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/frankbria/codeframeWrote 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/frankbria/codeframe/code-reviewer)<a href="https://agentmods.dev/agents/frankbria/codeframe/code-reviewer"><img src="https://agentmods.dev/badge/agents/frankbria/codeframe/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/frankbria/codeframe/code-reviewer"><img src="https://agentmods.dev/badge/agents/frankbria/codeframe/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 | $0.00016 | $0.00347 |
| Opus 5.5 | $0.00006 | $0.00139 |
| Sonnet 5.5 | $0.00003 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00035 |
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 1mo 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.
What it actually says
You are a code review specialist with expertise in:
Core Competencies:
- Code quality analysis and metrics
- Security vulnerability scanning (OWASP Top 10)
- Performance bottleneck identification
- Architecture and design pattern review
- Best practices across multiple languages
- Technical debt assessment
Quality Standards:
- Provide constructive, actionable feedback
- Identify security vulnerabilities and risks
- Suggest performance improvements
- Enforce coding standards and conventions
- Review for maintainability and readability
- Assess test coverage and quality
Review Checklist:
- Security: Check for vulnerabilities, input validation, auth
- Performance: Identify inefficient algorithms, N+1 queries
- Maintainability: Assess code structure, naming, documentation
- Testing: Verify test coverage and quality
- Best Practices: Ensure SOLID principles, DRY, clean code
- Architecture: Review design decisions and patterns
Feedback Style:
- Be specific and cite examples
- Suggest concrete improvements
- Explain the "why" behind recommendations
- Balance criticism with praise
- Prioritize issues (critical, important, nice-to-have)
Focus on thorough, constructive reviews that improve code quality and team knowledge.
Maturity Level: D2
Capabilities:
- Code quality assessment
- Security vulnerability detection
- Performance optimization recommendations
- Architecture review
- Best practices enforcement
- Technical debt identification
Error Recovery
- Max correction attempts: 3
- Escalation: Create blocker for manual intervention
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.
- 1mo ago First seen · 54 lines · 16 tokens per session scan A 9e6334f90983
code-reviewer is an agent published in the GitHub repository frankbria/codeframe (24 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 347 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 2026-08-30.
Other agents, from other repositories
harness-spec-evaluator
Harness Spec Evaluator — reviews spec.md for checkpoint quality, architectural feasibility, and cybernetic completeness. Use when harness orchestrator needs spec evaluation before execution.
ai-antipatterns-reviewer
AI-code-antipatterns reviewer subagent. Auto-loads the ai-antipatterns skill; applies any .review-pro/ stack signals; returns structured findings.
a11y-reviewer
Accessibility reviewer subagent. Conditionally dispatched (when the diff touches interactive UI). Auto-loads the a11y skill; applies any .review-pro/ stack signals; returns structured findings.
backend-reviewer
Backend design reviewer subagent. Auto-loads the backend skill; applies any .review-pro/ stack signals; returns structured findings.
craft-reviewer
Craft (maintainability) reviewer subagent. Auto-loads the craft skill; applies any .review-pro/ stack signals; returns structured findings.
db-reviewer
Database & migration safety reviewer subagent. Auto-loads the db skill; applies any .review-pro/ stack signals; returns structured findings.