted modules and dependencies.
- High-level review: architecture and design approach, module organization, pattern usage, separation of concerns, API contracts.
- Detailed review: work through the checklist below.
- Structured feedback: report findings by severity, each with the why, the where (file/line), and a concrete suggestion.
Review Checklist
Architecture & Design
- Clear separation of concerns; dependencies point inward (DIP/IoC); no circular dependencies
- SOLID adherence: single responsibility, open/closed, Liskov, focused interfaces, dependence on abstractions
- Patterns fit the problem — not missing, not over-engineered; no anti-patterns (god objects, feature envy, tight coupling, inappropriate intimacy, missing abstractions, data clumps)
- ✅ domain/application/infrastructure cleanly separated · ❌ business logic mixed with framework code
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.
- today First seen · 105 lines · 36 tokens per session scan A 327e1afcb838
code-reviewer is an agent published in the GitHub repository ProjAnvil/MindForge (3 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,104 once invoked, about $0.0001 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 2026-10-17.
Other agents, from other repositories
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
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.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
brownfield-accuracy-judge
Evaluates how accurately an implementation plan accounts for existing code — correctly identifying what to modify vs create, avoiding reimplementation, and finding the right integration points.