Skip to content

agentsope/SkillAlchemy / skills/agentsop-llm-tool-idempotency

agentsop-llm-tool-idempotency

Verified

Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the tool must promise the second call is safe. Framework-agnostic — applies to LangGraph node bodies that re-run on resume, MCP tools, OpenAI tool-calling retries, CrewAI delegated tool invocations, and direct HTTP wrappers. Search keywords: duplicate email sent, charged twice, exactly-once, idempotency key, tool called twice, retry side effect, double-send, at-least-once delivery.

FileKindSize
README.mdmarkdown1004 B
SKILL.mdskill md33.5 KB
intermediate/operation_candidates.jsonconfig8.2 KB
references/R1-source-evidence.mdmarkdown10.8 KB
references/R2-pattern-library.mdmarkdown7.5 KB
# d-llm-tool-idempotency-skill

A decision-protocol skill for making side-effectful agent tools idempotent so that a retried LLM tool call (transport timeout, framework resume, model duplicate-emission, or user re-run) becomes a no-op instead of a double-send. The load-bearing premise is that the language model can only promise *at-least-once* delivery, so the tool must engineer *at-most-once* execution via a caller-supplied idempotency key plus dedup at the execution boundary. It is framework-agnostic — covering LangGraph node bodies that re-run on resume, MCP tools, OpenAI/Anthropic tool-calling retries, CrewAI delegated invocations, and direct HTTP wrappers — and ships eight operation models (OP-1..OP-8), four worked dilemma cases, an anti-pattern list, and a cross-framework comparison table. Every load-bearing claim is traced to a real source (Stripe idempotency docs, AWS SQS/S3, PostgreSQL, Temporal, the microservices saga pattern, and the sibling LangGraph SOP) in `references/`.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall