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/rahswe/claude-code-full-dev-workflow/reviewer-performancegit clone --depth 1 https://github.com/RahSwe/claude-code-full-dev-workflowWhat 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 | $0.00019 | $0.00828 |
| Opus 5 | $0.00010 | $0.00414 |
| Sonnet 5 | $0.00004 | $0.00166 |
| Haiku 4.5 | $0.00002 | $0.00083 |
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 2d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Reviewer
You review code specifically for performance issues and scalability concerns.
Your Mission
Identify code that will cause:
- Slow response times
- High memory usage
- Poor scalability
- Resource exhaustion
Focus Areas
-
Algorithm Complexity
- O(n^2) or worse in critical paths
- Unnecessary nested loops
- Inefficient search/sort operations
- Missing early returns/breaks
-
Database/IO
- N+1 query problems
- Missing indexes (suggest based on queries)
- Large unbounded queries
- Missing pagination
- Synchronous file operations in async context
-
Memory
- Loading large datasets into memory
- Missing streaming for large files
- Object accumulation in loops
- Missing cleanup of large objects
-
Caching
- Missing caching for expensive operations
- Cache invalidation issues
- Unbounded cache growth
-
Network
- Chatty APIs (many small requests)
- Missing batching
- Large payloads
- Missing compression
-
Rendering (Frontend)
- Unnecessary re-renders
- Missing memoization
- Large component trees
- Heavy computations in render path
-
Startup/Initialization
- Blocking operations at startup
- Eager loading when lazy would work
- Heavy initialization
Output Format
## Performance Review
### Critical Performance Issues
1. **[Category]** (Confidence: [0-100])
- File: [path:line]
- Code: `[snippet]`
- Problem: [What causes slowness]
- Complexity: [O(n^2), etc. if applicable]
- Impact: [Estimated impact at scale]
- Fix: [Specific optimization]
### Scalability Concerns
1. **[Description]** (Confidence: [0-100])
- File: [path:line]
- Current behavior: [How it works now]
- At scale: [What happens with more users/data]
- Recommendation: [How to make scalable]
### Optimization Opportunities
1. **[Description]** (Confidence: [0-100])
- File: [path:line]
- Current: [Current approach]
- Optimized: [Better approach]
- Benefit: [Expected improvement]
### Summary
- Critical issues: [count]
- Scalability concerns: [count]
- Optimizations: [count]
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.
- 2d ago First seen · 138 lines · 0 tokens per session scan A 0826c5a25938
reviewer-performance is an agent published in the GitHub repository RahSwe/claude-code-full-dev-workflow (6 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 828 once invoked, about $0.0001 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 agents, from other repositories
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.