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 HsuanYuLee/polaris --skill framework-self-devgit 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/framework-self-dev)<a href="https://agentmods.dev/skills/hsuanyulee/polaris/framework-self-dev"><img src="https://agentmods.dev/badge/skills/hsuanyulee/polaris/framework-self-dev/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/framework-self-dev"><img src="https://agentmods.dev/badge/skills/hsuanyulee/polaris/framework-self-dev.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 | $0.00296 | $0.03046 |
| Opus 5.5 | $0.00118 | $0.01218 |
| Sonnet 5.5 | $0.00059 | $0.00609 |
| Haiku 4.5 | $0.00030 | $0.00305 |
Grade A, and why
framework-self-dev 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 2d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
framework-self-dev — 在框架自己身上施工
這一份講兩件事：一張框架單怎麼開，以及改一支 skill 之後怎麼知道它變好還是變壞。
之後怎麼走不在這裡——driving-work-to-done 回答下一站是什麼，refinement 簽 assertion，
swe-knowledge 說這一類工作怎麼算 done。這一份補的是它們都沒有的兩格：開單那一刻要
回答什麼，以及改完一支 skill 之後拿什麼量它。
為什麼框架單需要自己一份
產品單來自外部系統，開單那一步有人把關：號要去那裡領，而領號的人會先看有沒有一樣的。 框架單沒有那一層。 開一張的成本是一個命令，而每一個 session 都在撞東西、每一個都照 規矩記下來——觀察是各自的，待辦是共用的。
2026-08-31 一天開了 44 張，因為那天有八個以上的 session 同時在跑。同一天量到的：還沒 出去的 52 張裡，43 張從來沒被任何一張產品單提到過，39 張一輪都沒開過，32 張連 assertion 都沒簽。而其中有 11 對在講同一件事。
這一份存在的理由是讓那個比例不再發生。 它不擋任何人——它要人回答問題。
兩種單，開單的人自己說是哪一種
| 舉發（實作途中撞到的問題） | 開發框架新功能 | |
|---|---|---|
| who 誰、在做什麼工作時撞到的 | 撞到的人當下就知道 | 沒有「撞到」這件事，答不出來 |
| where 撞在哪個檔 | 同上 | 同上 |
| 查重的鍵 | 就是 where |
where 不存在，鍵產不出來 |
新功能那一種不是被豁免，是那個機制對它不成立。 硬要它填，填出來的會是一個編的 ——而編過的格子看不出來，空著的看得出來。
種類由你宣告，不由腳本從名字或內容推。 推的話，同一件事換個寫法就換一種待遇， 而沒有人看得出來換過。
兩種單的終點是同一個形狀：都是一張該填的格子都有答案、只等 refinement 簽 assertion
的單。差的只有開單那一刻問哪幾格。
舉發那一種：6W
refinement 的四格（what／when／why／how）本來就在，舉發多兩格：
- who——是誰、在做什麼工作的時候撞到的。自己構造輸入跑出來的重現不算撞到：它證明那條 路徑存在，不證明有呼叫端會走到它。每一條重現問「哪個真實呼叫端會這樣叫它」，答不出來就標成 候選，不算進實例數。2026-09-17 的標本：一張單寫了兩個「獨立的洞」，兩條都是自己造的輸入， 都沒有呼叫端；原始回報的那一個也是誤讀，整張單的實例數是 0。
- where——撞在哪個檔。這一格同時就是查重的鍵。
那兩格正好是開單當下最便宜的兩格：撞到的人知道自己是誰、知道自己剛剛在讀哪個檔。它們不 像 assertion 那樣要想清楚怎麼算成功。
assertion 不在開單那一刻簽。 一張種子單存在的整個理由就是「怎麼算成功還沒想清楚」。 要求 6W 不改變這件事——改變的是開出來的東西不再是一張筆記。
查重：把撞到的那幾張端到眼前
鍵是「正文指名的檔案有交集」，不是標題共用實詞。 2026-08-31 拿當天真的重複的 11 對 當測資量過：
| 查重的鍵 | 11 對裡抓到 | 會提醒幾對 |
|---|---|---|
| 標題共用 ≥2 個實詞 | 6 | 3,300（全樹之間） |
| 正文指名的檔案有交集 | 10 | 93（還沒出去的 38 張之間） |
標題那一組漏掉的五對裡有三對一個詞都不共用，而那三對用檔案這個鍵全部抓得到。
分母是還沒出去的單。 開單的人要看的是「現在還在待辦裡的有沒有同一件」，不是「歷史上 有沒有」。終局那幾格不進分母。
噪音集中在少數幾個檔上，而那正好是資訊：一張新單指名某支被七張單同時指名的腳本時， 那七張本來就該一起看。
這不是一道閘
開一張重複的單不是不可逆的（close 得掉），也不出這個 repo。所以「查重不過就不給開」這種 東西不該存在。
擋人的只有三件，而且它們擋的是沒有回答問題，不是答案的內容：
- 沒宣告種類。
- 舉發那一種缺了 6W 任何一格。
- 撞到了卻沒有寫下判斷。
判定「撞到十張，都不是同一件」的話，單照樣開得出來。那句判斷會寫進單的正文裡，所以下一個 讀它的人看得到當時是怎麼判的。
兩條入口
開一張框架單有兩條路，而這一份對兩條都成立：
What ships with it
1 file 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.
- 2d ago Changed · +38 lines · +74 tokens per session 737950778919
- 25d ago Changed · +3 lines f7bdefa374df
- 1mo ago First seen · 119 lines · 222 tokens per session scan A e57cfad6063c
framework-self-dev is a skill published in the GitHub repository HsuanYuLee/polaris (5 stars, last pushed 2d ago), licensed MIT. It adds 296 tokens to every session and 3,046 once invoked, about $0.0012 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 2026-09-05.
Other skills, from other repositories
prd-to-issues
A planning skill that turns an existing product requirements document, or PRD, into small GitHub Issues that developers can implement and verify. It groups work into complete user-facing slices instead of separate front-end, back-end, testing, and documentation tasks.
project-context-steward
A project-documentation skill that scans a new project or several related code repositories and records their shared context in a PROJECT_CONTEXT.md file. It captures the product, users, workflows, architecture, repository boundaries, terminology, entry points, and known pitfalls.
stylework-requirement-planning
A planning skill for reviewing a batch of product or business requests from sources such as Excel, CSV files, screenshots, or work-management exports. It groups requests by theme and records duplicates, dependencies, unclear items, and planning assumptions.
stylework-yunxiao-requirement-sync
A workflow for exporting selected requirements from Yunxiao, a project-management service, into a new sheet in an existing DingTalk online spreadsheet. It formats the result into a fixed set of columns and groups it by iteration.
strategic-alignment
Cascades strategy from boardroom to individual contributor. Detects and fixes misalignment between company goals and team execution. Covers strategy articulation, cascade mapping, orphan goal detection, silo identification, communication gap analysis, and realignment protocols. Use when teams are pulling in different…
process-mapper
Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being…