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/programming-pupil/aos/super-adversarialnpx skills add programming-pupil/aos --skill super-adversarialgit clone --depth 1 https://github.com/programming-pupil/aosWrote 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/programming-pupil/aos/super-adversarial)<a href="https://agentmods.dev/skills/programming-pupil/aos/super-adversarial"><img src="https://agentmods.dev/badge/skills/programming-pupil/aos/super-adversarial.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 | $0.00000 | $0.00622 |
| Opus 5 | $0.00000 | $0.00311 |
| Sonnet 5 | $0.00000 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade C, and why
super-adversarial scanned grade C with 1 finding 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 4d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- aos:section initial-system --> The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 55 lines · 0 tokens per session scan C 179619753ad3
super-adversarial is a skill published in the GitHub repository programming-pupil/aos (37 stars, last pushed 5d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 622 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
workflow_creation
Build a new Rome workflow app — one action whose body is a single async function that implements its control flow in plain TypeScript (await, if, for, Promise.all) and calls existing actions (including system:summon). Use whenever the user describes a multi-step automation OR asks an LLM to produce something from…
add-oauth-integration
Add a new Rome-managed OAuth integration for a third-party service so a user can delegate access by clicking Connect, and Rome can act on the service with the delegated token (the GitHub/Slack model — brokered by Pantheon, NOT Composio). Use when asked to "add an integration / connector for ", "let users connect their…
routine-from-chat
Turn a plain-language "do this automatically" request into a routine — either event-triggered ("text me when I get an email from my landlord") or scheduled ("remind me every Friday at 9am"). For third-party events (Gmail, GitHub, Slack…) it confirms with the guardian and then subscribes to the connector trigger so the…
color-audit
Audit a design system's color palette against measurable color-science disciplines — WCAG/APCA contrast of declared token pairs, perceptual (OKLCH) ramp uniformity, color-blindness safety of status/categorical sets, token architecture (primitives → semantic → components), dark-mode integrity, and hue budget — and…
secondary-text-audit
Audit the subordinate copy in a UI — section descriptions, field helper text, hints, card subtitles, empty-state body copy, tooltip bodies — against the secondary-text ruleset, and emit a per-string keep/rewrite/delete verdict table a coding agent can apply. Use this skill whenever the user asks to review, tighten…
app_creation
Scaffold a brand-new Rome app from a bundled template into an independent, git-versioned source directory and install it from there. Use for genuinely app-shaped software — something with its own user-edited data model, several distinct operations, or a conversational/long-lived agent. FIRST apply the litmus in "Is…