Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/HsuanYuLee/polarisnpx agentmods add skills/hsuanyulee/polaris/engineeringWrote 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/engineering)<a href="https://agentmods.dev/skills/hsuanyulee/polaris/engineering"><img src="https://agentmods.dev/badge/skills/hsuanyulee/polaris/engineering/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/hsuanyulee/polaris/engineering"><img src="https://agentmods.dev/badge/skills/hsuanyulee/polaris/engineering.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 | $0.00156 | $0.02932 |
| Opus 5.5 | $0.00062 | $0.01173 |
| Sonnet 5.5 | $0.00031 | $0.00586 |
| Haiku 4.5 | $0.00016 | $0.00293 |
Grade A, and why
engineering 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
engineering — 兩個關卡之間
這裡沒有關卡。派工怎麼切、實作怎麼做、試幾次、走哪條路，都在這裡，沒有人在等你交表格。 正因為頭尾兩個關卡在，中間才可以很隨便。
接手
讀 {issue}/index.md 就夠了——凍結塊是成功的定義，可以改的那部分是其餘一切。不需要去翻別的
artifact。
bash .claude/skills/engineering/scripts/frozen-assertion-fence.sh verify {issue}/index.md
bash .claude/skills/driving-work-to-done/scripts/spine-loop-state.sh show --state {issue}/.spine/loop-state.json
bash .claude/skills/engineering/scripts/record-measurement-change.sh show --ledger {issue}/.spine/measurement-ledger.json
量測命令
第一次寫的命令要登錄 baseline：
bash .claude/skills/engineering/scripts/record-measurement-change.sh record \
--ledger {issue}/.spine/measurement-ledger.json \
--assertion-id A-P1 --new-command '<cmd>' --baseline
量不到目標是常態，換就是了，但換要帶三元組：舊命令 hash、新命令 hash、以及這條新命令 在實作之前紅過的證據。
bash .claude/skills/engineering/scripts/record-measurement-change.sh record \
--ledger {issue}/.spine/measurement-ledger.json \
--assertion-id A-P1 --old-command '<舊>' --new-command '<新>' --red-evidence <path>
紅不了的命令什麼都沒量。一個因為工具不存在而失敗的紀錄不算紅過，它只證明環境壞了。
量不到要說出來，不能回綠。 負向的量測天生會把「我沒看到」讀成「它沒發生」——掃到 0 個 檔案、找不到那棵樹、正則對上 0 次，這些在輸出上跟「掃過了，沒問題」長得一模一樣。所以每條 量測前面要有一個 preflight：目標在不在、樣本數夠不夠。preflight 不過就用另一個 exit code 停下來（慣例是 2＝量不到、1＝量到了而且是紅的、0＝綠），不要讓它走進判定。
自己剛寫的檢查第一次就綠是可疑訊號，通常代表規則太窄。落地之前先餵它一份已知壞掉的 輸入，確認它真的會紅。
在這裡發現問題，先自己解
| 發現的問題 | 怎麼辦 |
|---|---|
| 量測方法不對 | 原地改，帶紅過證據換命令，繼續 |
| 切分不對 | 重切，繼續 |
| assertion 不對 | 不是這一站能解的——回 driving-work-to-done 讀該停哪一種 |
施工計劃那一類不存在：這條流程不分「明確施工」與「嘗試實作」。看得懂就做，看不懂就先探。
輪次
一輪沒產出 code 也是一輪。「試過 A，撞到 X，結論走 B，code 全丟」是正常結果——這一輪的產出 是知識，寫進可以改的那部分就是交付。不要為了讓這一輪看起來有東西，把失敗的探索包裝成交付。
bash .claude/skills/driving-work-to-done/scripts/spine-loop-state.sh record \
--state {issue}/.spine/loop-state.json \
--outcome converged|unconverged|zero_delta --note '<一句話>'
連續沒收斂到上限時流程升人類，不繼續自轉。上限是活區可調的參數，不是驗收條件。
三件要浮出來的事
方法自由，但有三件事 oracle 照不到，即使做了會變綠也要寫進可以改的那部分並講清楚為什麼，等人回話：
- 新增依賴：把一個新套件拉進來。
- 重造既有組件：手寫一個 repo 裡已經有的東西。
- 擴大 security surface：多開一個對外介面、多讀一份憑證、多信任一個輸入。
What ships with it
3 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 Changed · +14 lines 894e263b3104
- 11d ago Changed · +16 lines 7ab18831c790
- 1mo ago Changed · +8 lines 52938800bc68
- 1mo ago First seen · 131 lines · 156 tokens per session scan A 80e71f9e284c
engineering is a skill published in the GitHub repository HsuanYuLee/polaris (5 stars, last pushed 2d ago), licensed MIT. It adds 156 tokens to every session and 2,932 once invoked, about $0.0006 per session on Opus 5.5. 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
trip-email-html-itinerary
Extract trip logistics from pasted travel emails, booking confirmations, forwarded messages, reservation notes, or raw itinerary text, research useful restaurant and activity suggestions for each destination, and generate one polished, self-contained offline HTML itinerary file for sharing with family or other…
idea-forge
Run any raw idea through a multi-stage R&D pipeline that interprets, expands, scores, and converts it into an actionable engineering plan. Always trigger immediately when the user's message starts with "idea". Also trigger on "ideaforge", "analyze this idea", "expand this concept", "assess this invention", "explore…
facebook-post
Write and polish Facebook posts on any topic. Trigger on requests to draft, rewrite, polish, improve a Facebook post, or create cross-platform Facebook, X, and LinkedIn bundles, especially when the user starts with fbp.
fitness-log
Track workouts, log fitness progress, adjust the training program, and generate Facebook posts from workout data. Trigger on workout logging, PR updates, program questions, and fitness progress summaries.
food-analyzer
Analyze food photos, nutrition labels, and ingredient lists. Trigger on food images, nutrition label scans, macro questions, glycemic questions, medication interaction checks, and similar food-analysis requests.
travel-itinerary
Plan, format, and export travel itineraries as Obsidian-formatted Markdown files. Always trigger immediately when the user's message starts with "trip" or "itinerary". Also trigger when the user says "plan my trip", "build my itinerary", "travel plan", "export my trip", "format this itinerary", or describes an…