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 ninehills/skills --skill puagit clone --depth 1 https://github.com/ninehills/skillsWrote 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/ninehills/skills/pua)<a href="https://agentmods.dev/skills/ninehills/skills/pua"><img src="https://agentmods.dev/badge/skills/ninehills/skills/pua/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/ninehills/skills/pua"><img src="https://agentmods.dev/badge/skills/ninehills/skills/pua.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 | $0.00171 | $0.10363 |
| Opus 5.5 | $0.00068 | $0.04145 |
| Sonnet 5.5 | $0.00034 | $0.02073 |
| Haiku 4.5 | $0.00017 | $0.01036 |
Grade A, and why
pua scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `[PUA生效 🔥]` 部署后 curl 了全部端点 — 不验证的交付不叫交付，叫自嗨 The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
29 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/agent-team.md 4.5 KB
- references/de-escalation-protocol.md 5.9 KB
- references/ding-reminders.md 5.7 KB
- references/display-protocol.md 3.3 KB
- references/evolution-protocol.md 6.6 KB
- references/flavors.md 20 KB
- references/harness-governance.md 8.6 KB
- references/methodology-alibaba.md 2.0 KB
- references/methodology-amazon.md 2.8 KB
- references/methodology-apple.md 2.3 KB
- references/methodology-baidu.md 2.0 KB
- references/methodology-bytedance.md 2.3 KB
- references/methodology-ding.md 4.2 KB
- references/methodology-huawei.md 3.9 KB
- references/methodology-jd.md 2.6 KB
- references/methodology-meituan.md 2.4 KB
- references/methodology-microsoft.md 5.9 KB
- references/methodology-netflix.md 2.5 KB
- references/methodology-pinduoduo.md 2.0 KB
- references/methodology-router.md 6.4 KB
- references/methodology-tencent.md 2.4 KB
- references/methodology-tesla.md 2.7 KB
- references/methodology-xiaomi.md 2.9 KB
- references/p10-protocol.md 5.5 KB
- references/p7-protocol.md 11 KB
- references/p9-protocol.md 12 KB
- references/platform.md 14 KB
- references/survey.md 11 KB
- references/teardown-protocol.md 8.2 KB
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 · 429 lines · 171 tokens per session scan A 4521f3957261
pua is a skill published in the GitHub repository ninehills/skills (279 stars, last pushed 3mo ago), with no licence file. It adds 171 tokens to every session and 10,363 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
material-ui-nextjs
Integrates Material UI with Next.js App and Pages routers using @mui/material-nextjs, Emotion cache providers, next/font, CSS layers with Tailwind/CSS Modules, Link component prop patterns, CSS theme variables SSR notes, and App Router useSearchParams + Suspense. Use when setting up or debugging MUI in a Next.js app.
RootCauseAnalysis
Structured incident investigation using Five Whys, Fishbone, blameless Postmortem, Fault Tree, Kepner-Tregoe, and FMEA — traces failures to systemic root causes rather than blaming humans. USE WHEN root cause, RCA, 5 whys, fishbone, postmortem, incident analysis, fault tree, why does this keep failing, blameless…
benchmark-workflow
Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
incident-postmortem
Escribe un postmortem de incidente estructurado o revisión post-incidente. Úsalo cuando se te pida escribir un postmortem, reporte de incidente, revisión P1/P2, reporte de apagón o RCA (análisis de causa raíz). Produce un postmortem sin culpables con cronología, causa raíz, factores contribuyentes, resumen de impacto…
authoring-error-tracking-alerts
Author error tracking alerts that fire when an issue is created, reopened, or starts spiking. Use when the user asks to set up error notifications, route exceptions to Slack/webhook/Linear, or evaluate which error events are worth alerting on. Covers trigger-event selection, integration choice, dedup against existing…