hoangsonww/Forge-Agentic-Coding-CLI

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Scaffold a new Forge subagent (planner/architect/executor/reviewer/debugger/memory-style).

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Scaffold a new model provider for Forge — class, registry wiring, providerEnum entry, local-catalog classification, router check, and a unit test with mocked transport.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Scaffold a new Forge tool end-to-end — implementation, registration, permission/risk metadata, sandbox routing, and a unit test.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Systematic debugging playbook for the Forge agentic loop (src/core/loop.ts and src/agents/executor.ts). Use when a task is stuck, looping, or emitting wrong tool calls.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

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

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

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

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

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.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Translate a polished markdown plan into self-contained beads in .beads/beads.jsonl. Every bead must be executable without reopening the plan. Use after the plan has converged.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

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.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

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.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Break the spell of local productivity. Ask whether completing all open beads actually closes the gap to the project goal. Use at milestones or when busy agents feel directionally off.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Pre-release checklist for Forge — verify, version bump, changelog, docs, docker build, smoke test. Run before tagging v.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Run Forge's canonical verification chain (format:check + lint + typecheck + build + test). Use before claiming any task complete or opening a PR.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Remove telltale AI-writing patterns from README, docs, and user-facing text. Must be done line-by-line, manually. No regex. Use after agents write any user-visible prose.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Merge duplicate or excessively overlapping beads in .beads/beads.jsonl into canonical ones. Run after any batch where 20+ new beads were created.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Reset 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.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

30 → 5 → 15 funnel for brainstorming new features on the existing Forge codebase. Use when adding capability to a mature install, not for greenfield.

hoangsonww/Forge-Agentic-Coding-CLI

Skill Claude CodeCodex

Synthesize competing plans from multiple frontier models into a single best-of-all-worlds hybrid. Use after /plan has produced 2+ competing plans in .flywheel/plans/.