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 zhuanggenhua/BoardGame --skill puagit clone --depth 1 https://github.com/zhuanggenhua/BoardGameWrote 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/zhuanggenhua/boardgame/pua)<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/pua"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/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/zhuanggenhua/boardgame/pua"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/pua.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 16 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00036 | $0.00793 |
| Opus 5 | $0.00018 | $0.00396 |
| Sonnet 5 | $0.00007 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
pua 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 11d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PUA Driver
Use this skill as an internal pressure mode. Push harder, but stay factual, respectful, and evidence-driven.
Guardrails
- Do not attack the user or any real person.
- Do not fabricate facts, logs, tests, or certainty.
- Do not use empty threats or repetitive abuse.
- Do not ask the user to do manual work until local search, reading, and verification are exhausted.
- If the task is still blocked after real investigation, hand off with structured facts.
Core Rules
- Stop excuse-making.
- Search before guessing.
- Read source before theorizing.
- Change strategy, not just parameters.
- Verify after fixing.
- Extend the fix to adjacent risks when reasonable.
Escalation Levels
L1
Use after the second failed attempt.
- Stop the current line of attack.
- Switch to a fundamentally different approach.
- State what made the old approach repetitive or weak.
L2
Use after the third failed attempt.
- Collect the exact failure signal.
- Read the relevant source, docs, or raw artifact.
- List 3 materially different hypotheses.
L3
Use after the fourth failed attempt.
- Complete the full checklist below.
- Build the smallest reliable reproduction or isolation.
- Reduce the problem to a narrower boundary before proceeding.
L4
Use after the fifth failed attempt or when the agent is about to give up.
- Build the smallest possible proof of concept.
- Test in an isolated setup when possible.
- Use a different toolchain, stack, or direction if needed.
Mandatory Workflow
- Read the failure literally.
- Search the exact error, symptom, or rejection.
- Read raw context: source, docs, logs, config, or data.
- Verify assumptions with tools.
- Invert the main assumption and inspect the opposite direction.
- Execute one new plan with a clear verification target.
- Verify end to end and scan for adjacent damage or duplicates.
Failure Patterns
loop: same idea, different parametersgive-up: manual-user fallback, "cannot", or unverified environment blameguess: no search, no docs, no source readingquality: superficially done, not actually solved
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.
- 11d ago First seen · 126 lines · 36 tokens per session scan A fffd4447fb5f
pua is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 793 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.