← All skills

agentsop-bounded-loop

100 / 100 · Low risk

Fine to try.

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

Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every team relearns expensively: the LM in the loop is NEVER a reliable terminator. Termination must be provided by an explicit counter + exit predicate + stagnation signal + escalation path that live OUTSIDE the LM's control. This is a tool- level, framework-agnostic skill. It maps onto LangGraph (recu…

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-bounded-loop' ] || [ -L ~/.agents/skills/'agentsop-bounded-loop' ]; then echo 'A skill folder named agentsop-bounded-loop 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 "$d" checkout --quiet '955562e4416c483da946e9c95a1c3974ac52df3c' -- 'skills/agentsop-bounded-loop' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/agentsop-bounded-loop' ~/.agents/skills/'agentsop-bounded-loop' && 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-bounded-loop' ~/.claude/skills/'agentsop-bounded-loop' (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