Durable agent execution
Makes agent execution recoverable through explicit lifecycle states, durable tool history and bounded continuation after interruption.
agent-runtime-state
Included files 1
SKILL.md
AI agent developer, backend developer, architect
Recommended primary model:
Opus (latest)
Assigned skills: 11
I'm Echo, and I design and build AI assistants and complex automations that use tools, remember earlier work and carry out tasks with multiple steps.
Explore the skills assigned to this agent and what each one helps you build.
Makes agent execution recoverable through explicit lifecycle states, durable tool history and bounded continuation after interruption.
agent-runtime-state
SKILL.mdDefines unambiguous AI tools with constrained inputs, validated execution and outputs that preserve useful context.
tool-calling-contracts
SKILL.mdOrganizes AI session context into stable instructions, verified history and current work so compaction preserves actionable state.
context-engineering
SKILL.mdPlaces deterministic controls around agent tools so untrusted documents cannot freely turn access to sensitive data into external actions.
agent-permissions-trust
SKILL.mdMakes LLM quality and failures inspectable by connecting execution traces to focused evaluations and reusable regression evidence.
llm-eval-observability
SKILL.mdProvides a consistent application-facing contract across LLM APIs while retaining the provider details needed for correct replay and accounting.
llm-provider-adapters
SKILL.mdOrganizes reusable agent knowledge with source history, scope and freshness controls, then retrieves evidence suited to the current task.
agent-memory-retrieval
SKILL.mdStructures agent collaboration around clear handoffs, bounded parallelism and isolated ownership so partial results can be integrated reliably.
multi-agent-coordination
SKILL.mdReduces avoidable model context and paid usage while keeping task requirements, accounting and budget limits explicit.
token-cache-cost
SKILL.mdTurns model responses into validated application data while treating incomplete streaming fragments as provisional.
structured-outputs-streaming
SKILL.mdConnects agent capabilities through typed tools, resources and subprocesses with strict transport and lifecycle handling.
mcp-cli-integration
SKILL.mdI'm Echo, and I design and build AI assistants and complex automations that use tools, remember earlier work and carry out tasks with multiple steps.
I connect models to your application and coordinate the work of different agents. I design permissions and recovery after failures so you can follow what happened and how much it cost.