polish-beads

Polishing pass over all open beads. Run 4–6 times. "Check your beads N times, implement once." Use after plan-to-beads and between refinement rounds.

Jump to install

Repository: hoangsonww/Forge-Agentic-Coding-CLI
Last source activity: April 21, 2026 at 20:38
Detected SKILL.md language: English
Stars: 22
Forks: 9

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/hoangsonww/Forge-Agentic-Coding-CLI --skill polish-beads

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

name	polish-beads
description	Polishing pass over all open beads. Run 4–6 times. "Check your beads N times, implement once." Use after plan-to-beads and between refinement rounds.

Use the verbatim prompt at .flywheel/prompts/polish-beads.md.

Each round, verify:

Self-containment — a fresh agent can execute without the plan.
Dependencies — depends_on is correct; no missing edges.
Tests — concrete obligations with logging expectations.
Coverage — cross-reference vs .flywheel/plans/*.md.
Duplicates — merge overlapping beads (see dedupe-beads prompt).
Forge invariants — permission gate, LEGAL_TRANSITIONS, UI < 120KB, provider probe ~1.5s.

Stop when two consecutive rounds produce only small corrective edits. If polishing has flatlined after 3 rounds, switch to a fresh session and .flywheel/prompts/fresh-eyes.md.

Final round: run through a different model (e.g. switch Claude ↔ Codex). Different models catch different things.

Back to search Back to installation

deep-review

Deep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses. Run every 30–60 min during active implementation.

2026-04-21

flywheel

Overview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.

2026-04-21

landing

End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.

2026-04-21

View all from this repository

name	polish-beads
description	Polishing pass over all open beads. Run 4–6 times. "Check your beads N times, implement once." Use after plan-to-beads and between refinement rounds.

Use the verbatim prompt at .flywheel/prompts/polish-beads.md.

Each round, verify:

Self-containment — a fresh agent can execute without the plan.
Dependencies — depends_on is correct; no missing edges.
Tests — concrete obligations with logging expectations.
Coverage — cross-reference vs .flywheel/plans/*.md.
Duplicates — merge overlapping beads (see dedupe-beads prompt).
Forge invariants — permission gate, LEGAL_TRANSITIONS, UI < 120KB, provider probe ~1.5s.

Stop when two consecutive rounds produce only small corrective edits. If polishing has flatlined after 3 rounds, switch to a fresh session and .flywheel/prompts/fresh-eyes.md.

Final round: run through a different model (e.g. switch Claude ↔ Codex). Different models catch different things.

polish-beads

Source facts

Install options

Review the source files

More from this repository

More from this repository