multi-mode-review

multi-mode-review is a skill for Claude Code, Codex from vnnkl/agentflywheel. It costs 135 tokens per session (2,671 once invoked), scanned A, original, MIT.

A code-review method that examines changes from three perspectives: fresh eyes, another agent, and random exploration.

In plain words
What is it for?
It reviews code for logic errors, edge cases, component-boundary problems, missing interface handling, dead paths, and inconsistent patterns.
Why use it?
Different review perspectives catch different problems, including local mistakes, integration issues, and broader design drift.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit It reviews code for logic errors, edge cases, component-boundary problems, missing interface…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vnnkl/agentflywheel/multi-mode-review
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.

Any agent
npx skills add vnnkl/agentflywheel --skill multi-mode-review
Clone the repo
git clone --depth 1 https://github.com/vnnkl/agentflywheel

Made for: Claude Code, Codex.

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 multi-mode-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/vnnkl/agentflywheel/multi-mode-review.svg)](https://agentmods.dev/skills/vnnkl/agentflywheel/multi-mode-review)
Your own site
<a href="https://agentmods.dev/skills/vnnkl/agentflywheel/multi-mode-review"><img src="https://agentmods.dev/badge/skills/vnnkl/agentflywheel/multi-mode-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,671 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00135 $0.02671
Opus 5 $0.00068 $0.01336
Sonnet 5 $0.00027 $0.00534
Haiku 4.5 $0.00014 $0.00267

Measured 6d ago against content hash 6e86472c9ca2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

multi-mode-review 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 6d 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.

skills/multi-mode-review/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Mode Review

Three distinct review modes that activate different problem-finding behaviors. Each mode catches a different category of bugs. Using only one mode leaves entire bug categories undetected.

Why Three Modes?

Mode What It Catches Blind Spots
Fresh Eyes Local logic errors, off-by-ones, missed edge cases, naming issues Cannot see integration problems or systemic drift
Cross-Agent Integration errors, boundary mismatches, coupling, missing error handling at interfaces Cannot see local logic errors (different agent lacks original context)
Random Exploration Architectural drift, dead code paths, inconsistent patterns, systemic issues Cannot see local logic errors or specific integration bugs

A single-mode review gives false confidence. The code "passes review" but only for one category of bugs.

When to Use Which Mode

Default: Run All Three

For any meaningful review request, run all three modes. They are complementary, not alternatives.

If time-constrained, prioritize by situation:

  • Just finished writing code -> Fresh Eyes first (catch logic errors before they propagate)
  • Integrating multiple components -> Cross-Agent first (catch boundary mismatches early)
  • Codebase has grown organically / tech debt concerns -> Random Exploration first (find systemic rot)
  • Pre-merge / PR review -> All three, start with Cross-Agent (integration issues are the costliest to fix post-merge)
  • Bug hunt (something is wrong but unclear what) -> Random Exploration first (trace actual execution to find where assumptions break)

Mode 1: Fresh Eyes Review

Why This Mode Exists

After writing code, you are blind to your own assumptions. You read what you intended, not what you wrote. Fresh Eyes forces a perspective shift: pretend you did not write this code. Look for what is wrong, not what is right.

This mode catches: off-by-one errors, unhandled edge cases, incorrect boolean logic, misleading variable names, missing null checks, wrong operator precedence, silent failures, resource leaks.

Read the full file on GitHub · 260 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. 6d ago First seen · 260 lines · 135 tokens per session scan A 6e86472c9ca2

Subscribe to this mod's changes

multi-mode-review is a skill published in the GitHub repository vnnkl/agentflywheel (2 stars, last pushed 3mo ago), licensed MIT. It adds 135 tokens to every session and 2,671 once invoked, about $0.0007 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 2026-08-31.