~ / leaderboard / skill / loop-design-check
Skill · #4725
loop-design-check
Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion. Covers machine-decidable goals, loop types, plan/bui
4rigs use it
0%of all rigs
6.8kavg rig context tax
Get it
$ npx degit baksohyeon/mogui-ADE-orchestrator/master-ops/skills/loop-design-check .claude/skills/loop-design-check From the most-starred rig that ships it: baksohyeon/mogui-ADE-orchestrator. Same-named skills in different rigs may differ — review before use.
Often used together with
agent-introspection-debugging · 3agent-self-evaluation · 3codehealth-mcp · 3dev-team · 3dmux-workflows · 3inherit-legacy-style · 3growth-log · 3council · 2continuous-learning-v2 · 2iterative-retrieval · 2
Rigs using loop-design-check (4)
baksohyeon/mogui-ADE-orchestrator
Run one AI agent as the orchestrator of your whole workspace, inside the Orca ADE, on the CLI subscription you already pay for. No API key, no model endpoint. Orca hosts and places every session; the harness dispatches workers under contrac
Orchestrator 2.3k tok · · Q0
AjayIrkal23/agentic-mercy-10x
My complete Claude Code agentic workspace - 200+ curated skills, 9-agent specialist mesh, 3-act /invoke orchestration, enforcement hooks. Clone + one command = full setup.
Orchestrator 11.0k tok · · Q5
siddu1004/SFP
Stop burning 30% of your agent's context on unused skills. 819 curated superpowers across 16 IDEs. One autonomous hive equipping the exact skills you need in 9ms. Take total command—and watch yourself build miracles with your agents as they
Skill Collector 8.6k tok · · Q3
phantanphatdgteam-gif/snagon-dev-mods
Coding-agent harness mod for Claude Code: project memory, safety gate, journal and handoff, setup interview, plus skills, agents and commands.
Skill Collector 5.1k tok · · Q0