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 commands/xcodethink/open-claude-code-skills/pb-capturegit clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsWrote 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/commands/xcodethink/open-claude-code-skills/pb-capture)<a href="https://agentmods.dev/commands/xcodethink/open-claude-code-skills/pb-capture"><img src="https://agentmods.dev/badge/commands/xcodethink/open-claude-code-skills/pb-capture.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 | $0.00033 | $0.00467 |
| Opus 5 | $0.00016 | $0.00234 |
| Sonnet 5 | $0.00007 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
pb-capture 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 4d 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.
What it actually says
pb-capture — 经验收录通路触发器
用户输入 /pb-capture $ARGUMENTS 表示要把一段可复用的通用指令经验沉淀成 playbook 模板。
立刻读取并完整加载:
~/.claude/prompts/lib/09-元指令/收录通路.md
按其"行为契约"段严格执行,核心:
- 先判边界:只收"通用可复用指令模板"。属于记忆层(
/lesson)、协议演化( lesson-loop)、或 负责人 个人风格(<handle>-personal/)的经验 → 一句话指向对应入口,本通路止步。 - 提炼草稿(主 Claude 亲自写,符合 lib frontmatter schema)。
- 查重:扫
index.yaml的 triggers/title,近似已有 → 建议"更新现有模板"而非新增。 - 去敏感:通用库铁律,沿用
/lesson去敏感清单;清理不掉 → 改投<handle>-personal/。 - 落候选暂存区
prompts/candidates/<id>.md(纯新增,零风险),给用户看。 - 晋级入库必须等用户确认 diff:列
index.yaml追加 + 文件移入lib/的 diff → 等 "yes" → 入库 → 跑prompts/scripts/build-library.sh重建LIBRARY.md。
核心契约:candidates/ 是纯新增缓冲;任何对 index.yaml / lib/ 的写入前必有 diff + 用户 yes,零静默改库;不阻塞会话主线(出问题退回手动)。
参数: $ARGUMENTS
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.
- 4d ago First seen · 25 lines · 33 tokens per session scan A 07d403805016
pb-capture is a command published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 33 tokens to every session and 467 once invoked, about $0.0002 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 commands, from other repositories
memstack-search
Search MemStack memory for past sessions, insights, and project context.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
memory-consent
Grant or revoke consent for session-end auto-memorize. Usage: /memory-consent yes|no|ask.
learn
Learn Claude Code best practices and capture lessons into persistent memory.
record
Record a new architectural decision into project memory.
review
Review the current diff against project memory.