/fresh-eyes — break the local minimum
SkillAI & modelsReset review context when bead polishing or code review has flatlined. Requires starting a brand-new Claude / Codex session. Use when you're seeing the same small edits round after round.
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 /fresh-eyes — break the local minimum skill
What this skill tells your AI
The instructions your AI receives, as published by hoangsonww/forge-agentic-coding-cli in .claude/skills/fresh-eyes/SKILL.md and read by ahel’s review.
When a session has accumulated too many assumptions, fresh eyes beat tired eyes. Context exhaustion can feel like convergence.
Prerequisite
Start a new Claude Code or Codex session. Don't just /clear.
Two-step prompt
Send, in order, the two prompts at
.flywheel/prompts/fresh-eyes.md:
- First, a deep context load (AGENTS.md + CLAUDE.md + FLYWHEEL.md + README.md + code investigation).
- Then, a review of
.beads/beads.jsonlagainst.flywheel/plans/<PLAN>.md.
When this operator pays off most
- Bead polishing flatlined after 3–4 rounds.
- Deep code review keeps finding the same class of bug.
- A major architectural decision feels locked in but nobody remembers justifying it.
After
If the fresh session finds new issues → back to /polish-beads.
If it comes back clean → you're genuinely at convergence. Proceed.
Signals
- GitHub stars
- 22
- Forks
- 9
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
fresh-eyes-hoangsonww- Source
- github.com/hoangsonww/forge-agentic-coding-cli