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 request-pr-reviewgit 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/request-pr-review)<a href="https://agentmods.dev/skills/hsuanyulee/polaris/request-pr-review"><img src="https://agentmods.dev/badge/skills/hsuanyulee/polaris/request-pr-review/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/request-pr-review"><img src="https://agentmods.dev/badge/skills/hsuanyulee/polaris/request-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00323 | $0.03920 |
| Opus 5.5 | $0.00129 | $0.01568 |
| Sonnet 5.5 | $0.00065 | $0.00784 |
| Haiku 4.5 | $0.00032 | $0.00392 |
Grade A, and why
request-pr-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
request-pr-review — 請人來看已經開好的 PR
實作做完、PR 開出來了，缺的是最後一步：請同事看。這支 skill 承載那一步的全部——這批 總共有多少、分在哪些 repo、每一個現在被誰看了、要通知誰。
三步，順序固定，中間那一步是人：
- query 名下所有 open PR，帶回每一個的 review 狀態。
- 列出來問使用者要怎麼處理——列的東西要足夠讓他當場決定，不用再去 GitHub 翻一遍。
- 照他的決定通知對的人。
這支 skill 不知道的三件事
要看哪個 org、哪個 repo 通知誰、一張單長什麼樣。 三者都由認領那個 org 的 skill 在
自己的 SKILL.md 宣告，這裡掃所有 skill 找那一行：
<!-- {任意前綴}-PR-CONTEXT-{org}: {命令} -->
鍵裡那一段就是 org 名，所以掃一次同時回答「要 query 誰」與「拿到之後問誰」。一個宣告都 沒有時說出來並停下——不猜一個 org，不用占位字串當預設值。
命令裡的相對路徑，錨是宣告它的那份 SKILL.md 所在的目錄，不是呼叫者當下的 cwd——核心
跑它之前會先切過去。宣告行寫得出來的只有相對路徑，而「相對於我自己」在 skill 被單獨帶到
別的環境時仍然成立，「這個 workspace 的 root 在哪」在那裡沒有答案。
宣告的命令要認得兩個模式，第一個參數就是模式名：
| 模式 | 進 | 出 |
|---|---|---|
notify --repo R |
參數 | 這個 repo 的 PR 通知誰，格式由那一層自己定 |
ticket |
stdin：repo⇥number⇥title⇥branch |
repo⇥number⇥單號⇥單的 URL |
ticket 走 TSV 而不是把 PR 的 JSON 丟過去：那個資料結構是這支 skill 的事，交出去等於逼
每一家公司的知識層都得認得它。這裡不認得任何一家公司的單號長什麼樣，也不該認得。
所以這裡沒有前置設定要人先準備，也不需要任何環境變數。author 沒指定時自己偵測：
MY_USER="$(gh api user --jq '.login')"
approval threshold 是公司 pack 的知識，不是這支 skill 的：幾票算看過了由那家公司說，寫在它自己
的 pack 裡（repo-notes 那支的 PR 與 review 慣例那一份）。check-pr-approval-status.sh 的
--threshold 沒給時用 2，公司 pack 說的數字不是 2 時就帶 --threshold N。以前這裡寫「讀
workspace config 的 shared defaults」並在 pipe 裡放一個 $APPROVAL_THRESHOLD——那個鍵從來
不存在，那個變數整支 skill 沒有人賦值，讀到的永遠是腳本的預設值。
Bundled Scripts
路徑相對於本 skill 目錄。
| Script | 用途 | 輸出 |
|---|---|---|
scripts/resolve-pr-context.sh |
orgs 列出被宣告的 org；notify / ticket 轉交給認領那個 org 的命令 |
org 清單／那一層的答案 |
scripts/fetch-user-open-prs.sh |
名下所有 open PR，含 org/base/head | PR JSON array |
scripts/check-pr-approval-status.sh |
approval 數、stale、被指名還沒看的 reviewer | 加上 approval 欄位 |
scripts/fetch-pr-review-comments.sh |
還沒被回覆的 actionable comments | 加上 unaddressed_comments |
scripts/check-pr-ci-status.sh |
CI 狀態 | 加上 ci |
scripts/attach-pr-ticket.sh |
這個 PR 屬於哪一張單 | 加上 ticket |
scripts/plan-pr-notify.sh |
這批要通知哪裡，逐個 repo 給建議 | repo⇥狀態⇥數量⇥目的地 |
What ships with it
20 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/report-format.md 7.3 KB
- references/request-pr-review-reporting.md 6.3 KB
- references/stale-approval-detection.md 2.3 KB
- scripts/attach-pr-ticket.sh 3.6 KB runs code
- scripts/check-pr-approval-status.sh 6.2 KB runs code
- scripts/check-pr-ci-status.sh 3.1 KB runs code
- scripts/fetch-pr-review-comments.sh 11 KB runs code
- scripts/fetch-user-open-prs.sh 4.6 KB runs code
- scripts/lib/approval-staleness.sh 2.1 KB runs code
- scripts/lib/github-rest.sh 10 KB runs code
- scripts/lib/main-checkout.sh 1.9 KB runs code
- scripts/lib/pr-approval-count.sh 4.3 KB runs code
- scripts/lib/validate_language_policy_1.py 11 KB runs code
- scripts/lib/workspace-config-root.sh 2.6 KB runs code
- scripts/plan-pr-notify.sh 4.0 KB runs code
- scripts/resolve-pr-context.sh 6.3 KB runs code
- scripts/selftests/fixtures/gh 5.6 KB
- scripts/selftests/request-pr-review-selftest.sh 22 KB runs code
- scripts/selftests/request-pr-review-shape-selftest.sh 21 KB runs code
- scripts/validate-language-policy.sh 9.2 KB 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 Changed · +10 lines 4641a450f32b
- 1mo ago Changed · +21 lines 2b0c7af414ab
- 1mo ago First seen · 186 lines · 323 tokens per session scan A 5c941f4c0c80
request-pr-review is a skill published in the GitHub repository HsuanYuLee/polaris (5 stars, last pushed 2d ago), licensed MIT. It adds 323 tokens to every session and 3,920 once invoked, about $0.0013 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
understand-diff
Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks.
address-github-comments
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
github-pr-comments
Resolve inline code review comments on a GitHub PR. Use when asked to "resolve review comments", "address PR feedback", "fix PR comments", or "work through review comments". Fetches every inline comment with its surrounding code context, then applies each change systematically.
skills-pr-handle
Use when explicitly asked to handle a pull request in the Scenario skills repository, including review comments and skill validation.
pr-handle-comments
Handle review comments received on GitHub for the current branch's PR or a given PR number or URL, by triaging each unresolved thread, fixing what is warranted, pushing, and replying in each thread, when asked to address, fix or answer PR comments. Works in any Scenario repository.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…