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.
git clone --depth 1 https://github.com/mturac/hermes-supercode-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/plugins/mturac/hermes-supercode-skills/prediction-alpha)<a href="https://agentmods.dev/plugins/mturac/hermes-supercode-skills/prediction-alpha"><img src="https://agentmods.dev/badge/plugins/mturac/hermes-supercode-skills/prediction-alpha/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/plugins/mturac/hermes-supercode-skills/prediction-alpha"><img src="https://agentmods.dev/badge/plugins/mturac/hermes-supercode-skills/prediction-alpha.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
prediction-alpha 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 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.
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.
What it actually says
{
"name": "prediction-alpha",
"type": "skill",
"path": "skills/prediction-alpha",
"description": "Prediction market analysis, odds, arbitrage detection"
}What it installs
The manifest is a name and a version. 13 skills travel with it, and installing the plugin installs all of them — 1,828 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill auth-architect A 166 tokens
- Skill db-whisperer A 131 tokens
- Skill obs-guardian A 165 tokens
- Skill api-sculptor A 143 tokens
- Skill prompt-forge A 129 tokens
- Skill quantum-debugger A 143 tokens
- Skill security-sentinel A 146 tokens
- Skill deploy-ninja A 147 tokens
- Skill ghost-scraper A 139 tokens
- Skill mcp-conductor A 133 tokens
- Skill pipeline-architect A 148 tokens
- Skill prediction-alpha A 129 tokens
- Skill infra-automation A 109 tokens
What ships with it
1 file beside marketplace.json#prediction-alpha 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.
- 1mo ago First seen · 6 lines scan A 5499a0616e3f
prediction-alpha is a plugin published in the GitHub repository mturac/hermes-supercode-skills (2 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
sox-itgc
SOX ITGC advisor — the four IT general control domains auditors test for SOX 404 (access, change management, operations, development), system scoping, risk-and-control matrices, control narratives and test scripts, deficiency evaluation (AS 2201 / Reg S-X ladder), remediation planning, filer-status and IPO timelines…
geldwaesche-aml-kyc
Geldwäsche- und Terrorismusfinanzierungs-Prävention aus deutscher Praxisperspektive – GwG-Risikoanalyse § 5 (Methodik, Risikokategorien, Aktualisierung), KYC-Identifikationspflicht §§ 10 ff. mit wirtschaftlich Berechtigtem §§ 3 ff. und Transparenzregister, Verdachtsmeldung an die FIU § 43 inklusive § 46…
kostenrecht-rvg
Anwaltsvergütung und Verfahrenskosten aus Praxisperspektive – Gegenstandswert §§ 22, 23 RVG i.V.m. §§ 3 ff. ZPO, Wertgebühr § 13 RVG mit Anlage 2, VV RVG (2300 Geschäftsgebühr mit Schwellengebühr 1,3 und § 14 RVG, 3100 Verfahrensgebühr, 3104 Terminsgebühr, 1000/1003 Einigungsgebühr, Anrechnung Vorbem. 3 Abs. 4 VV…
kapitalmarktrecht
Deutsches Kapitalmarktrecht im engeren Sinne – Wertpapier- und Emittentenrecht: WpHG/MAR (Marktmissbrauch, Insiderhandel, Ad-hoc-Publizität, Directors' Dealings, Stimmrechtsmeldungen), Prospekt-VO (EU) 2017/1129 iVm WpPG (Prospektpflicht, Ausnahmen, BaFin-Billigung, Prospekthaftung) und WpÜG (Pflichtangebot, Acting in.
insolvenzrecht
Insolvenzrecht und Sanierungsrahmen. Insolvenzantragspflicht § 15a InsO, StaRUG-Restrukturierungsplan, 13-Wochen-Liquiditätsplanung, positive Fortbestehensprognose, Zahlungsunfähigkeit und Überschuldung §§ 17, 19 InsO.
bankrecht
Bank- und Kapitalmarktrecht (Fachanwaltschaft). Kreditvertragsprüfung, Verbraucherdarlehen §§ 491 ff. BGB, Anlageberatung WpHG, MiFID II, Bauspar-/Hypothekenrecht.