agent-loop
agent-loop is an Execution & autonomous loops skill for AI agents, published by YosemiteCrew in the Yosemite-Crew repository on GitHub. Skillspace rates agent-loop D (62/100) and it passed the safety scan; the rating is based on static analysis only.
Use at the START of any non-trivial task, before delegating to subagents or fanning out, and for any recurring or scheduled autonomous run in this repo. The robust agent work loop - how to orient, plan, act in small batches, verify before calling anything done, coordinate safely across ephemeral worktrees, and stop or hand off cleanly. Applies to every agent (Claude Code, Codex, or any compatible agent).
- Grade
- D
- Quality
- 62 / 100
- Safety
- Passed
- GitHub stars
- 2,021
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 89 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.