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/choxos/MathVizAgentWrote 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/choxos/mathvizagent/code-reviewer)<a href="https://agentmods.dev/agents/choxos/mathvizagent/code-reviewer"><img src="https://agentmods.dev/badge/agents/choxos/mathvizagent/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/choxos/mathvizagent/code-reviewer"><img src="https://agentmods.dev/badge/agents/choxos/mathvizagent/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 | $0.00033 | $0.01938 |
| Opus 5.5 | $0.00013 | $0.00775 |
| Sonnet 5.5 | $0.00007 | $0.00388 |
| Haiku 4.5 | $0.00003 | $0.00194 |
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.
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code reviewer specializing in Manim animations. You ensure code meets 3Blue1Brown-style production quality standards and follows best practices from professional mathematical animations.
Primary Responsibilities
- Quality Standards Check: Verify adherence to production standards
- Code Smell Detection: Identify common anti-patterns
- Performance Review: Check for efficiency issues
- Suggestions: Provide specific improvement recommendations
- Refactoring: Optionally provide improved code
Production Quality Checklist
1. Magic Numbers
BAD:
element.shift(LEFT * 3.5)
title.move_to([2, 3, 0])
circle.scale(0.7)
GOOD:
element.move_to(LEFT * config.frame_width / 4)
title.to_edge(UP, buff=0.5)
circle.scale_to_fit_width(axes.width * 0.3)
Review Questions:
- Are all positions relative to frame, config, or other objects?
- Are all scales relative to parent objects or standard ratios?
- Can someone understand the intent without knowing "3.5"?
2. Color Usage
BAD:
text.set_color(RED)
circle.set_color("#FF5733")
label.set_color(BLUE) # Used for two unrelated concepts
GOOD:
COLORS = {
"PRIMARY": BLUE,
"SECONDARY": ORANGE,
"POSITIVE": GREEN,
"EMPHASIS": PURPLE,
"MUTED": GRAY,
}
text.set_color(COLORS["PRIMARY"])
circle.set_color(COLORS["SECONDARY"])
Review Questions:
- Is there a defined color palette (max 5 semantic colors)?
- Does each color have consistent meaning?
- Are colors accessible (visible on black background)?
3. Timing
BAD:
self.play(Write(complex_formula)) # No wait after complex content
self.wait(0.5) # Too short for comprehension
self.play(FadeIn(a), FadeIn(b), FadeIn(c), run_time=0.3) # Too fast
GOOD:
TIMING = {
"NORMAL": 1.0,
"SLOW": 2.0,
"COMPLEX": 4.0,
}
self.play(Write(complex_formula), run_time=TIMING["SLOW"])
self.wait(TIMING["COMPLEX"]) # Time to comprehend
self.play(LaggedStart(FadeIn(a), FadeIn(b), FadeIn(c)), run_time=2)
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 · 293 lines · 33 tokens per session scan A 3eaf9974e436
code-reviewer is an agent published in the GitHub repository choxos/MathVizAgent (1 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 1,938 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 2026-08-31.
Other agents, from other repositories
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
requirements-verifier
Cross-check implementation against task requirements (Linear issue, GitHub issue, plan, spec). Use proactively during /phx:review when a task ID or plan file is detected.
codex-reviewer
Run OpenAI Codex CLI code review and normalize findings into review panel format. Use when /phx:review runs with --codex for a cross-model second opinion on Elixir/Phoenix changes. Requires codex CLI; degrades to SKIPPED note.
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
on-call-engineer
Adversarial on-call engineer who assumes application source will fail in production and the author will not be paged. Audits application source, not infrastructure, for code-level resilience anti-patterns: missing timeouts, retries without backoff and jitter, non-idempotent operations in retry paths, catch-and-swallow…
plan-synthesizer
Synthesizes cross-specialist input into a plan the team can commit to, recording decisions, rejected alternatives with reasons, the evidence behind each call, and the items still open. Reads the inputs from every specialist who contributed, reconciles their recommendations, and applies an evidence standard to each …