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 agentmods add skills/0xharryriddle/hermes-pmxt/skillnpx skills add 0xharryriddle/hermes-pmxt --skill skillgit clone --depth 1 https://github.com/0xharryriddle/hermes-pmxtWrote 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/0xharryriddle/hermes-pmxt/skill)<a href="https://agentmods.dev/skills/0xharryriddle/hermes-pmxt/skill"><img src="https://agentmods.dev/badge/skills/0xharryriddle/hermes-pmxt/skill.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.01749 |
| Opus 5 | $0.00010 | $0.00874 |
| Sonnet 5 | $0.00004 | $0.00350 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
pmxt 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 5d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pmxt -- Prediction Markets for Hermes
Real-time access to prediction markets for fact-checking, probability analysis, arbitrage detection, execution planning, and portfolio inspection.
When to Use
- User asks "What's the probability of X?" or "Is X likely to happen?"
- User wants trending prediction markets
- User wants arbitrage opportunities across exchanges
- User wants to place or manage trades
- User wants to check positions or balance
Setup
Install from PyPI. This brings in pmxt>=2.50.0; do not instruct users to clone
the repo unless they are developing the integration.
pip install hermes-pmxt
# Check runtime status
python3 -c "from hermes_pmxt import pmxt_runtime_status; print(pmxt_runtime_status())"
Hosted mode (recommended): set PMXT_API_KEY env var. Local sidecar mode works
without an API key but requires pmxt-core running on localhost:3847.
If Hermes needs an explicit skill install, install this file to
~/.hermes/skills/pmxt/SKILL.md or use your Hermes skill/plugin installer with the
GitHub URL https://github.com/0xharryriddle/hermes-pmxt. Upgrade with
pip install --upgrade hermes-pmxt.
Quick Reference
All tools are in the hermes_pmxt package. Import and call from execute_code:
from hermes_pmxt import pmxt_search, pmxt_quote, pmxt_order_book, pmxt_call
| Function | Auth | Description |
|---|---|---|
pmxt_search(query, exchange?, limit?, sort?, search_in?, slug?) |
Mode-dep | Search markets |
pmxt_events(query, exchange?, limit?, sort?, search_in?, slug?) |
Mode-dep | Search event groups |
pmxt_quote(keyword, exchange) |
Mode-dep | Get YES/NO probabilities |
pmxt_order_book(outcome_id, exchange, limit?) |
Mode-dep | Order book depth |
pmxt_ohlcv(outcome_id, exchange, res?, limit?) |
Mode-dep | Price candles |
pmxt_trades(outcome_id, exchange, limit?) |
Mode-dep | Recent trades |
pmxt_execution_price(outcome_id, exchange, side, amount) |
Mode-dep | Slippage estimate |
pmxt_compare_market(query, exchanges?, limit?) |
Mode-dep | Cross-exchange comparison |
pmxt_arbitrage_scan(query, exchanges?, threshold?) |
Mode-dep | Cross-exchange spreads |
pmxt_balance(exchange) |
Yes | Account balance |
pmxt_positions(exchange) |
Yes | Open positions |
pmxt_portfolio(exchanges?) |
Yes | Unified balances and positions |
pmxt_build_order(...) |
Yes | Build/sign order (SAFE, does NOT submit) |
pmxt_submit_order(built, exchange, confirmed=True) |
Yes | Submit a pre-built order |
pmxt_cancel_order(order_id, exchange, confirmed=True) |
Yes | Cancel an open order |
pmxt_call(method, exchange, ...) |
Varies | Generic PMXT API call |
pmxt_runtime_status() |
No | Runtime diagnostics |
pmxt_list_exchanges() |
No | Known/available exchanges |
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.
- 5d ago First seen · 171 lines · 21 tokens per session scan A 84889d14d283
pmxt is a skill published in the GitHub repository 0xharryriddle/hermes-pmxt (23 stars, last pushed 26d ago), licensed MIT. It adds 21 tokens to every session and 1,749 once invoked, about $0.0001 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
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.