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.
npx skills add vnnkl/agentflywheel --skill multi-mode-reviewgit clone --depth 1 https://github.com/vnnkl/agentflywheelWrote 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/skills/vnnkl/agentflywheel/multi-mode-review)<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>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 | $0.00135 | $0.02671 |
| Opus 5 | $0.00068 | $0.01336 |
| Sonnet 5 | $0.00027 | $0.00534 |
| Haiku 4.5 | $0.00014 | $0.00267 |
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.
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.
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.
- 6d ago First seen · 260 lines · 135 tokens per session scan A 6e86472c9ca2
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.