← All skills

agentsop-llm-tool-idempotency

100 / 100 · Low risk

Fine to try.

By agentsope/SkillAlchemy (GitHub) · productivity · 469 stars · scanned at commit 955562e

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 d…

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'agentsop-llm-tool-idempotency' ] || [ -L ~/.agents/skills/'agentsop-llm-tool-idempotency' ]; then echo 'A skill folder named agentsop-llm-tool-idempotency already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/agentsope/SkillAlchemy' "$d" && git -C "$d" checkout --quiet '955562e4416c483da946e9c95a1c3974ac52df3c' -- 'skills/agentsop-llm-tool-idempotency' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/agentsop-llm-tool-idempotency' ~/.agents/skills/'agentsop-llm-tool-idempotency' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'agentsop-llm-tool-idempotency' ~/.claude/skills/'agentsop-llm-tool-idempotency' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for agentsope/SkillAlchemy shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/agentsope/SkillAlchemy.svg)](https://zalavijaysinh.github.io/skilltrust/repos/agentsope/SkillAlchemy/)

Score history