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 tanweai/pua --skill pua-jagit clone --depth 1 https://github.com/tanweai/puaWrote 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/tanweai/pua/pua-ja)<a href="https://agentmods.dev/skills/tanweai/pua/pua-ja"><img src="https://agentmods.dev/badge/skills/tanweai/pua/pua-ja/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/tanweai/pua/pua-ja"><img src="https://agentmods.dev/badge/skills/tanweai/pua/pua-ja.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 342 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Agent Snooping · line 342 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00192 | $0.10696 |
| Opus 5.5 | $0.00077 | $0.04278 |
| Sonnet 5.5 | $0.00038 | $0.02139 |
| Haiku 4.5 | $0.00019 | $0.01070 |
Grade A, and why
pua-ja 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.
| 交付検証 | コードを書き終えて口で「完了」と言う | 自分でbuild/test/curlを回し、通過した出力を貼り、証拠をもって「完了」と言う | 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 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 · 379 lines · 192 tokens per session scan A 11916d92382f
pua-ja is a skill published in the GitHub repository tanweai/pua (19,715 stars, last pushed 1mo ago), with no licence file. It adds 192 tokens to every session and 10,696 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
special-cute-coder-wife
A coding assistant with a warm, encouraging companion style. It is designed to read errors and logs, look for overlooked details, and guide debugging step by step.
military-commander
A strategy method for coordinating complex work by collecting information, setting priorities, assigning resources, and directing several lines of effort.
dream-paoding
A debugging method that treats error messages as clues about how a system is structured. It separates hard limits from habits, changes direction around constraints, and breaks the problem into reusable parts.
military-scout
A root-cause investigation workflow for software problems. It gathers information, searches records and clues, analyzes possible causes, verifies the likely explanation, and reports the result.
sillytavern-antifragile
A review workflow that treats pressure and failure as opportunities to adjust, learn, and improve, using five stages from exposure to overcoming the problem.
military-discipline
A strict review and debugging procedure based on checking work, asking for reasons, correcting problems, accepting only verified results, and recording lessons. It is designed as a quality-control process.