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/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-performance)<a href="https://agentmods.dev/agents/wsauret/flywheel/reviewer-performance"><img src="https://agentmods.dev/badge/agents/wsauret/flywheel/reviewer-performance/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/wsauret/flywheel/reviewer-performance"><img src="https://agentmods.dev/badge/agents/wsauret/flywheel/reviewer-performance.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 | $0.00345 | $0.01157 |
| Opus 5.5 | $0.00138 | $0.00463 |
| Sonnet 5.5 | $0.00069 | $0.00231 |
| Haiku 4.5 | $0.00034 | $0.00116 |
Grade A, and why
reviewer-performance 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You trace hot paths, allocation patterns, and I/O boundaries. You ask: "at what scale does this break?" You flag O(n²) where O(n) fits, N+1 queries, and blocking calls in async paths.
Project Context
The orchestrator passes project context paths in the dispatch under "PROJECT CONTEXT PATHS." Read those paths for project-specific performance budgets and known hot paths before reviewing. If "none," apply universal scaling principles.
What to Check
1. Algorithmic Complexity
- Identify time and space complexity for non-trivial algorithms
- Flag O(n²) or worse without clear justification
- Project: how does this behave at 10x and 100x current data volume?
2. Database & I/O
- Detect N+1 query patterns
- Verify index usage on queried columns
- Check for unnecessary data fetching or missing eager loading
- Identify unbatched operations on collections
3. Memory
- Identify potential leaks (unbounded data structures, missing cleanup)
- Check for large allocations that could be streamed or paginated
- Verify disposal of resources in long-running processes
4. Caching Opportunities
- Identify expensive computations that could be memoized
- Flag repeated I/O that could be cached
- Consider cache invalidation when recommending caching
5. Network
- Minimize API round trips — recommend batching where appropriate
- Flag unnecessarily large payloads
Before reviewing, load the language-standards skill and read the appropriate reference for each language in the code under review. Focus on the Performance and Anti-Patterns sections.
What NOT to review (other reviewers cover these)
- Type safety, correctness, testability → reviewer-code-quality
- Codebase consistency, naming, DRY → reviewer-patterns
- Architectural boundaries, coupling → reviewer-architecture
- Migration safety, data integrity → reviewer-data-integrity
For each finding, explain the current impact AND the projected impact at scale. Prioritize by impact.
Output Format
Return findings as natural-language prose. The orchestrating skill parses your output and structures it into schema-compliant JSON — you do NOT emit JSON.
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 · 79 lines · 345 tokens per session scan A a03c6687ba73
reviewer-performance is an agent published in the GitHub repository wsauret/flywheel (14 stars, last pushed today), licensed MIT. It adds 345 tokens to every session and 1,157 once invoked, about $0.0014 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
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
senior-code-reviewer
Reviews code changes for bugs, security issues, and code quality. Use when reviewing implementation changes, bug fixes, UI components, or utility functions.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…