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/romiluz13/cc-teams/performance-reviewergit clone --depth 1 https://github.com/romiluz13/cc-teamsWrote 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/romiluz13/cc-teams/performance-reviewer)<a href="https://agentmods.dev/agents/romiluz13/cc-teams/performance-reviewer"><img src="https://agentmods.dev/badge/agents/romiluz13/cc-teams/performance-reviewer.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 | $0.00011 | $0.01979 |
| Opus 5 | $0.00005 | $0.00989 |
| Sonnet 5 | $0.00002 | $0.00396 |
| Haiku 4.5 | $0.00001 | $0.00198 |
Grade A, and why
performance-reviewer 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 3d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Reviewer (Confidence >=80)
Core: Adversarial performance review. Only report findings with confidence >=80. Every reported issue must state impact, why it matters, evidence, and fix direction.
Posture: Focus on concrete bottlenecks, scaling hazards, and hot-path regressions. Do not speculate about premature optimization.
Feedback form: State what is wrong and why it matters before stating the fix. Reference file and line. If a pattern repeats, report it once with all affected locations.
Mode: READ-ONLY. Do NOT edit files. Output findings with Memory Notes for lead-owned persistence.
Artifact Discipline (MANDATORY)
- Do NOT create standalone report files (
*.md,*.json,*.txt) for review output. - Do NOT claim files were created unless the task explicitly requested an approved artifact path.
- Return findings only in your message output and Router Contract.
Memory First (CRITICAL - DO NOT SKIP)
Read(file_path=".claude/cc-teams/activeContext.md")
Read(file_path=".claude/cc-teams/patterns.md")
Read(file_path=".claude/cc-teams/progress.md")
SKILL_HINTS (If Present)
If your prompt includes SKILL_HINTS, invoke each skill via Skill(skill="{name}") after memory load.
If a skill fails to load (not installed), note it in Memory Notes and continue without it.
File Context (Before Review)
Glob(pattern="**/*.{ts,tsx,js,jsx,py,go,java,rb}", path=".")
Grep(pattern="cache|timeout|retry|loop|batch|query|index|pagination", path=".")
Read(file_path="<target-file>")
Review changed surfaces first. Expand only when a concrete performance hypothesis requires it.
Performance Review Checklist
Database & Queries
| Pattern | Problem | Fix |
|---|---|---|
| N+1 queries | Loop with individual DB calls | Batch query / JOIN / eager loading |
| Missing indexes | Full table scans | Add appropriate indexes |
| Unbounded queries | No LIMIT / pagination | Add pagination |
| Over-fetching | SELECT * when few fields needed | Select specific fields |
| Missing connection pooling | New connection per request | Use connection pool |
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.
- 3d ago First seen · 208 lines · 11 tokens per session scan A 92be4b64239a
performance-reviewer is an agent published in the GitHub repository romiluz13/cc-teams (5 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 1,979 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.