Borrowing it
Nothing to install: this file belongs to suisya-systems/claude-org-ja. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suisya-systems/claude-org-ja/main/.claude/skills/org-conveyor/SKILL.mdgit clone --depth 1 https://github.com/suisya-systems/claude-org-jaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/suisya-systems/claude-org-ja/org-conveyor)<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/org-conveyor"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/org-conveyor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/org-conveyor"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/org-conveyor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 105 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What 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 5.1 | $0.00236 | $0.07436 |
| Opus 5 | $0.00118 | $0.03718 |
| Sonnet 5 | $0.00047 | $0.01487 |
| Haiku 4.5 | $0.00024 | $0.00744 |
Grade A, and why
org-conveyor 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 11d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
org-conveyor: 承認スコープ内自走ループ（ベルトコンベア）
窓口が人間から 承認スコープの輪郭 を受け取り、それを機械契約として articulate したうえで、
その内側を triage → /org-delegate → worker iteration → Codex round → verify（applicable なら必須）→ push → gh pr create → pr-watch CI 監視 → CI green まで 完了駆動で自走 し、PR ごとに
merge gate で必ず停止 する。人間は「レビュー待ち PR のキュー」を順次 merge するだけになる。
本スキルは 薄い orchestrator であって、実作業の機構は既存スキルに委譲する。本スキルが固有に持つのは (1) 承認スコープ契約の articulate と gate、(2) 完了駆動ループとバックプレッシャー、(3) 観測可能性、 (4) 機械的退出条件 の 4 つだけ。受信モデル・ack・push/PR/CI・escalation の機構は下記スキルを呼ぶ:
- triage:
/work-discovery（propose-only / 候補生成） - 派遣:
/org-delegate（Step 0〜、レーン選択・派遣・受信モデル・ack・監視） - 検証:
/verify（Claude Code 組込みスキル。app を起動して実行ビヘイビアを観測する。app + 変更が居る worker の worktree 内で worker が実行する）+.claude/skills/org-conveyor/references/verify-evidence.md（conveyor 側の applicability classifier + エビデンス転記） - PR:
/org-pull-request（push / PR / CI 監視 / レビューループ / マージ後クローズ） - 判断仰ぎ:
/org-escalation（worker escalation を人間へ）
位置づけ（他ループ系との差分）
| skill | 駆動 | 停止条件 | 人間ゲート |
|---|---|---|---|
/loop |
時間駆動 | なし（間隔ごとに再実行） | なし |
/work-discovery |
イベント / 手動 | 候補提示で hard stop（propose-only） | 候補ごとに人間が番号選択 |
/org-delegate |
単発委譲 | escalation 境界で人間に戻る | 派遣ごと / escalation ごと |
/org-conveyor |
完了駆動ループ | PR ごとに merge gate で halt / 退出条件 | 起動時のスコープ承認（1 回）+ merge ごと |
/org-conveyor は /work-discovery の per-candidate 人間選択を、起動時に 1 回だけ取る「承認スコープ契約」
へ畳み込んだものである。スコープ契約の内側では候補を再質問なしで自動投入し、スコープ外の候補は scope 縁として
投入せず halt する。これが propose-only / hard-stop の /work-discovery との本質的な差分。
不変条件（非交渉 / 破ってはならない）
- INV-1 merge 承認は人間 gate: スコープ契約は dispatch〜CI 監視を事前承認できるが、merge は決して事前承認できない。
CI green に到達したら必ず停止し、PR を人間へ提示して merge を仰ぐ（
feedback-merge-approval/feedback-no-overgate-after-decisionの「不可逆点でのみ再承認」）。bare「OK」を merge 承認と解釈しない。 - INV-2 scope 境界に触れたら必ず halt: スコープ契約の述語に合致しない候補・判断・差分が現れたら、自走を止めて
/org-escalation経由で人間に上げる（feedback-no-stopgap/ 場当たり継続をしない）。 - INV-3 worker からの judgment escalation は人間へ: worker の「判断仰ぎ」「承認を仰ぎ」「スコープ拡張」「ブロッカー」は
窓口が一次承認せず
/org-escalationで人間へ。conveyor は escalation を自動判断しない。 - INV-4 propose-only の継承: 候補生成は
/work-discovery（決定的ツール）に委ね、conveyor は その出力をスコープ契約で gate するだけ。候補の中身を自前調査・実装しない。 - INV-5 起動主体は窓口のみ: 委譲済み worker は本スキルを起動しない（「1 worker = 1 task = 1 scope」原則。
CLAUDE.md「役割の境界」）。 - INV-6 merge 自動化・escalation 自動判断・
/loop置換をしない（Non-goals 節）。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 250 lines · 236 tokens per session scan A d88423d8bbc1
org-conveyor is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 5d ago), licensed MIT. It adds 236 tokens to every session and 7,436 once invoked, about $0.0012 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 skills, from other repositories
orch
AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.
board
Read and write the workspace BOARD.md (shared task board for agents + Val). Wraps bin/board, a small Python CLI that preserves the markdown schema and appends to the activity log automatically. Use this whenever an agent proposes, claims, or finishes work that should be visible to the rest of the roster.
ai-agent-job-marketplace
The job marketplace where bots hire bots. Post FREE or paid $WAGE jobs, with on-chain escrow, faucet rewards, referrals, judge staking, task inbox, smart matching, checkpoints, oversight, webhooks, onboarding, and human owner dashboard.
agent-freelance-bounty-marketplace
Earn USDC completing bounties, post jobs, join multi-agent raids, build reputation, rank up. AI agent freelance marketplace with x402 escrow on Solana. Free SOL airdrop on signup. Guilds, ranks, vouching, disputes, Castle Town, leaderboard.
agent-job-marketplace-with-bidding
Agent-to-agent marketplace MVP. Agents post jobs, bid, contract, submit deliverables, and leave reviews. Payments are off-platform (crypto) in v1.
dos-dispatch-loop
Run recurring dos-dispatch cycles, switching to dos-replan when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.