メニュー
Implement — Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/thiagofernandes1987-create/APEX --skill agenthubコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Token-aware reasoning workflow with real tools: picks an operating mode to control cost, runs a structured pipeline (decompose → validate → verify → snapshot), and gives Claude Program-of-Thought, RK4/Euler, a code gate, and a safe skill router. Use when: multi-step or high-stakes tasks, real math, precise computation, audits, or the user mentions APEX, PoT, pipeline, or scientific mode.
**v00.33.0**: Ingested from antigravity-awesome-skills community repo
run multiple local CLI agents in parallel (separate tmux sessions)
SOC 職業分類に基づく
SKILL.md を表示中
| name | agenthub |
| description | Implement — Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric |
| license | MIT |
| metadata | {"version":"2.1.2","author":"Alireza Rezvani","category":"engineering","updated":"2026-03-17T00:00:00.000Z"} |
| executor | HYBRID |
| skill_id | engineering.cs-engineering.agenthub |
| status | ADOPTED |
| security | {"level":"standard","pii":false,"approval_required":false} |
| anchors | ["engineering","git","agent"] |
| input_schema | [{"name":"code_or_task","type":"string","description":"Code snippet, script, or task description to process","required":true}] |
| output_schema | [{"name":"result","type":"string","description":"Primary output from agenthub"}] |
Spawn N parallel AI agents that compete on the same task. Each agent works in an isolated git worktree. The coordinator evaluates results and merges the winner.
| Command | Description |
|---|---|
/hub:init | Create a new collaboration session — task, agent count, eval criteria |
/hub:spawn | Launch N parallel subagents in isolated worktrees |
/hub:status | Show DAG state, agent progress, branch status |
/hub:eval | Rank agent results by metric or LLM judge |
/hub:merge | Merge winning branch, archive losers |
/hub:board | Read/write the agent message board |
/hub:run | One-shot lifecycle: init → baseline → spawn → eval → merge |
When spawning with --template, agents follow a predefined iteration pattern:
| Template | Pattern | Use Case |
|---|---|---|
optimizer | Edit → eval → keep/discard → repeat x10 | Performance, latency, size |
refactorer | Restructure → test → iterate until green | Code quality, tech debt |
test-writer | Write tests → measure coverage → repeat | Test coverage gaps |
bug-fixer | Reproduce → diagnose → fix → verify | Bug fix approaches |
Templates are defined in references/agent-templates.md.
Trigger phrases:
The main Claude Code session is the coordinator. It follows this lifecycle:
INIT → DISPATCH → MONITOR → EVALUATE → MERGE
Run /hub:init to create a session. This generates:
.agenthub/sessions/{session-id}/config.yaml — task config.agenthub/sessions/{session-id}/state.json — state machine.agenthub/board/ — message board channelsRun /hub:spawn to launch agents. For each agent 1..N:
.agenthub/board/dispatch/isolation: "worktree"Run /hub:status to check progress:
dag_analyzer.py --status --session {id} shows branch stateprogress/ channel has agent updatesRun /hub:eval to rank results:
Run /hub:merge to finalize:
git merge --no-ff winner into base branchgit tag hub/archive/{session}/agent-{i}Each subagent receives this prompt pattern:
You are agent-{i} in hub session {session-id}.
Your task: {task description}
Instructions:
1. Read your assignment at .agenthub/board/dispatch/{seq}-agent-{i}.md
2. Work in your worktree — make changes, run tests, iterate
3. Commit all changes with descriptive messages
4. Write your result summary to .agenthub/board/results/agent-{i}-result.md
5. Exit when done
Agents do NOT see each other's work. They do NOT communicate with each other. They only write to the board for the coordinator to read.
hub/{session-id}/agent-{N}/attempt-{M}
YYYYMMDD-HHMMSS)Frontier = branch tips with no child branches. Equivalent to AgentHub's "leaves" query.
python scripts/dag_analyzer.py --frontier --session {id}
The DAG is append-only:
Location: .agenthub/board/
| Channel | Writer | Reader | Purpose |
|---|---|---|---|
dispatch/ | Coordinator | Agents | Task assignments |
progress/ | Agents | Coordinator | Status updates |
results/ | Agents + Coordinator | All | Final results + merge summary |
---
author: agent-1
timestamp: 2026-03-17T14:30:22Z
channel: results
parent: null
---
## Result Summary
- **Approach**: Replaced O(n²) sort with hash map
- **Files changed**: 3
- **Metric**: 142ms (baseline: 180ms, delta: -38ms)
- **Confidence**: High — all tests pass
{seq:03d}-{author}-{timestamp}.mdBest for: benchmarks, test pass rates, file sizes, response times.
python scripts/result_ranker.py --session {id} \
--eval-cmd "pytest bench.py --json" \
--metric p50_ms --direction lower
The ranker runs the eval command in each agent's worktree directory and parses the metric from stdout.
Best for: code quality, readability, architecture decisions.
The coordinator reads each agent's diff (git diff base...agent-branch) and ranks by:
Run metric first. If top agents are within 10% of each other, use LLM judge to break ties.
init → running → evaluating → merged
→ archived (if no winner)
State transitions managed by session_manager.py:
| From | To | Trigger |
|---|---|---|
init | running | /hub:spawn completes |
running | evaluating | All agents return |
evaluating | merged | /hub:merge completes |
evaluating | archived | No winner / all failed |
The coordinator should act when:
| Signal | Action |
|---|---|
| All agents crashed | Post failure summary, suggest retry with different constraints |
| No improvement over baseline | Archive session, suggest different approaches |
| Orphan worktrees detected | Run session_manager.py --cleanup {id} |
Session stuck in running | Check board for progress, consider timeout |
# Copy to your Claude Code skills directory
cp -r engineering/agenthub ~/.claude/skills/agenthub
# Or install via ClawHub
clawhub install agenthub
| Script | Purpose |
|---|---|
hub_init.py | Initialize .agenthub/ structure and session |
dag_analyzer.py | Frontier detection, DAG graph, branch status |
board_manager.py | Message board CRUD (channels, posts, threads) |
result_ranker.py | Rank agents by metric or diff quality |
session_manager.py | Session state machine and cleanup |
Implement — Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric
Use this skill when the task requires agenthub capabilities.
If this skill fails to produce the expected output: (1) verify input completeness, (2) retry with more specific context, (3) fall back to the parent workflow without this skill.