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/hsuanyulee/polaris/learningnpx skills add HsuanYuLee/polaris --skill learninggit clone --depth 1 https://github.com/HsuanYuLee/polarisWrote 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/hsuanyulee/polaris/learning)<a href="https://agentmods.dev/skills/hsuanyulee/polaris/learning"><img src="https://agentmods.dev/badge/skills/hsuanyulee/polaris/learning.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 | $0.00180 | $0.01840 |
| Opus 5 | $0.00090 | $0.00920 |
| Sonnet 5 | $0.00036 | $0.00368 |
| Haiku 4.5 | $0.00018 | $0.00184 |
Grade A, and why
learning 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
learning
learning 把外部資料、文章 queue、PR review lessons、daily scanner setup
轉成可落地的 workspace knowledge。SKILL.md 只保留 mode routing、邊界與
必讀 reference；mode 細節延後載入。
Mandatory Contracts
- 任何 sub-agent dispatch 前，先說出它要回傳什麼（Completion Envelope），並要求它把
完整分析寫進一個檔案（
/tmp/polaris-agent-{timestamp}.md），主 session 只收摘要。 envelope 的形狀由派工的那一份 flow 自己定義——PR / Batch 在learning-pr-batch-flow.md，queue 在learning-queue-flow.md。 - 任何 Slack / JIRA / GitHub / Confluence 或其他 external write 前，遵守
scripts/validate-language-policy.sh或 external write gate。 - 任何 specs Markdown 產出或匯入，遵守
starlight-authoring-contract.md。 - Learning 可以 seed / import research evidence，但不得自動 invoke
refinement， 也不得替任何已凍結的 assertion 改寫成功的定義。 - 寫入 handbook、backlog、learnings、README acknowledgement、RemoteTrigger 或 specs artifact 後，最後必跑 Post-Task Reflection。
Mode Detection
依使用者輸入選 mode；只讀該 mode 的 reference。
| Signal | Mode | Reference |
|---|---|---|
PR number、PR URL、PR + 學習/learn、某人的 PR、時間範圍 + PR |
PR mode | learning-pr-batch-flow.md |
掃 review、batch learn、批次學習、掃歷史 PR、補齊 review lessons |
Batch mode | learning-pr-batch-flow.md |
| 外部 URL、GitHub repo、文章、local research file、使用者貼的研究題材 | External mode | learning-external-flow.md |
每日學習、今天有什麼可以學的、有新文章嗎、讀文章、daily learning、queue、bare 學習 without URL/PR context |
Queue mode | learning-queue-flow.md |
設定學習、learning setup、更新學習主題、scanner 設定、learning scanner |
Setup mode | learning-setup-flow.md |
| 模糊輸入 | Ask one concise clarification | N/A |
首次使用但 daily scanner 尚未設定時，提示使用者可用 設定學習 或
learning setup 啟用每日文章推薦。
External Mode Contract
讀 learning-external-flow.md。外部學習必須先判斷 target：
framework：Polaris / 框架 / AI agent pattern / skill / rule / mechanism。project:{name}：使用者指定產品 repo 或目前工作脈絡可明確推導。- ambiguous：詢問「這個學習要用在 Polaris 框架，還是特定產品 repo？」
GitHub repo 若包含 .claude/skills/、SKILL.md 或 skills/，探索前先跑
.claude/skills/learning/scripts/skill-sanitizer.py pre-scan；HIGH/CRITICAL 風險需讓使用者確認是否繼續。
What ships with it
24 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/learning-external-flow.md 8.7 KB
- references/learning-pr-batch-flow.md 4.9 KB
- references/learning-queue-flow.md 3.2 KB
- references/learning-setup-flow.md 5.7 KB
- references/review-lesson-extraction.md 6.8 KB
- references/starlight-authoring-contract.md 7.7 KB
- scripts/lib/main-checkout.sh 1.9 KB runs code
- scripts/lib/specs-root.sh 4.2 KB runs code
- scripts/lib/validate_dp_metadata_1.py 10 KB runs code
- scripts/lib/validate_language_policy_1.py 11 KB runs code
- scripts/lib/validate_learning_seed_contract_1.py 6.9 KB runs code
- scripts/lib/validate_specs_collection_shape_1.py 2.6 KB runs code
- scripts/lib/validate_starlight_authoring_1.py 8.3 KB runs code
- scripts/lib/workspace-config-root.sh 2.6 KB runs code
- scripts/polaris-embed-setup.sh 917 B runs code
- scripts/polaris-embed.py 7.5 KB runs code
- scripts/polaris-learnings.sh 9.8 KB runs code
- scripts/skill-sanitizer.py 23 KB runs code
- scripts/sync-spec-sidebar-metadata.sh 9.9 KB runs code
- scripts/validate-dp-metadata.sh 769 B runs code
- scripts/validate-language-policy.sh 9.2 KB runs code
- scripts/validate-learning-seed-contract.sh 281 B runs code
- scripts/validate-specs-collection-shape.sh 4.1 KB runs code
- scripts/validate-starlight-authoring.sh 639 B 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.
- 5d ago First seen · 125 lines · 180 tokens per session scan A ff6bd5376e89
learning is a skill published in the GitHub repository HsuanYuLee/polaris (5 stars, last pushed yesterday), licensed MIT. It adds 180 tokens to every session and 1,840 once invoked, about $0.0009 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
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.
baoyu-comic
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
offensive-exploit-dev-course
Full exploit development course roadmap and syllabus: weekly topics, recommended reading, lab setup, and learning path from vulnerability classes through advanced exploitation. Use to structure exploit dev training or onboard new researchers.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
master-debate
Use when user explicitly asks for an adversarial / multi-round dialectic between masters — 祖师辩论, 各执一词, 谁更对, debate, 应成 vs 顿悟, 顿渐之争. Differs from /compare-masters (parallel single-round) by being adversarial multi-round via fresh-subagent orchestration. Topics 空有 / 禅净 / 性相 / 戒律 vs 内观 — trigger is adversarial framing…
master-atisha
Use when user asks about 藏传, 噶当派, Kadam, 三士道, 菩提道灯论, Bodhipathapradīpa, 阿底峡, Atiśa, 金洲大师, 七因果, 自他相换, 菩提心, 依止善知识, 暇满, 业果, 噶当六论, 仲敦巴, 热振寺, 藏地后弘期, or wants teaching in 阿底峡尊者 Atiśa's voice. Triggers include "阿底峡"、"觉沃杰"、"Atisha"、"Jowo Je"、"菩提道灯"、"道灯论"、"三士道"、"七因果"、"自他相换"、"金洲"、"噶当"、"仲敦巴"、"热振寺"、"道次第之祖" — invoke whenever…