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/work-discovery/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/work-discovery)<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/work-discovery"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/work-discovery/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/work-discovery"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/work-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00162 | $0.06641 |
| Opus 5 | $0.00081 | $0.03320 |
| Sonnet 5 | $0.00032 | $0.01328 |
| Haiku 4.5 | $0.00016 | $0.00664 |
Grade A, and why
work-discovery 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 10d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
work-discovery: 次の仕事候補の triage 提示(提案のみ)
open Issue を triage し、依存解決済みの候補を「N 件 + 推奨 1 件」の形で窓口が人間へ提示する。 判定(scan・ランク付け)は決定的ツールが担い、本スキルはその出力を人間可読に整形して見せるだけ。 候補を出したら停止する。着手判断は人間が行う。
- 設計一次参照:
docs/design/work-discovery-triage.md(§5.2 人間可読レンダリング / §6.2 案 B ローカル skill / §7 不変条件 INV-1〜5)。 - 計算層ツール:
tools/work_discovery_scan.py(read-only・副作用ゼロ。本スキルが消費する計算層)。 - repo セット解決ツール:
tools/work_discovery_repos.py(read-only。registry/projects.mdの triage 列(既定 include / 明示 opt-out)とregistry/org-config.mdのtriage_home(既定 off)から scan に渡す--repo owner/repoセットを決定的に導出。設計 §10.4)。 - 本スキルは案 B(手動エントリ)。定常トリガ(dispatcher 拡張)と post-merge 統合は別 Phase(別タスク)。
起動主体とトリガ(厳守)
- 起動できるのは窓口だけ(設計 §6.2)。委譲済みワーカーは本スキルを起動しない。
ワーカーが自タスク外の「次の仕事」探索を起動すると「1 worker = 1 task = 1 scope」を崩すため
(
CLAUDE.mdの役割境界)。 - 常駐
/loopを付けない(設計 §6.2 留意 1)。手動起動、または PR マージ後の proactive next-dispatch のようなイベント起点でのみ走らせる。時間ベースの定常起動は 変化の無い日に提示を汚すため避ける。 - 定常トリガ(worker クローズ)は別案(dispatcher 拡張・別 Phase)の責務であって本スキルではない。
不変条件(破ってはならない / 設計 §7)
- INV-1 propose-only: 本スキルの出力は「候補リスト + 提示」のみ。生成後に停止する。
spawn / delegate / ブランチ作成 / commit / PR / Issue・PR への書き込みを一切しない。
(allowed-tools が repo 解決(
tools/work_discovery_repos.py)と scan(tools/work_discovery_scan.py)の read-only コマンドだけに絞られているのは、この不変条件の宣言的な意図表明であって機械的強制ではない。allowed-toolsは列挙したツールを起動ターンに限って事前承認するフィールドで、列挙外のツールを禁じない (列挙外は通常の permission 設定に従い確認プロンプトが出るだけ)。絞り込みの実利は正路の明示と プロンプト削減であり、正路を外れたときに確認という摩擦が立つこと。不変条件を機械的に強制したい場合はPreToolUseフック(例:.hooks/block-foreground-subagent.sh)を 別途置く。resolver も scan と同じく read-only で、git remote get-urlと任意のgh repo view読み取りのみを 行い、書き込み・spawn・git 変更をしない。) - INV-2 着手判断は人間ゲート必須: 候補の選択は人間のみ。選ばれた候補は
既存の
/org-delegateの Step 0 から通常委譲フローに入る。 本スキルが org-delegate を自分で呼ぶことは禁止。推奨(rank 1)の自動着手も禁止。 - INV-3 自動 commit / 自動 PR をしない: ソースツリー・Issue・PR・git(commit / branch / push)を 一切変更しない。triage 結果をソースに残す運用にする場合も、それは別途人間判断による別タスクであり、本スキルが自動で行わない。
- INV-4 窓口経由: 提示は窓口セッションの会話内で人間へ行う。GitHub 等の人間可視面へ直接書かない。
- INV-5 秘書は調査しない: scan は決定的ツール実行であって「調査」ではない。候補の実現性深掘り・ 設計が要るなら、それは人間ゲートを通った後の委譲ワーカータスク。本スキル内で候補の中身を自前調査・実装しない。
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.
- 10d ago First seen · 190 lines · 162 tokens per session scan A 52f595c8165b
work-discovery is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 4d ago), licensed MIT. It adds 162 tokens to every session and 6,641 once invoked, about $0.0008 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.