SIG audit loop
SkillDev toolsLets your agent iteratively improve code maintainability, keeping only changes that measurably improve it without regressions.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the SIG audit loop skill
About this capability
Iteratively improve Fallow maintainability using measured SIG audit deltas, retaining only changes that improve the targeted property without regressions.
What this skill tells your AI
The instructions your AI receives, as published by fallow-rs/fallow in .agents/skills/sig-audit-loop/SKILL.md and read by ahel’s review.
- Run
sig-auditand select one weak property. - Identify a bounded structural change with a measurable expected effect.
- Measure before, implement, and measure after with identical settings.
- Keep the change only when the target improves and verification remains green.
- Repeat until the target is met or further changes have no credible benefit.
- Run
reviewbefore proposing the final result.
Never combine unrelated cleanup into one measurement iteration.
Signals
- GitHub stars
- 5k
- Forks
- 158
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
sig-audit-loop- Source
- github.com/fallow-rs/fallow