release-check
193hoangsonww/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.
22 16d ago A 30 tokens
original MIT
verify
194hoangsonww/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.
22 16d ago A 33 tokens
original MIT
bead-polisher
195hoangsonww/Forge-Agentic-Coding-CLI
Agent Claude Code
Polishes .beads/beads.jsonl in isolated context. Runs the full polish loop (self-containment, dependencies, test obligations, coverage vs plan, duplicates, Forge invariants) and returns a focused report. Use when you want to burn a polish round without filling the main conversation.
22 16d ago A 64 tokens
original MIT
code-reviewer
196hoangsonww/Forge-Agentic-Coding-CLI
Agent Claude Code
Reviews Forge TypeScript changes for correctness, security, sandbox/permission coverage, state-machine integrity, and test adequacy. Invoke for any non-trivial diff before merge.
22 16d ago A 38 tokens
original MIT
docs-auditor
197hoangsonww/Forge-Agentic-Coding-CLI
Agent Claude Code
Audits Forge documentation for drift against the code. Checks that README counts, ARCHITECTURE hot paths, SETUP env vars, and INSTALL instructions still match reality. Read-only.
22 16d ago A 42 tokens
original MIT
plan-synthesizer
198hoangsonww/Forge-Agentic-Coding-CLI
Agent Claude Code
Reads multiple competing markdown plans from .flywheel/plans/ and synthesizes a best-of-all-worlds hybrid. Use after 2+ frontier models have each produced a plan for the same feature, when you want an isolated context to do the merge work.
22 16d ago A 58 tokens
original MIT
skill-refiner
199hoangsonww/Forge-Agentic-Coding-CLI
Agent Claude Code
Meta-skill agent. Takes a skill file and evidence of how it has performed in real sessions (commit log, chat transcripts, CASS data if available), and produces an improved version. Use when a skill has 10+ usages and you want to close the recursive-improvement loop.
22 16d ago A 62 tokens
original MIT
test-runner
200hoangsonww/Forge-Agentic-Coding-CLI
Agent Claude Code
Runs the Forge test suite and analyses failures. Isolated context so full vitest output does not pollute the main conversation. Returns a focused summary.
22 16d ago A 34 tokens
original MIT
fix-issue
201hoangsonww/Forge-Agentic-Coding-CLI
Command Claude Code
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".
22 16d ago A 0 tokens
original MIT
metrics
202hoangsonww/Forge-Agentic-Coding-CLI
Command Claude Code
!bash scripts/metrics.sh.
22 16d ago A 0 tokens
original MIT
hoangsonww/Forge-Agentic-Coding-CLI
Settings file Claude Code
Agent settings declaring 40 allowed tools.
22 16d ago F
tokens not measured
original MIT
de-slopify
204hoangsonww/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.
22 16d ago A 43 tokens
original MIT
dedupe-beads
205hoangsonww/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.
22 16d ago A 36 tokens
original MIT
fresh-eyes
206hoangsonww/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.
22 16d ago A 40 tokens
original MIT
idea-wizard
207hoangsonww/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.
22 16d ago A 37 tokens
original MIT
plan-synthesize
208hoangsonww/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/.
22 16d ago A 40 tokens
original MIT
forge-core
209hoangsonww/Forge-Agentic-Coding-CLI
Cursor rule Cursor
Core Forge project conventions — always applied.
22 16d ago A 601 tokens
original MIT
hoangsonww/Forge-Agentic-Coding-CLI
Cursor rule Cursor
Model, agent, and core-loop rules.
22 16d ago A 0 tokens
original MIT
security
211hoangsonww/Forge-Agentic-Coding-CLI
Cursor rule Cursor
Security rules (non-negotiable).
22 16d ago A 0 tokens
original MIT
testing
212hoangsonww/Forge-Agentic-Coding-CLI
Cursor rule Cursor
Testing rules for vitest suite.
22 16d ago A 0 tokens
original MIT
tools
213hoangsonww/Forge-Agentic-Coding-CLI
Cursor rule Cursor
(none|read|write|network|exec) and risk (low|medium|high|critical). These drive the permission classifier — be honest.
22 16d ago A 0 tokens
original MIT
typescript
214hoangsonww/Forge-Agentic-Coding-CLI
Cursor rule Cursor
TypeScript style rules, scoped to .ts files.
22 16d ago A 0 tokens
original MIT
ui
215hoangsonww/Forge-Agentic-Coding-CLI
Cursor rule Cursor
UI/dashboard rules — vanilla JS, no frameworks.
22 16d ago A 0 tokens
original MIT
hoangsonww/Forge-Agentic-Coding-CLI
Instructions file CodexOpenCode
Instructions for hoangsonww/Forge-Agentic-Coding-CLI, covering agents.md, 1. project identity, 2. commands you'll run, 3. layout and 4. rules.
22 16d ago A 2,033 tokens
original MIT