Borrowing it
Nothing to install: this file belongs to haoxiang-xu/PuPu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/haoxiang-xu/PuPu/main/.agents/skills/community-repo-issue-polling/SKILL.mdgit clone --depth 1 https://github.com/haoxiang-xu/PuPuWrote 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/haoxiang-xu/pupu/community-repo-issue-polling)<a href="https://agentmods.dev/skills/haoxiang-xu/pupu/community-repo-issue-polling"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/community-repo-issue-polling/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/haoxiang-xu/pupu/community-repo-issue-polling"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/community-repo-issue-polling.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 | $0.00068 | $0.01086 |
| Opus 5.5 | $0.00027 | $0.00434 |
| Sonnet 5.5 | $0.00014 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
community-repo-issue-polling 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 1mo 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Community: Repository Issue Polling
Turn repository activity into a small, evidence-backed decision queue. Default repository in this workspace: haoxiang-xu/PuPu, checkout /Users/red/Desktop/GITRepo/PuPu, maintainer haoxiang-xu. Verify the remote before use; for another repository derive its configuration instead of copying PuPu's maintainer. Respond in the user's language.
Modes
- 巡检 / scan: Collect changes, assess new actionable signals, update the local inbox. Scheduled runs use this mode. Notify only for new actionable activity, material changes, completion, failure, or a newly required decision. Keep unchanged pending items without repeating their notification every day.
- 逐项评判 / triage: Show a short ordered queue, then work through the first item with the user. Give the evidence, your recommendation, and the one decision needed. Carry forward their answers and move to the next item after completing the agreed action. Do not ask all questions at once.
- 执行 / act: Carry out the specific action already authorized in this conversation or recorded standing rules. Re-read the current item immediately before writing, verify the result, and record it. Do not ask again for an action already authorized.
For collection and durable inbox details, read references/inbox.md.
Assess the actual item
Read the full issue/PR and relevant conversation, including maintainers' later replies. Group a linked issue, PR and comments into one decision where they concern the same outcome. Distinguish outside human contributions, maintainer activity, and bots; a comment from an outsider on a maintainer-created issue still belongs in the community inbox. Bot review findings may be actionable; routine bot noise need not be surfaced. Author association is context, not proof that a contribution is correct.
For each actionable item record its URL, author, what changed, current status/assignees, supporting evidence, recommended next action, and whether user input is needed. Prioritize reported security/data-loss or release-blocking problems, misleading/incomplete PRs, contributors waiting for direction, then ordinary bugs/features/questions. Calibrate these claims against evidence rather than the submitter's title.
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.
- 1mo ago First seen · 41 lines · 68 tokens per session scan A 139a3f9a252b
community-repo-issue-polling is a skill published in the GitHub repository haoxiang-xu/PuPu (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,086 once invoked, about $0.0003 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 2026-09-21.
Other skills, from other repositories
antfu-issue-triage
Triage open issues and PRs of the current GitHub repo - find already-fixed, duplicate, and spam items, suggest labels, gauge demand from reactions and comments, then present a table of proposed actions and comments for confirmation before touching anything. Use when asked to triage, organize, clean up, or groom issues…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…