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-climbgit 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-climb)<a href="https://agentmods.dev/skills/yusenzhang0601/context-canopy/second-brain-climb"><img src="https://agentmods.dev/badge/skills/yusenzhang0601/context-canopy/second-brain-climb/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yusenzhang0601/context-canopy/second-brain-climb"><img src="https://agentmods.dev/badge/skills/yusenzhang0601/context-canopy/second-brain-climb.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00114 | $0.01706 |
| Opus 5 | $0.00057 | $0.00853 |
| Sonnet 5 | $0.00023 | $0.00341 |
| Haiku 4.5 | $0.00011 | $0.00171 |
Grade A, and why
second-brain-climb 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 9d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Brain - Climb（维护长期方向与爬山状态）
让长期方向成为持续可导航的山，而不是口号、任务清单或静态愿望。当前 Agent 负责基于实际工作证据维护 mountain 页面；不建立目标数据库、常驻追踪器、统一评分器或标准角色库。
显式调用
- Codex：
$second-brain-climb，或从/skills选择。 - Claude、Hermes、AntiGravity：
/second-brain-climb。
Authority
- 山脉总览：
03-Personal/Profile/长期方向与山脉.md - 单座山：
03-Personal/Mountains/<山名>.md - 读取可优先使用 MCP
get_mountain_context。 - 实际工作状态仍由各项目自己的 authority 拥有；mountain 只链接和解释，不复制项目状态。
一座山表达一个长期方向。角色分工写入 Agent profile，不把 Agent 当成山；短期项目也不必都升级为山。
证据层级
清楚区分：
verified：有当前项目产物、用户明确陈述、真实结果或可重放验证。supported inference：证据支持但仍需判断。assumption：暂为行动所需，列出替换或敏感性计划。unknown：信息不足，不虚构精确状态。
山的“当前位置”不是情绪估计，也不是完成百分比；它由已经具备的能力、资产、验证和可见阻点组成。
深度 mountain 模型
每次维护都逐项检查，允许没有变化，但不得跳过未审计项：
1. Summit
定义最终想抵达的可识别状态：为谁服务、具备什么持续能力、保持哪些边界、什么证据表示“真的到了”。Summit 是方向，不是固定实现或某个厂商产品。
修改 summit 会改变长期身份和资源取舍，属于高风险；无论推断多合理，都先向用户展示旧/新差异、原因和后果并取得确认。
2. Current position
列出当前真实资产、已验证能力、尚未验证能力和最近证据日期。链接实际项目、commit、报告、对话学习或外部结果。
3. Gap
说明 summit 与 current 之间缺少的能力、信息、信誉、基础设施、习惯或资源。避免把“任务未完成”误写成根本差距。
4. Candidate routes
维护至少一个主路线和有证据时的替代路线。每条路线写清机制、依赖、可逆性、成本、反馈速度和最早可证伪点；不要为了形式凑路线。
5. Constraints
记录真实硬约束与软偏好，例如时间、资金、隐私、本地优先、供应商独立、设备可用性和维护负担。标明来源及是否仍有效。
6. Blockers
阻点是当前不能前进的具体因果条件，不是“还没做”。区分外部阻点、知识阻点、决策阻点和执行阻点，并写出解除它所需证据。
7. Evidence
把支持或反驳路线的观察连到真实工作。证据既包括成功，也包括失败、用户纠正和未达到的验收标准。历史管理标签只作辅助，不替代事实。
8. Uncertainty
列出会改变路线选择的关键未知、置信度和影响范围。不要把所有不确定性都变成任务；优先处理决策价值高的未知。
9. Next information action
指定一个最小动作，用最少成本减少最关键未知。它应写清：要观察什么、结果 A/B 分别意味着什么、何时停止。单纯“继续研究”不合格。
10. Active bet
明确当前正在押注的路线、为何此刻值得押、投入上限、预期反馈时间和失败信号。一次只保留少量真实 active bets，避免把愿望清单都标为进行中。
11. Switch criteria
写明哪些可观测证据触发切换路线，以及切换到哪条候选路线。不要因一次挫折就切换，也不要因沉没成本永远坚持。
12. Pause criteria
写明资源冲突、外部依赖或信息不足到何种程度应暂缓；暂停时保留恢复条件和最小维护动作。
13. Abandon criteria
写明什么证据说明 summit 本身不再值得、不可行或与更高优先级方向冲突。达到条件仍属于高风险决策，只提出并请求用户确认，不自动放弃。
14. Checkpoints and reflection
checkpoint 记录“发生了什么、什么预期被验证/反驳、对路线意味着什么、下一信息动作”。reflection 审计判断质量，不用励志措辞遮盖停滞。保留日期和来源，但不复制完整项目日志。
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.
- 9d ago First seen · 117 lines · 114 tokens per session scan A a39e6e28c97a
second-brain-climb is a skill published in the GitHub repository YusenZhang0601/context-canopy (2 stars, last pushed 17d ago), licensed MIT. It adds 114 tokens to every session and 1,706 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
audhd-executive-function
AUDHD executive function accommodations. Apply to all output the founder will act on.
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.
day-log
Quick timestamped log entry — no conversation, just capture.
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.