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 pandazki/pneuma-skills --skill skillgit clone --depth 1 https://github.com/pandazki/pneuma-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/pandazki/pneuma-skills/skill)<a href="https://agentmods.dev/skills/pandazki/pneuma-skills/skill"><img src="https://agentmods.dev/badge/skills/pandazki/pneuma-skills/skill/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/pandazki/pneuma-skills/skill"><img src="https://agentmods.dev/badge/skills/pandazki/pneuma-skills/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 Anti-Refusal · line 96 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Anti-Refusal · line 550 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00150 | $0.07444 |
| Opus 5 | $0.00075 | $0.03722 |
| Sonnet 5 | $0.00030 | $0.01489 |
| Haiku 4.5 | $0.00015 | $0.00744 |
Grade A, and why
pneuma-bansho 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 yesterday.
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 — 584 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bansho — board-writing explainer
板上只有一支笔。你写下的每一件事都会等前一件事收笔。 — one pen on the board; everything you write waits for the previous thing to finish.
You are at a board with something to explain. You write the lecture — plain
structured markdown in board.md — and the board performs it: handwriting
flows in, your emphasis marks become hand-drawn ink, your charts draw
themselves as the talk reaches them. The user watches live, scrubs back
through time, and points at steps to ask about them.
Nothing here asks you to pick effects or manage timing — the board derives
all of that from what you wrote and how you punctuated it. If board.md
reads well as an essay, it plays well as a lecture.
Write in performance rhythm: look up (glance-board), decide where the
writing lands and say it (@at), append one or two blocks, let them play,
then compare — the tail past the playhead is still free to rewrite. Every
save streams straight onto the user's board; one giant write compresses a
live talk into a poster.
How the board reads your writing
Plain markdown IS the dialect: each block is one step of the talk, and the marks you would write anyway are the pen's instructions. The six highest-frequency forms:
| You write | On the board |
|---|---|
# 标题 / ## 小节 |
written large, hand-drawn underline, then a longer breath |
| a paragraph | handwriting flows in; commas and periods carry their own pauses |
- 条目 |
a hand-drawn dot per item, one item at a time |
==三倍== / **结构性** / ((35.6B)) |
ink — the sentence is written first, then the pen returns: marker sweep / underline / circle |
~~常规反弹~~ |
write it wrong on purpose: written, a pause, struck through — crossed out, never erased |
```chart 名字 / ```graph 名字 |
evidence — axes then one line at a time; boxes and arrows one at a time |
Turning back to earlier writing is its own line — the pen goes back to the nearest earlier exact match of the quoted text and inks it:
@strike "慢了就加机器"
What ships with it
8 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.
- yesterday Changed · +150 tokens per session 94bd03f380ea
- 12d ago First seen · 584 lines · 0 tokens per session scan A b1d11c3129d0
pneuma-bansho is a skill published in the GitHub repository pandazki/pneuma-skills (161 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 7,444 once invoked, about $0.0007 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
xray
Investigate how a concept, code path, application, network flow, system, incident, document, or local artifact actually works, then deliver a two-depth visual HTML explainer with a dead-simple big-picture first layer and source-backed technical depth behind it. Use when the user invokes $xray, asks how something works…
教程类H5-小红书小工具
A method for building offline, single-page course experiences for Xiaohongshu’s Mini Tools, which are interactive pages published inside the platform. It combines written lessons, generated illustrations, and JavaScript page switching in a constrained container.
sansheng-distill
A book and text summarizer that creates one self-contained HTML page with five sections: an overview, chapter notes, the book’s central idea, an action checklist, and questions for judging its reliability. The page includes an embedded Mermaid mind map and works offline without a web server.
master
Turn reference docs into active mastery through retrieval practice, case binding, and scenario simulation. Combines Skycak (learning science) and Chin (expertise acceleration) frameworks. Use when you want to deeply learn material, not just read it.
upskilling-coach
Expert coach for learning, mastering, and upskilling in any domain. Use when the user wants to learn, master, improve, upskill, get better at, or get coached on any topic. Helps build consistent practice habits, identify prerequisites, design efficient learning loops, avoid common pitfalls, maintain discipline, and…
explain
Guided code tour of a file or subsystem this session touched — entry point, the load-bearing pieces, the edges, and what connects to it.