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/airmcp-com/mcp-standardsWrote 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/commands/airmcp-com/mcp-standards/optimization)<a href="https://agentmods.dev/commands/airmcp-com/mcp-standards/optimization"><img src="https://agentmods.dev/badge/commands/airmcp-com/mcp-standards/optimization/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/commands/airmcp-com/mcp-standards/optimization"><img src="https://agentmods.dev/badge/commands/airmcp-com/mcp-standards/optimization.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 | $0.00000 | $0.00623 |
| Opus 5.5 | $0.00000 | $0.00249 |
| Sonnet 5.5 | $0.00000 | $0.00125 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
optimization 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.
This is a copy
100% identical to optimization — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimization Swarm Strategy
Purpose
Performance optimization through specialized analysis.
Activation
Using MCP Tools
// Initialize optimization swarm
mcp__claude-flow__swarm_init({
"topology": "mesh",
"maxAgents": 6,
"strategy": "adaptive"
})
// Orchestrate optimization task
mcp__claude-flow__task_orchestrate({
"task": "optimize performance",
"strategy": "parallel",
"priority": "high"
})
Using CLI (Fallback)
npx claude-flow swarm "optimize performance" --strategy optimization
Agent Roles
Agent Spawning with MCP
// Spawn optimization agents
mcp__claude-flow__agent_spawn({
"type": "optimizer",
"name": "Performance Profiler",
"capabilities": ["profiling", "bottleneck-detection"]
})
mcp__claude-flow__agent_spawn({
"type": "analyst",
"name": "Memory Analyzer",
"capabilities": ["memory-analysis", "leak-detection"]
})
mcp__claude-flow__agent_spawn({
"type": "optimizer",
"name": "Code Optimizer",
"capabilities": ["code-optimization", "refactoring"]
})
mcp__claude-flow__agent_spawn({
"type": "tester",
"name": "Benchmark Runner",
"capabilities": ["benchmarking", "performance-testing"]
})
Optimization Areas
Performance Analysis
// Analyze bottlenecks
mcp__claude-flow__bottleneck_analyze({
"component": "all",
"metrics": ["cpu", "memory", "io", "network"]
})
// Run benchmarks
mcp__claude-flow__benchmark_run({
"suite": "performance"
})
// WASM optimization
mcp__claude-flow__wasm_optimize({
"operation": "simd-acceleration"
})
Optimization Operations
// Optimize topology
mcp__claude-flow__topology_optimize({
"swarmId": "optimization-swarm"
})
// DAA optimization
mcp__claude-flow__daa_optimization({
"target": "performance",
"metrics": ["speed", "memory", "efficiency"]
})
// Load balancing
mcp__claude-flow__load_balance({
"swarmId": "optimization-swarm",
"tasks": optimizationTasks
})
Monitoring and Reporting
// Performance report
mcp__claude-flow__performance_report({
"format": "detailed",
"timeframe": "7d"
})
// Trend analysis
mcp__claude-flow__trend_analysis({
"metric": "performance",
"period": "30d"
})
// Cost analysis
mcp__claude-flow__cost_analysis({
"timeframe": "30d"
})
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 · 118 lines · 0 tokens per session scan A 13b18f422d43
optimization is a command published in the GitHub repository airmcp-com/mcp-standards (3 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 623 tokens. A static security scan graded it A with 0 findings. It is 100% identical to optimization, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
reproduce-bug
Reproduce and investigate a bug using logs, console inspection, and browser screenshots.
verify-loop
A command that repeatedly checks recent code changes and tries to fix failures, with a configurable retry limit. It can run code review, builds, tests, linting, and type checks according to the project language.
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.
lint
The canonical linter per ecosystem over your changes: findings are diagnoses you judge, fix, or explain.
build-fix
A build-error fixing procedure for TypeScript projects. It runs the project build, groups and explains errors, applies fixes one at a time, and checks the build again.
validate
Run SDLC compliance check against the current project. Validates build system, code quality, testing, CI/CD, security, documentation, VCS, and release configurations.