WenyuChiou

34 mods across 7 repositories, 6.9k stars between them.

WenyuChiou/agent-collab-skills

Plugin Claude Code

6 skills for context-safe multi-agent collaboration: task-splitter, context-budget, output-reconciler, debate, shared-memory, and acceptance-gate. Composes with codex-delegate and pinned-model Claude lanes via bounded .ai task packets (gemini lane deprecated 2026-06-18), .coord context policy, and result.json…

24 1mo ago A tokens not measured original MIT

WenyuChiou/agent-collab-skills

Skill Claude CodeCodex

Use when a multi-agent round needs a pre-merge gate, pre-commit check, verification before push, or a PASS/FAIL decision after reconciliation.

24 1mo ago A 38 tokens original MIT

WenyuChiou/agent-collab-skills

Skill Claude CodeCodex

Use when multi-agent work risks context overflow, memory growth, noisy logs, oversized handoffs, cross-session continuation, or parallel Codex and Gemini execution.

24 1mo ago A 35 tokens original MIT

agent-debate

28

WenyuChiou/agent-collab-skills

Skill Claude CodeCodex

Use when a consequential decision needs adversarial review, opposing agent arguments, a second opinion via debate, or explicit trade-off analysis before implementation.

24 1mo ago A 32 tokens original MIT

WenyuChiou/agent-collab-skills

Skill Claude CodeCodex

Use when multiple agents have completed a round and the user asks to reconcile outputs, compare Codex and Gemini, synthesize run results, identify conflicts, or decide what should be retried.

24 1mo ago A 44 tokens original MIT

WenyuChiou/agent-collab-skills

Skill Claude CodeCodex

Use when a task needs single-agent self-correction across multiple iterations — write plan, execute, critique own output, revise plan, re-execute, until convergence or budget exhausted. Different from agent-debate (which is 2 agents arguing pro vs con); this is 1 agent looping over its own work.

24 1mo ago A 71 tokens original MIT

agent-shared-memory

31

WenyuChiou/agent-collab-skills

Skill Claude CodeCodex

Use when the user asks to update shared memory, initialize multi-agent memory, summarize decisions so far, identify open questions, or prepare a fresh session primer.

24 1mo ago A 36 tokens original MIT

agent-task-splitter

32

WenyuChiou/agent-collab-skills

Skill Claude CodeCodex

Use when the user asks to split a goal across Claude, Codex, or Gemini (gemini requests are rerouted - lane deprecated); plan a multi-agent run; break work into parallel agent tasks; or decompose a large task that needs bounded context handoffs. This is the generic multi-agent task splitter — writes .coord/plan.yml (a…

24 1mo ago A 146 tokens original MIT

session-sweep

33

WenyuChiou/session-sweep

Plugin Claude Code

Sweep up all session artifacts left behind by Claude Code: stale git worktrees, dangling git refs, and orphaned worktree directories. Essential for heavy Claude Code users — each code task creates a full repo copy that persists after the session ends.

2 5mo ago A tokens not measured original MIT

session-sweep

34

WenyuChiou/session-sweep

Skill Claude CodeCodex

Sweep up ALL session artifacts left behind by Claude Code: stale git worktrees, dangling git refs, and orphaned worktree directories. Use this skill whenever the user mentions slow performance, low disk space, too many worktrees, cleanup, maintenance, freeing space, or wants to reduce clutter from Claude Code…

2 5mo ago D 127 tokens original MIT