plan

Start a new Flywheel planning round. Produce initial markdown plan, route to competing frontier models, synthesize hybrid, refine 4–5×. Use before any coding begins on a new feature.

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 plan

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	plan
description	Start a new Flywheel planning round. Produce initial markdown plan, route to competing frontier models, synthesize hybrid, refine 4–5×. Use before any coding begins on a new feature.

Plan space. Before any code, before any beads.

Create .flywheel/plans/<YYYY-MM-DD>-<slug>.md.
Copy .flywheel/prompts/plan-initial.md as the prompt template. Fill in intent, workflows, and feature-specific constraints.
Send independently to 3–4 frontier models (GPT Pro, Opus, Gemini Deep Think, Grok Heavy). Save each output separately: <date>-<slug>-<model>.md.
Synthesize: use .flywheel/prompts/plan-synthesize-best-of-all-worlds.md with GPT Pro to produce a hybrid plan (<date>-<slug>-hybrid.md).
Apply diffs in Claude Code / Codex with .flywheel/prompts/plan-integrate-synthesis.md.
Refine 4–5× in fresh GPT Pro conversations using .flywheel/prompts/plan-refine.md. Stop when suggestions become small and corrective.

Plans at 3k–6k lines are normal and correct. When stable, run the plan-to-beads skill.

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	plan
description	Start a new Flywheel planning round. Produce initial markdown plan, route to competing frontier models, synthesize hybrid, refine 4–5×. Use before any coding begins on a new feature.

Plan space. Before any code, before any beads.

Create .flywheel/plans/<YYYY-MM-DD>-<slug>.md.
Copy .flywheel/prompts/plan-initial.md as the prompt template. Fill in intent, workflows, and feature-specific constraints.
Send independently to 3–4 frontier models (GPT Pro, Opus, Gemini Deep Think, Grok Heavy). Save each output separately: <date>-<slug>-<model>.md.
Synthesize: use .flywheel/prompts/plan-synthesize-best-of-all-worlds.md with GPT Pro to produce a hybrid plan (<date>-<slug>-hybrid.md).
Apply diffs in Claude Code / Codex with .flywheel/prompts/plan-integrate-synthesis.md.
Refine 4–5× in fresh GPT Pro conversations using .flywheel/prompts/plan-refine.md. Stop when suggestions become small and corrective.

Plans at 3k–6k lines are normal and correct. When stable, run the plan-to-beads skill.

plan

Source facts

Install options

Review the source files

More from this repository

More from this repository