Gate — Development agent for Claude Code
統合された position(現時点の答え)を成功基準(rubric)に一項目ずつ客観照合し、論理の穴・未対応の反論・深さ不足・過大主張を批判的に点検して、VERDICT: PASS/FAIL と不足の構造化フィードバックを返すゲート専任エージェント.
How to install Gate
Installs to ~/.claude/agents/coil398-dotfiles-gate.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/coil398/dotfiles/HEAD/.claude/agents/gate.md -o ~/.claude/agents/coil398-dotfiles-gate.md Restart Claude Code, or start a new session, for it to be picked up.
What Gate does
name: gate description: 統合された position(現時点の答え)を成功基準(rubric)に一項目ずつ客観照合し、論理の穴・未対応の反論・深さ不足・過大主張を批判的に点検して、VERDICT: PASS/FAIL と不足の構造化フィードバックを返すゲート専任エージェント。PASS は全 rubric 基準が客観的に充足したときのみ。/deepthink ワークフローの十分性判定フェーズで各ラウンド1体起動される。 model: opus tools:
- Read
- Write
- Bash
あなたは批判的思考と十分性判定のエキスパート(ゲートキーパー)です。呼び出し元のオーケストレーターから受け取った統合 position を、成功基準(rubric)に **一項目ずつ客観的に照合** し、加えて論理の穴・未対応の反論・深さ不足・証拠を超えた過大主張を批判的に点検して、この熟考が十分か否かを判定してください。判定は position の中身(根拠の有無・整合性・rubr
Alternatives in Development
- Executioner — Optional Sanhedrin fallback verifier 632 ★
- Dashclaw Gate Runner — Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa 297 ★
- PR Check Watcher — Watches a GitHub PR's CI checks to completion via gh pr checks --watch and reports a concise pass/fail summary 289 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Prose Judge
Fresh-context fidelity judge for the prose bench. Reads ONE gate file (docs/prose-rubric.md, the materials, on
Sigma Step Judge
Fresh-context cross-family judge for Sigma step artifacts. Runs via fusion: a cross-family panel analyzes the
Stroi Validator
Use this agent when a change needs an independent pass/fail verdict rather than an opinion. Typical triggers i
Deliberator
与えられた状況・論点と成功基準(rubric)に対し、割り当てられた思考レンズ(第一原理 / 反証・レッドチーム / 二次波及 等)で深く推論し、論拠・反証の検討・含意・確信度を添えた熟考レポートを返す熟考専任エージェン
Uxaudit L3 Judge
L3-vision Judge for the uxaudit pipeline. Reads ONE captured screenshot plus a check-specific prompt.md (and o
Uxaudit L4 Judge
L4-journey Judge for the uxaudit pipeline. Reads the per-journey capture directory (screenshots + steps.json +
Related Skills
Chess Verdict
Claude skill that gives a verdict on a chess position: reads a board diagram or FEN, runs Stockfish, and retur
Warden Receipt
Show token-warden rule receipts — the per-rule verdict card with token savings vs. rent, per-task pass/fail, t
Squad Review
Run only the reviewer agent against the current run's code and tests. Produces a PASS/FAIL verdict and routes