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/memory-managernpx skills add cloud99277/KitClaw --skill memory-managergit 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 | $0.00104 | $0.01451 |
| Opus 5 | $0.00052 | $0.00726 |
| Sonnet 5 | $0.00021 | $0.00290 |
| Haiku 4.5 | $0.00010 | $0.00145 |
Grade A, and why
memory-manager 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memory-manager
跨 Agent 持久记忆管理 Skill，基于三层记忆模型（身份层 / 会话层 / 知识层）。
快速开始
检索记忆
# 全层检索
python3 ~/.ai-skills/memory-manager/scripts/memory-search.py "关键词"
# 仅检索 L2 会话层（Whiteboard）
python3 ~/.ai-skills/memory-manager/scripts/memory-search.py "关键词" --layer=L2
# 按项目过滤
python3 ~/.ai-skills/memory-manager/scripts/memory-search.py "关键词" --project=agent-os
# 按领域搜索（仅限 L3，覆盖 config.json）
python3 ~/.ai-skills/memory-manager/scripts/memory-search.py "关键词" --scope=dev # 研发领域
python3 ~/.ai-skills/memory-manager/scripts/memory-search.py "关键词" --scope=content # 内容/社交
python3 ~/.ai-skills/memory-manager/scripts/memory-search.py "关键词" --scope=personal # 个人领域
# 组合使用
python3 ~/.ai-skills/memory-manager/scripts/memory-search.py "关键词" --scope=dev --layer=L3 --json
# 输出 JSON（供其他 skill 机器消费）
python3 ~/.ai-skills/memory-manager/scripts/memory-search.py "关键词" --json
更新记忆
# 从文字中直接写入
python3 ~/.ai-skills/memory-manager/scripts/memory-update.py --from-text "决定使用 JSON 而非 chromadb" --type=decision --project=agent-os
# 从文件中提取（Agent-guided：脚本展示文件内容和提取指令，由 Agent 逐条调用 --from-text 写入）
python3 ~/.ai-skills/memory-manager/scripts/memory-update.py --from-file conversation.md --project=agent-os
# 查看当前 Whiteboard
python3 ~/.ai-skills/memory-manager/scripts/memory-update.py --list
如果你要更方便地把当前任务/对话提炼成 1-3 条 L2 条目，优先用：
python3 ../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
memory-update.py 仍然是底层入口；l2-capture 是更适合日常写入的上层封装。
监听知识库目录
# 安装稳定版 systemd 用户服务（推荐）
bash ~/.ai-skills/memory-manager/scripts/install-knowledge-watch-service.sh
# 启动目录监听
bash ~/.ai-skills/memory-manager/scripts/start-knowledge-watch.sh
# 查看状态
bash ~/.ai-skills/memory-manager/scripts/status-knowledge-watch.sh
# 停止监听
bash ~/.ai-skills/memory-manager/scripts/stop-knowledge-watch.sh
# 卸载稳定版服务
bash ~/.ai-skills/memory-manager/scripts/uninstall-knowledge-watch-service.sh
What ships with it
12 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.
- references/memory-architecture.md 1.1 KB
- references/whiteboard-template.md 1.2 KB
- scripts/ensure-knowledge-frontmatter.py 7.1 KB runs code
- scripts/install-knowledge-watch-service.sh 2.4 KB runs code
- scripts/l2_capture.py 244 B runs code
- scripts/memory-search.py 8.9 KB runs code
- scripts/memory-update.py 11 KB runs code
- scripts/start-knowledge-watch.sh 1.7 KB runs code
- scripts/status-knowledge-watch.sh 1.2 KB runs code
- scripts/stop-knowledge-watch.sh 841 B runs code
- scripts/uninstall-knowledge-watch-service.sh 1.5 KB runs code
- scripts/watch-knowledge-base.py 7.7 KB runs code
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 · 142 lines · 104 tokens per session scan A 5fa4e049fdb7
memory-manager is a skill published in the GitHub repository cloud99277/KitClaw (5 stars, last pushed 4mo ago), licensed MIT. It adds 104 tokens to every session and 1,451 once invoked, about $0.0005 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…