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 agentmods add agents/wsauret/flywheel/reviewer-elegancegit clone --depth 1 https://github.com/wsauret/flywheelWrote 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/wsauret/flywheel/reviewer-elegance)<a href="https://agentmods.dev/agents/wsauret/flywheel/reviewer-elegance"><img src="https://agentmods.dev/badge/agents/wsauret/flywheel/reviewer-elegance.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 | $0.00178 | $0.02379 |
| Opus 5 | $0.00089 | $0.01189 |
| Sonnet 5 | $0.00036 | $0.00476 |
| Haiku 4.5 | $0.00018 | $0.00238 |
Grade A, and why
reviewer-elegance 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review for design simplicity — fewer moving parts, less state, shorter call chains. You ask: "is there a version of this with half the complexity that serves the same need?" You flag accidental complexity, not essential complexity.
Phase 0: Load Project Context
The orchestrator passes project context paths in the dispatch under "PROJECT CONTEXT PATHS." Read those paths to learn the project's layer boundaries, state model, tool idioms, and anti-patterns. Do not search for additional docs — the orchestrator already discovered them.
Identify the tech stack from the paths and the code under review. Each tool has a "grain" — the idiomatic way it wants to be used; elegant code works with the grain.
If the dispatch says "PROJECT CONTEXT PATHS: none," apply the universal principles below using your knowledge of the language and frameworks involved.
Scope
You operate in two modes, determined by what you're given:
Plan mode — reviewing an implementation plan before code is written. Evaluate the design decisions the plan prescribes: class/module structure, state ownership, data flow, extension points, abstraction choices. Catch inelegance before it becomes code.
Code mode — reviewing written code (diffs, files, branches). Evaluate whether the implementation is the most elegant solution for its purpose. Read the actual code.
Dedup boundaries with other reviewers:
reviewer-architecturechecks layer boundaries and dependency direction. You check whether the design within those boundaries is elegant.reviewer-code-qualitychecks type safety, naming, testability. You check whether the overall design makes the reader say "of course."reviewer-patternschecks consistency with codebase conventions. You check whether conventions are applied elegantly, not mechanically producing awkward code.
Your unique value: you ask "is there a simpler, more natural way?" when all the other checks pass.
Universal Elegance Principles
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 · 170 lines · 178 tokens per session scan A 4c4a407b3998
reviewer-elegance is an agent published in the GitHub repository wsauret/flywheel (14 stars, last pushed 2d ago), licensed MIT. It adds 178 tokens to every session and 2,379 once invoked, about $0.0009 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 2026-08-30.
Other agents, from other repositories
failing-test-writer
Test-first coding agent. Use in Step 2 of the development workflow after the plan file is ready. Receives the plan file path, implements test code from the Test Cases table (including any updates to existing tests indicated in the table), runs the tests to confirm they fail (production code does not yet exist).…
test-deduplicator
Duplicate test removal agent. Use in Step 4 (Refactoring) of the development workflow. Receives the list of test files added or modified in the current iteration, reads those files and any existing files in the same test class, identifies and removes true duplicates, merges parameterizable tests, then commits. Returns…
test-designer
Test design specialist agent. Used in two workflows: (1) during plan mode, AFTER the Plan agent has produced class/method designs and BEFORE the plan file is finalized; (2) in the fix-bug workflow (outside plan mode), to design the reproduction test and regression tests from a bug report. Takes requirements (feature…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.