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/yusenzhang0601/context-canopy/second-brain-syncnpx skills add YusenZhang0601/context-canopy --skill second-brain-syncgit 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-sync)<a href="https://agentmods.dev/skills/yusenzhang0601/context-canopy/second-brain-sync"><img src="https://agentmods.dev/badge/skills/yusenzhang0601/context-canopy/second-brain-sync.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 | $0.00113 | $0.01776 |
| Opus 5 | $0.00056 | $0.00888 |
| Sonnet 5 | $0.00023 | $0.00355 |
| Haiku 4.5 | $0.00011 | $0.00178 |
Grade A, and why
second-brain-sync 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 5d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Brain - Sync（同步通用规则与 Agent 配置）
让当前 Agent 自己完成双向审计与受控同步。不要创建常驻同步服务、数据库、规则编译器或外部推理 API。
显式调用
- Codex：
$second-brain-sync，或从/skills选择。 - Claude、Hermes、AntiGravity：
/second-brain-sync。
两类 owner
90-System/Personal-AI/COMMON-RULES.md只拥有真正跨 Agent 的稳定规则。90-System/Personal-AI/AGENTS/<agent-id>.md只拥有该 Agent 的角色、分工、能力边界和宿主差异。
不要建立标准角色库。两个表面相似的 Agent 可以保留完全不同的 profile。宿主全局规则文件只是这两个 owner 的短投影；自动记忆、会话摘要和本地 cache 不是 authority。
同步方向
一次同步同时检查两个方向：
- Agent → Second Brain：识别当前宿主里尚未沉淀的稳定偏好、角色事实与冲突。
- Second Brain → Agent：把当前 common 与本 Agent profile 的最新短投影更新到宿主。
不要扫描所有 Agent 的本地配置。跨 Agent 同步通过 Vault 中的 profile 页面完成：当前 Agent 读取所有已登记 profile 只为发现通用候选和冲突，但只修改自己的宿主投影。
工作流
1. 建立基线
- 读取 Vault 根
AGENTS.md、COMMON-RULES、当前 Agent profile 和现有宿主管理块。 - 检查
90-System/.capture.lock、Vault compiler 基线、Git 状态、authority 模式与授权账号；公开 Release remote 不得成为个人 authority 的 push target。 - 记录各表面的 SHA-256；不要输出规则文件中的秘密。
2. 形成候选
逐项给候选标注：
common：任何已接入 Agent 都应遵守。agent-specific：只属于当前 Agent 的定位、能力或宿主约束。project-local：应留在项目 AGENTS/CLAUDE 等局部规则。skill-workflow：应进入某个 Second Brain Skill，而非身份规则。cache-only：短期上下文，不应沉淀。conflict：与现有 owner 或高优先级规则冲突。
每个候选保留来源位置、原文或可核验摘要、风险级别和目标 owner。
同时标注相对活动规则的主要转换：add、reinforce/no-op、correct、narrow、broaden、replace、merge、relocate 或 retire。同步不是只把新文本向前复制；被替代、迁移或退役的旧正文必须从 authority 与投影一起退出。
3. 风险裁决
以下低风险项目可自动合并：
- 用户在当前或可追溯对话中明确表达的稳定输出偏好。
- 对既有规则的去重、错别字修复和不改变含义的压缩。
- 有更强证据支持、范围清楚且不改变高风险边界的纠错、缩限、替代、迁移或退役。
- 已有 profile 的版本、安装方式或验证状态更新。
- 多个 Agent profile 中直接一致、且不涉及权限的通用偏好。
以下高风险项目先询问用户：
- 权限、隐私、安全、自动外部写入或数据删除边界。
- 核心身份、价值观、长期方向 summit 或 Agent 职责重新划分。
- 证据互相矛盾，无法判断哪个规则仍有效。
- 将 Agent-specific 规则提升为全局 common。
- 规则扩域、无法证明新证据强于旧规则，或会移除仍有独特价值的长期资产。
- 会覆盖用户手写且不在 Second Brain 管理块内的规则。
不确定但低影响的推断可以保留为带证据和复核日期的候选，不得伪装成用户明确偏好。
4. 修改 authority
- 先更新 COMMON-RULES 或当前 Agent profile 的唯一 owner；不要直接从一个宿主复制到另一个宿主。
- 保留 Agent profile 的叙事性和独特定位，不按统一字段把角色削平成模板。
- 把 owner 维护为当前最优状态：去重、纠错、压缩、迁移并移除失效活动正文；历史依据进 Git、LOG、receipt 或不可变来源，不在活动 owner 中累积 tombstone。除非有可验证硬限制，不设任意行数或字节上限。
- 更新来源、时间和变更说明。若涉及 Vault canonical，遵守完整 capture/原子性/关系门禁。
- 所有 authority 变化先使用本地短任务分支、精确 diff、秘密扫描和门禁；
private-remote再经已验证为 private 的originPR 汇合，local-only只保留本地 commit 与备份，不做远端写入。
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.
- 5d ago First seen · 111 lines · 113 tokens per session scan A 42920a944d7a
second-brain-sync is a skill published in the GitHub repository YusenZhang0601/context-canopy (2 stars, last pushed 13d ago), licensed MIT. It adds 113 tokens to every session and 1,776 once invoked, about $0.0006 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.
start
One-word self-unfolding onboarding. Sets up a fresh, unpersonalized vault end-to-end — installs the memory engine, runs the profile interview, scaffolds the vault, and teaches the user as it goes. The single front door.