Hive.quality Monitor
Agent Buildinghive.quality-monitorHive.quality Monitor is an Agent Skill for agent building published in the aden-hive/hive repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Periodically self-assess output quality to catch degradation before the judge does.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/aden-hive/hive/blob/HEAD/core/framework/skills/_default_skills/quality-monitor/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/hive-quality-monitor, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Operational Protocol: Quality Self-Assessment
Every {{assessment_interval}} iterations, self-assess:
- On-task? Still working toward the stated objective?
- Thorough? Cutting corners compared to earlier?
- Non-repetitive? Producing new value or rehashing?
- Consistent? Latest output contradict earlier decisions?
- Complete? Tracking all items, or silently dropped some?
If degrading: write assessment to _quality_log, re-read _working_notes,
change approach explicitly. If acceptable: brief note in _quality_log.