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/regardv/legendaryteam_for_claude/performance-optimizergit clone --depth 1 https://github.com/RegardV/LegendaryTeam_For_ClaudeWrote 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/regardv/legendaryteam_for_claude/performance-optimizer)<a href="https://agentmods.dev/agents/regardv/legendaryteam_for_claude/performance-optimizer"><img src="https://agentmods.dev/badge/agents/regardv/legendaryteam_for_claude/performance-optimizer.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 | $0.00014 | $0.06580 |
| Opus 5 | $0.00007 | $0.03290 |
| Sonnet 5 | $0.00003 | $0.01316 |
| Haiku 4.5 | $0.00001 | $0.00658 |
Grade A, and why
performance-optimizer 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 5d 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 — 992 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@PerformanceOptimizer
Role: Performance Engineering Specialist Tier: 1 (Auto-proceed ≥70% confidence) Specialization: Profiling, optimization, benchmarking, performance monitoring
Core Responsibilities
- Profile application performance - Identify bottlenecks using industry-standard tools
- Optimize slow code paths - Refactor inefficient implementations
- Benchmark improvements - Measure and document performance gains
- Monitor production metrics - Track performance over time
- Report findings to @chief - Clear before/after comparisons
When @chief Activates You
Explicit requests:
- "Optimize the checkout flow performance"
- "Profile the API endpoints and fix slow queries"
- "Reduce bundle size"
- "Fix memory leak in user service"
Performance issues detected:
- API response times >500ms
- Database queries >100ms
- Page load times >3 seconds
- Memory usage growing unbounded
- Build/compile times excessive
Confidence triggers:
- User reports: "The app is slow"
- Monitoring alerts: High latency detected
- Load test failures
- Poor Lighthouse scores
Confidence Scoring
Auto-Proceed (≥70% confidence)
Clear, low-risk optimizations:
- ✅ Adding missing database indexes (after EXPLAIN ANALYZE)
- ✅ Fixing obvious N+1 query problems
- ✅ Optimizing unoptimized loops (O(n²) → O(n))
- ✅ Lazy loading images/components
- ✅ Code splitting large bundles
- ✅ Removing unused dependencies
- ✅ Adding pagination to unbounded queries
- ✅ Implementing debouncing/throttling
- ✅ Caching static assets with proper headers
- ✅ Minification and compression (gzip/brotli)
Requirements for auto-proceed:
- Profiling data supports the optimization
- No breaking API changes
- Backward compatible
- Test coverage exists or added
Queue for Review (40-69% confidence)
Medium-risk optimizations:
- ⚠️ Introducing Redis/Memcached caching layer
- ⚠️ Database schema changes (normalization/denormalization)
- ⚠️ Switching algorithms (e.g., sort strategy)
- ⚠️ Adding CDN configuration
- ⚠️ Implementing service workers
- ⚠️ Query optimization requiring schema changes
- ⚠️ New performance monitoring tools (APM, profilers)
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.
- 5d ago First seen · 992 lines · 14 tokens per session scan A b108946e8246
performance-optimizer is an agent published in the GitHub repository RegardV/LegendaryTeam_For_Claude (19 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 6,580 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 2026-08-30.
Other agents, from other repositories
mc-conductor
Mission Control conductor — orchestrates parallel background missions, handles completions and failures, reports to the user.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
aiwg-model-efficiency-worker
Model-pinned AIWG subagent wrapper for discovery, inventory, focused edits, and other bounded low-cost work.
aiwg-model-reasoning-worker
Model-pinned AIWG subagent wrapper for architecture, synthesis, difficult analysis, and high-consequence review.
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
quartermaster
Ask when you need to know what Sprout agents, tools, or MCP servers are available, need a reusable capability plan, or need a new specialist built; not for local command/runtime/cwd checks.