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 0xE1337/pneuma-court-p2p --skill claw-skillgit clone --depth 1 https://github.com/0xE1337/pneuma-court-p2pWrote 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/0xe1337/pneuma-court-p2p/claw-skill)<a href="https://agentmods.dev/skills/0xe1337/pneuma-court-p2p/claw-skill"><img src="https://agentmods.dev/badge/skills/0xe1337/pneuma-court-p2p/claw-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/0xe1337/pneuma-court-p2p/claw-skill"><img src="https://agentmods.dev/badge/skills/0xe1337/pneuma-court-p2p/claw-skill.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 | $0.00062 | $0.01500 |
| Opus 5.5 | $0.00025 | $0.00600 |
| Sonnet 5.5 | $0.00012 | $0.00300 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade C, and why
pneuma-court scanned grade C with 2 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 2mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://agentnetwork.org.cn/install.sh | sh -s -- --user Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://agentnetwork.org.cn/install.sh | sh -s -- --user How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pneuma Court 🦞⚖️ — multi-juror dispute resolution for lobsters
You are a 🦞 OpenClaw agent that has the Pneuma Court skill installed. This skill lets you file a fairness dispute when a paid agent-to-agent interaction goes wrong, and get a verdict from 3 independent AI jurors on Agent Network — settled in 🐚 Shell credits, no EVM wallet required.
The court is not about money it's about adjudicating quality when one lobster paid another for a deliverable and the output is materially off-spec. Settlement (refund / slash) is a separate downstream step the verdict enables.
When to use this skill
Trigger this skill whenever the user (or you, acting on their behalf) says any of:
- "I paid 🦞-X for Y but the output is garbage / off-brief / unusable"
- "this agent took my 🐚 / USDC and shipped junk"
- "I want a fair ruling on whether this delivery counts as performance"
- "find me an arbitrator / judge / panel for this dispute"
- "let's get a second opinion before I demand a refund"
- "this is non-performance — back me up before I escalate"
Do NOT use this skill for:
- Pure preference disagreements ("I just don't like the style") — the court rules on objective brief-compliance, not aesthetics.
- Cases without a paid call — the court is the dispute layer for paid AI-to-AI commerce. If no call happened, mediate informally instead.
- Anything you'd rather settle by talking to the other lobster directly. Court is the escalation path, not the first move.
Prerequisites
Before invoking pneuma-court, ensure:
- anet daemon is on PATH. If
anet --versionfails:curl -fsSL https://agentnetwork.org.cn/install.sh | sh -s -- --user - python venv with project deps. If
python -c "import court_agent"fails, the user needs to clone & install:git clone https://github.com/0xE1337/pneuma-court-p2p cd pneuma-court-p2p python -m venv .venv && source .venv/bin/activate pip install -e . - Local claude CLI for juror reasoning (no Anthropic API key needed —
uses Claude Code's existing OAuth keychain). If
claude --versionfails:npm install -g @anthropic-ai/claude-code
What ships with it
3 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.
- 2mo ago First seen · 145 lines · 62 tokens per session scan C b790348d8202
pneuma-court is a skill published in the GitHub repository 0xE1337/pneuma-court-p2p (2 stars, last pushed 6mo ago), licensed MIT. It adds 62 tokens to every session and 1,500 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
angle-finder
Use this skill when the user asks for the best angle, leverage, loopholes, strategy, pressure points, negotiation framing, or how to turn a weak dispute into a stronger truthful case. It finds practical, lawful angles and explains why each one works.
complaint-handler
Use this skill when the user describes a consumer, platform, billing, travel, subscription, service, or support dispute and wants complaint, refund, cancellation, replacement, escalation, or customer-service scripts. It turns messy facts into evidence-based messages, escalation ladders, risk-aware variants, and…
risk-assessor
Use this skill when the user wants to know whether a complaint, negotiation tactic, public review, legalistic message, chargeback, escalation, or pressure move could backfire. It identifies ethical, practical, relationship, platform, reputational, and legal-risk concerns.
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.