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-store-verify-plugin/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-store-verify-plugin)<a href="https://agentmods.dev/skills/haoxiang-xu/pupu/community-store-verify-plugin"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/community-store-verify-plugin/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-store-verify-plugin"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/community-store-verify-plugin.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 | $0.00065 | $0.01641 |
| Opus 5.5 | $0.00026 | $0.00656 |
| Sonnet 5.5 | $0.00013 | $0.00328 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
community-store-verify-plugin 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PuPu plugin verification
Produce a scoped, reproducible security judgment for the requested artifact. This skill is the verification operator; the PuPu registry and installer remain the enforcement layer. Follow the proposed v0.1 policy below, label its maturity, and preserve stronger current project requirements where applicable. Do not describe this as OWASP, SLSA, OpenSSF or third-party certification.
Read controls and tools for the relevant artifact type. Read product integration plan when implementing evidence storage, UI or installer enforcement; those changes are not already implemented by installing this skill.
Authority and states
The user's request to verify a named candidate authorizes scoped inspection, acquisition of its public immutable artifacts, and bounded tests in an available isolated environment. Continue without asking repeatedly for already authorized work. Honor explicitly authorized publication and catalog changes; otherwise produce the report without editing external systems.
Availability, publisher origin and verification are separate. The project owner can allow an unverified package to be listed/installed. That does not fabricate a scan, change its security verdict, or grant a Verified badge. Preserve existing authorization from the session. Never run the scanner against all local agent configs when only one candidate was requested.
Report verdicts are PASS, FAIL or INCOMPLETE, each with explicit scope. PASS requires all applicable required checks, analyzed findings and reproducible evidence for the same artifact. A skipped/errored/timed-out check is NOT_RUN/ERROR, not PASS. N/A needs a reason grounded in the target's behavior. Do not infer safety from popularity, official provenance, a scanner's zero findings, or a maintainer decision to make a package available.
No routine human sign-off is required merely because the reviewer is an agent. Identify the actual reviewer/model and analysis methods honestly. Use skeptical second-pass review for ambiguous findings; never label the same run an independent review. Ask the owner only for a missing scope/permission decision or an explicit risk exception, not routine interpretation of technical evidence.
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 · 47 lines · 65 tokens per session scan A 92d3eff86eff
community-store-verify-plugin is a skill published in the GitHub repository haoxiang-xu/PuPu (36 stars, last pushed 3d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,641 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…