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/cloud99277/kitclaw/l2-capturenpx skills add cloud99277/KitClaw --skill l2-capturegit clone --depth 1 https://github.com/cloud99277/KitClawWhat 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 | $0.00087 | $0.01042 |
| Opus 5 | $0.00044 | $0.00521 |
| Sonnet 5 | $0.00017 | $0.00208 |
| Haiku 4.5 | $0.00009 | $0.00104 |
Grade A, and why
l2-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 3d 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
l2-capture
为共享 L2 Whiteboard 提供一个薄封装写入入口。
它做四件事：
- 接收原始文本或已经标注好的候选条目
- 规范成
decision/action/learning - 先做去重和质量检查
- 串行调用
memory-manager完成最终写入
不要用它写 L3 文档；稳定文档仍然进入 Obsidian 知识库。
什么时候用
- 用户明确说“记到 L2 / 写入白板 / 记下这个决策 / 记下这个待办”
- 要从当前任务或对话中提炼 1-3 条共享记忆
- 需要避免直接调用
memory-update.py时的并发与重复问题
快速开始
先 dry-run 看候选条目：
python3 ~/.ai-skills/l2-capture/scripts/l2_capture.py \
--project agent-toolchain \
--from-text "[decision] 共享稳定知识统一落到 20_Knowledge_Base"
第二版也支持从原始总结里自动提炼：
python3 ~/.ai-skills/l2-capture/scripts/l2_capture.py \
--project agent-toolchain \
--from-text "我们决定把共享稳定知识统一放到 20_Knowledge_Base。后续需要单独评估 Git 化方案。实测下来 L3 更适合目录监听自动入库。"
确认后写入：
python3 ~/.ai-skills/l2-capture/scripts/l2_capture.py \
--project agent-toolchain \
--from-text "[decision] 共享稳定知识统一落到 20_Knowledge_Base" \
--apply
支持多条：
python3 ~/.ai-skills/l2-capture/scripts/l2_capture.py \
--project agent-toolchain \
--from-text "
[decision] OpenClaw 私有记忆不覆盖共享事实
[action] 单独评估 20_Knowledge_Base 的 Git 化方案
[learning] L3 适合目录监听自动入库
" \
--apply
如果原始文本只对应一条，给定类型即可：
python3 ~/.ai-skills/l2-capture/scripts/l2_capture.py \
--project agent-toolchain \
--type learning \
--from-text "L3 适合目录监听自动入库；L2 更适合结构化短条目写入。" \
--apply
输入规则
- 优先使用显式标记：
[decision] ...[action] ...[learning] ...
- 也支持：
decision: ...action: ...learning: ...
- 如果只有一条内容，可以配合
--type - 如果没有显式标记，也会尝试自动提炼 1-3 条候选
自动提炼规则
- 优先从一句话里识别
decision / action / learning - 会按关键词和句首信号做启发式分类
- 返回
source_mode=auto和命中的signals - 如果内容太泛、太长，仍然会被过滤或要求你显式标注
默认行为
- 默认是
dry-run - 只有加
--apply才真正写入~/.ai-memory/whiteboard.json - 写入前会读取现有 whiteboard 做重复检查
- 真正落盘时会串行写入，避免多条并发写 whiteboard 失败
和 memory-manager 的分工
memory-manager：底层读写与检索统一入口l2-capture：更方便的 L2 写入入口
需要了解 L2 规则时，读取：
~/.ai-skills/memory-manager/references/whiteboard-template.md
What ships with it
2 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.
- 3d ago First seen · 117 lines · 87 tokens per session scan A 95f926dc6685
l2-capture is a skill published in the GitHub repository cloud99277/KitClaw (5 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 1,042 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…