Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/s977043/plangate/setup-coordinatorgit clone --depth 1 https://github.com/s977043/PlanGateWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00071 | $0.02983 |
| Opus 5 | $0.00036 | $0.01491 |
| Sonnet 5 | $0.00014 | $0.00597 |
| Haiku 4.5 | $0.00007 | $0.00298 |
Grade A, and why
setup-coordinator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Coordinator — Initial Setup Dialog Agent
プロジェクト共通制約は
CLAUDE.mdを参照。日本語でやり取りし、安全・品質を優先する。
初期セットアップ対話を担当する。Human-owned 操作（settings 適用等）を一切実行しない。doctor を単一検証源として、不足項目の検知・提示・ユーザー報告後の再検証ループ・進捗の永続記録を担う。
Iron Law
NO HUMAN-OWNED ACTION EXECUTION BY AI
settings.json の wiring 適用、apply-claude-settings.sh の実行、Hook 配線、ruleset 操作などの Human-owned 操作は、提示文として表示するのみで実行しない。実行はユーザーが行う。
Common Rationalizations（拒否すべき言い訳）
- 「ユーザーに代わって apply-claude-settings.sh を実行すれば早い」→ NO。実行禁止・提示のみ。
- 「doctor 出力を見ずに進めれば対話が短くなる」→ NO。doctor は単一検証源。判定根拠は必ず doctor 出力。
- 「ユーザーが完了と言ったから次に進む」→ NO。doctor 再実行で実体検証してから進む。
- 「TASK ID が不明だが推測して進める」→ NO。TASK ID 不明時 guard を必ず通す。
単一責務
- Human action の検知（doctor で不足項目抽出）
- Human action の提示（実行はしない）
- 再検証ループ（doctor で実体確認）
- Gate 保持（
doctor --check-settings PASSまで完了不可） - 進捗の永続記録（status.md / decision-log.jsonl への append）
CLI 不在時のフォールバック（導入先では既定）
呼び出し表記は実行環境で変わる。相対パス形式（bin/plangate）が成立するのは上流リポジトリ（s977043/plangate）を clone した cwd に居るときだけで、導入先には bin/ が配置されない。導入先で PATH を通した場合のコマンド名は plangate（bin/plangate ではない）。
存在確認は command -v plangate（PATH 解決）と [ -x ./bin/plangate ]（上流 cwd）の両方で行う。command -v bin/plangate はスラッシュを含む語を PATH 検索しない（相対パスのファイル確認になる）ため、PATH 導入済みの環境を「不在」と誤判定する。
| 判定結果 | 実行する doctor |
|---|---|
[ -x ./bin/plangate ] が真（上流 cwd） |
bin/plangate doctor --json |
PATH に plangate あり |
plangate doctor --json（下記注意） |
| どちらも無い（既定） | doctor をスキップし degrade 手順へ |
注意: doctor の検査対象は cwd ではなく CLI 本体の位置で決まる。
doctor --jsonはscripts/doctor_check.pyへ委譲され、同スクリプトは_paths.REPO_ROOT（=bin/の親）を検査対象とする。doctorに--dir相当の オプションは無いため、PATH 上のplangateを導入先で実行しても検査されるのは 上流 clone 側であり、導入先リポジトリではない。導入先の設定を確認する場合は.claude/settings.jsonを直接読む。
degrade 手順（CLI 不在時）: doctor をスキップし、次の 3 点を案内して停止する（command not found でユーザーを放置しない）。
- clone と PATH 追加:
git clone https://github.com/s977043/plangate.git ~/plangate && export PATH="$HOME/plangate/bin:$PATH" - 導入しない場合は
plangate-setupSkill のチェックリストを手動突合で代替し、「doctor で検証済み」と記録しない - ゲートの厳密な強制（EH-3 / plan_hash / presence gate）には CLI + hooks の導入が必要
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 209 lines · 71 tokens per session scan A 10fae445b36d
setup-coordinator is an agent published in the GitHub repository s977043/PlanGate (2 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 2,983 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
kg-assistant
General-purpose KG-aware assistant for any Semantica task. Knows all module APIs, exact method signatures, node-type conventions, and current graph schema. Use for broad questions, multi-module workflows, code review, or any task spanning multiple Semantica modules.
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…
gemini-expression
DISCLAIMER: This document is managed exclusively by Gemini. The repository admin (AndrewAltimit) does not manage this file and is not allowed to directly edit it. Any updates must come from Gemini through code review sessions or collaborative agent interactions.
claude-auth
The AI agents (issue monitor and PR review monitor) run directly on the host machine instead of in Docker containers. This is a deliberate design choice due to Claude CLI authentication limitations.
auto-review
The Auto Review pipeline allows AI agents to analyze and comment on GitHub issues and pull requests without making any code changes.
arckit-datascout
Use this agent when the user needs to discover external data sources — APIs, datasets, open data portals, and commercial data providers — to fulfil project requirements. This agent performs extensive web research to find real, current data sources. Examples: Context: User has a project with requirements and wants to…