41 tagged cost optimization, measured the same way as everything else here.
Browse within: azure 14Multi-Agent 11agentic-devops 8ai-credits 8ai-observability 8aspire 8reasoning-effort 7token-economy 7agentic 6aiops 6aws 6
Agent Claude Code
Fresh-context correctness reviewer. Given a code diff, verifies it by actually building/testing the affected service and reading the changed lines, then reports correctness findings grounded in machine-checkable evidence. Never edits code — reports only.
Agent Claude Code
Fresh-context adversary. Given a proposed implementation plan, argues against it — finds the strongest structural objections grounded in the actual codebase, plus a future-self critique. Does not design alternatives (that is plan-alternative's job) and does not write code.
Agent
Most agenttest.go files in this directory are smoke tests against a populated test cluster, not regression-grade self-contained tests. This file explains why, the limits of the current model, and the migration target for tests that need to be self-validating.
Agent
Cost-optimized assistant that routes every task through LLM Router first.
Agent
Read-only codebase sweep that returns conclusions and path:line citations only, never file contents. Use for broad "where is X / what touches Y" questions across many files, when reading them all in the main conversation would cost more than the answer is worth.
paulasilvatech/frontier-cockpit
Agent
Expert agent for creating comprehensive Architectural Decision Records (ADRs) with structured formatting optimized for AI consumption and human readability.
paulasilvatech/frontier-cockpit
Agent
AI-native engineering persona focused on GitHub platform and Azure AI Foundry: designs production agentic architectures (model routing, prompt and semantic caching, context and memory, tools and MCP, guardrails, evaluation, observability, and cost), then renders complete architecture diagrams with official Azure…
paulasilvatech/frontier-cockpit
Agent
Provide expert Azure Principal Architect guidance using Azure Well-Architected Framework principles and Microsoft best practices.
Agent
The agents feature is Attune's Universal Agent Factory — one interface for creating, running, and orchestrating AI agents, backed by your choice of framework (native, LangChain, LangGraph, AutoGen, or Haystack) without rewriting code when you switch frameworks. The entry point is AgentFactory: it picks a framework…
Agent
Create an agent and invoke it. invoke is a coroutine, so drive it with asyncio.run.
Agent
Goal: create one agent and get a result.
Agent
Use shorthand-first compression for agent workflows while keeping technical precision and exact literals.
Agent
GitHub issue management specialist. Creates, updates, labels, links, and manages issues efficiently. Handles bulk operations and templating. Perfect for deterministic GitHub operations at 87% cost savings with Haiku 4.5.
Agent
Benchmark and analyze parallel workflow performance. Measures timing, identifies bottlenecks, calculates speedup metrics (Amdahl's Law), generates cost comparisons, and provides optimization recommendations. Use for workflow performance analysis and cost optimization.
Agent
Autonomous test execution and reporting across multiple languages and frameworks. Runs tests, generates reports, creates GitHub issues for failures, tracks coverage, and performs benchmarking. Optimized for cost-efficiency with Haiku 4.5.
Agent
Implements one well-defined task from an approved plan or spec. Needs a self-contained task description; not for exploratory or ambiguous work. Pinned to sonnet - dispatch with model=opus for multi-file, architectural, or subtle work.
Agent
Read-only codebase explorer. Use for "where is X", "how does Y work", "which files touch Z" - returns conclusions with file:line refs, never file dumps. Never modifies anything.
Agent
Read-only breadth sweeps over a codebase - enumerate, list, trace a chain end to end ("list every stage in order", "which files import X", "where does this pipeline end"). Returns the list or the ordering, never file dumps. Use scout instead when the answer needs judgement about what code does. Never modifies anything.
Agent
Real subagent persona definitions. Each .json defines one agent — its system prompt, tool grants, skill wrappers, trigger signals, success metrics, and per-agent learnings file.