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 skills add YusenZhang0601/context-canopy --skill second-brain-helpgit clone --depth 1 https://github.com/YusenZhang0601/context-canopyWrote 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/yusenzhang0601/context-canopy/second-brain-help)<a href="https://agentmods.dev/skills/yusenzhang0601/context-canopy/second-brain-help"><img src="https://agentmods.dev/badge/skills/yusenzhang0601/context-canopy/second-brain-help.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 | $0.00105 | $0.01253 |
| Opus 5 | $0.00053 | $0.00626 |
| Sonnet 5 | $0.00021 | $0.00251 |
| Haiku 4.5 | $0.00011 | $0.00125 |
Grade A, and why
second-brain-help 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 6d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Brain - Help（查看全部能力并选择正确 Skill）
这是随手可取的工具目录。默认只读，不执行安装、同步、知识写入、历史删除或山脉修改；选定后显式转交相应 Skill。
真实调用语法
- Codex：使用
$second-brain-<name>；也可打开/skills选择。Codex 不应被告知字面量/second-brain-<name>是原生命令。 - Claude、Hermes、AntiGravity：使用
/second-brain-<name>。 - 其他宿主：先查其原生 Skill 机制，再给真实语法。
可以通过 MCP list_second_brain_skills 查看当前 authority 清单、通过 read_second_brain_skill 读取所选流程；不要用缓存列表冒充当前清单。
七个入口
| Skill | 中文显示 | 什么时候用 | 是否默认写入 |
|---|---|---|---|
second-brain-attach |
Second Brain - Attach（接入并注入新 Agent） | 新 Agent/新设备首次接入、迁移、重装或残缺安装 | 是，先备份与基线 |
second-brain-sync |
Second Brain - Sync（同步通用规则与 Agent 配置） | common、Agent profile 与当前宿主投影出现漂移或需要传播偏好 | 是，低风险可自动合并 |
second-brain-learn |
Second Brain - Learn（沉淀当前对话与工作经验） | 从当前对话学习偏好、方法、知识、失败教训或山脉进展 | 视候选风险而定 |
second-brain-distill |
Second Brain - Distill（榨取历史对话并清理原始数据） | 批量挖掘历史会话，晋升附件，门禁通过后删除 allowlist 原文 | 是，删除需精确授权 |
second-brain-climb |
Second Brain - Climb（维护长期方向与爬山状态） | 维护长期方向的 summit、位置、路线、阻点、证据和下一信息动作 | 是，summit 高风险 |
second-brain-doctor |
Second Brain - Doctor（检查接入、注入和同步状态） | 检查 Skills、MCP、身份注入、Git 和 fresh-session 是否真实健康 | 否，只读诊断 |
second-brain-help |
Second Brain - Help（查看全部能力并选择正确 Skill） | 忘记名称、想看能力或任务意图不清 | 否 |
快速选择
- “给一个全新 Agent 穿上我的外骨骼” → Attach。
- “它已经接入，但规则/角色/Skill 版本不一致” → Sync。
- “从我们正在进行的这次对话里记住东西” → Learn。
- “批量挖旧聊天并在完整榨取后腾空间” → Distill。
- “这个长期方向现在走到哪、接下来验证什么” → Climb。
- “别改东西，只告诉我现在是否装好” → Doctor。
边界情况：
- Attach 结束必须调用 Doctor；Doctor 本身不修复。
- Learn 只处理当前对话；历史批次使用 Distill。
- Learn 写入 common/profile 后包含必要 Sync，但不逐台修改其他 Agent。
- Distill 可以调用 Learn 的候选路由和 Climb 的山脉更新，但只有 Distill 拥有原始会话删除门禁。
- Sync 处理规则漂移；项目代码或普通知识检索仍使用项目流程或 MCP 知识工具。
共同理念
- COMMON-RULES 是跨 Agent 通用规则唯一 owner；每个 Agent profile 保持独立角色。
- Agent 根据 Skills 自己执行，MCP 只是薄传输与确定性门禁。
- 低风险、有证据的学习可自动合并；权限、隐私、核心身份、summit 和冲突先问用户。
- authority 变化先保留本地可恢复历史；
private-remote经私有originPR 汇合，local-only不远端写入，公开 Release remote 只读；不用数据库、守护进程、规则编译器或外部推理 API。 - 原始对话不进 Git；完整榨取、附件晋升、receipt 和恢复验证通过后，才删除精确 allowlist。
- SkillOpt 的程序不是依赖，只吸收其从工作轨迹中学习的理念。
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.
- 6d ago First seen · 68 lines · 105 tokens per session scan A 54040a945efc
second-brain-help is a skill published in the GitHub repository YusenZhang0601/context-canopy (2 stars, last pushed 14d ago), licensed MIT. It adds 105 tokens to every session and 1,253 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
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
hipocampus-compaction
Build 5-level compaction tree (daily/weekly/monthly/root) with smart thresholds and fixed/tentative lifecycle. Run at session start when triggers are met, or via external scheduler.
hipocampus-core
3-tier agent memory system with 5-level compaction tree. Codex CLI version. Defines session start protocol, end-of-task checkpoints, and memory file management. MUST be followed every session.
hipocampus-search
Search memory using qmd (BM25 + optional vector) and compaction tree traversal. Use ROOT.md to decide whether to search memory or look externally. Always check memory before external lookups.
hipocampus-recall
Memory recall guide. Structured retrieval from hipocampus memory — ROOT.md triage, manifest-based LLM selection, qmd search fallback.
hipocampus-flush
Manual memory flush: dump current session context to daily raw log via subagent. Invoke with /hipocampus:flush. Run hipocampus:compaction afterwards for tree propagation and qmd reindex.