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 skills/satoh-y-0323/claude-code-conductor/pattern-statusnpx skills add satoh-y-0323/claude-code-conductor --skill pattern-statusgit clone --depth 1 https://github.com/satoh-y-0323/claude-code-conductorWrote 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/satoh-y-0323/claude-code-conductor/pattern-status)<a href="https://agentmods.dev/skills/satoh-y-0323/claude-code-conductor/pattern-status"><img src="https://agentmods.dev/badge/skills/satoh-y-0323/claude-code-conductor/pattern-status.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01095 |
| Opus 5 | $0.00028 | $0.00548 |
| Sonnet 5 | $0.00011 | $0.00219 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
pattern-status 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 yesterday.
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.
What it actually says
pattern-status
patterns.json の現状を可視化する。読み取り専用 で patterns.json を変更しない。
Step 1: patterns.json を読み込む
.claude/memory/patterns.json を Read する。
ファイルが存在しない、または patterns 配列が空の場合は以下を表示して終了する:
## パターン統計
現在、登録されているパターンはありません。
セッション内で発見したパターンは session ファイルの JSON ブロックに記録され、
セッション終了時に .claude/hooks/stop.py が patterns.json へ統合します。
Step 2: パターンを分類する
各パターンを以下の 4 区分に分類する:
| 区分 | 条件 |
|---|---|
| 昇格済み | promoted: true |
| 昇格候補 | promotion_candidate: true かつ promoted: true でない |
| 蓄積中 | promotion_candidate が false または未設定で、promoted が true でない |
| 期限切れ間近 | registered_date から 25 日以上経過(30 日で自動削除) |
「期限切れ間近」は他区分と排他ではない(蓄積中かつ期限切れ間近 → 両方に表示してよい)。
Step 3: サマリを表形式で表示する
以下の形式で表示する。空のセクションは「(なし)」と書く。
## パターン統計 ({今日の日付})
### 昇格候補({N}件)
| trust | id | description | 登録日 | 経過 |
|---|---|---|---|---|
| 0.85 | example_pattern | パターンの説明 | 2026-04-30 | 5日 |
...
→ `/promote-pattern` で昇格できます。
### 蓄積中({N}件)
| trust | id | description | 登録日 | 観測 |
|---|---|---|---|---|
| 0.33 | another_pattern | パターンの説明 | 2026-05-02 | 1回 |
...
### 昇格済み({N}件)
| id | 昇格先 | 昇格日 | trust |
|---|---|---|---|
| promoted_pattern | rules/promoted/20260503-promoted_pattern.md | 2026-05-03 | 0.90 |
...
### 期限切れ間近(25日以上経過 / 30日で自動削除)({N}件)
| trust | id | 登録日 | 残り日数 |
|---|---|---|---|
| 0.20 | stale_pattern | 2026-04-10 | 5日 |
...
### 信用度別分布
- 0.8 以上: {N}件(昇格候補入り)
- 0.5 〜 0.8: {N}件
- 0.3 〜 0.5: {N}件
- 0.1 〜 0.3: {N}件
合計: {N}件
Step 4: 次のアクションを案内する
表示の最後に、状況に応じた一文を案内する:
| 状況 | 案内 |
|---|---|
| 昇格候補が 1 件以上 | /promote-pattern で昇格できます。 |
| 期限切れ間近が 1 件以上 | あと {N} 日で削除されるパターンがあります。観測されると信用度が上がり、昇格候補になります。 |
| 蓄積中のみで昇格候補なし | 信用度 0.8 以上・登録から 3 日以上で昇格候補になります。 |
| すべて空 | (Step 1 のメッセージで終了済み) |
注意事項
- patterns.json を 絶対に変更しない。読み取り専用のコマンドである
- ファイルの修正・パターンの追加削除は
/promote-patternまたは.claude/hooks/stop.pyの担当 - 経過日数は
registered_date(YYYYMMDD) と今日の日付から計算する
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.
- yesterday First seen · 104 lines · 57 tokens per session scan A f2f385473037
pattern-status is a skill published in the GitHub repository satoh-y-0323/claude-code-conductor (1 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,095 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when (1) a command, tool, API, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
knowledge-spider
Skill "knowledge-spider" from UnicomAI/wanwu, covering 本地知识库技能, when to use (必须使用本技能的场景), 使用原则, 触发词示例 and 执行流程.
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
project-context
Use PowerContext project memory and handoff tools through MCP when continuing prior work, recalling decisions, maintaining durable memory, or transferring work across tasks, sessions, or agents.