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 OPTIMETA/PAIDEIA --skill alt-importgit clone --depth 1 https://github.com/OPTIMETA/PAIDEIAWrote 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/optimeta/paideia/alt-import)<a href="https://agentmods.dev/skills/optimeta/paideia/alt-import"><img src="https://agentmods.dev/badge/skills/optimeta/paideia/alt-import/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/optimeta/paideia/alt-import"><img src="https://agentmods.dev/badge/skills/optimeta/paideia/alt-import.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Prompt Injection · line 20 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00088 | $0.01888 |
| Opus 5.5 | $0.00035 | $0.00755 |
| Sonnet 5.5 | $0.00018 | $0.00378 |
| Haiku 4.5 | $0.00009 | $0.00189 |
Grade A, and why
alt-import 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
alt-import
Exam Radar is OPTIMETA's Alt plugin. From lecture-recording transcripts it extracts the topics a professor verbally emphasized, ranks them by exam probability, and lets the user triage each into one of three zones. Its 복사 button emits a fixed markdown form. This skill ingests that form.
PAIDEIA already has one exam-probability signal — HW density (course-index/coverage.md). Exam Radar adds a second, independent one — lecture emphasis. The two corroborate where they agree and expose blind spots where they diverge.
Premise (do not break). HW density remains the primary Exam tier. Lecture emphasis is layered on as annotation and a second opinion — it is surfaced, never substituted. As with a user-declared weak zone, a single lecture signal does not auto-upgrade an HW-based tier (mirror course-builder's rule). What it does is flag divergences for the user to judge.
1. The export format (exam-radar:v1)
# Exam Radar 작전 — <course>
<!-- exam-radar:v1 source=alt -->
- 코스: <course>
- 시험까지: <D-N>
- 토픽: 총 <N>개 (골드존 <G> · 버려도 안전 <D>)
- 버려도 안전 비중: 전체의 <P>%
## 지금 할 것 — 골드존 (시험확률 높음 · 아직 약함)
1. <topic> · 시험확률 <p>%[ · 🎙]
...
## 이미 다진 것 (잘 알거나 시험에 덜 나옴)
- <topic> · 시험확률 <p>%
...
## 버려도 안전 (안 해도 되는 것)
- <topic> · 시험확률 <p>%
...
Parse rules:
- Detect by the
<!-- exam-radar:v1marker. Parse thevNinteger; if> 1, warn and parse the v1 fields best-effort (ignore unknown ones). - Meta: read
- 코스:,- 시험까지:(D-N), and the count line. - Zones: three
##headings →지금 할 것 — 골드존→ zonegold(high exam-prob, low self-confidence).이미 다진 것→ zonestrong(already known or low exam-prob).버려도 안전→ zoneskip(safe to drop).
- Each topic line:
<name> · 시험확률 <p>%, optionally· 🎙(the professor verbally stressed it). The leading1./-is just list markup. Parsename, integerp(0–100), and the🎙flag. - Be lenient on whitespace and the leading marker. A zone with
(없음)/(아직 없음 …)is empty.
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 · 140 lines · 88 tokens per session scan A 4f3e5b3b929a
alt-import is a skill published in the GitHub repository OPTIMETA/PAIDEIA (91 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 1,888 once invoked, about $0.0004 per session on Opus 5.5. 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
cortex-integrate
Design and implement an AI feature integration — model selection, architecture pattern, system prompt, data flow, error handling, cost estimate. Use when asked to "add AI to this", "LLM integration", "add Claude/GPT", or "AI-powered feature".
cortex-prompt
Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval criteria. Use when asked to "prompt engineering", "build a prompt", "write a system prompt", or "improve this prompt".
cortex-eval
Evaluate model performance — check for accuracy drops, data drift, and error patterns. Use when asked about "model accuracy dropped", "evaluate the model", "check for drift", or "model performance".
cortex-recon
ML reconnaissance — inventory all models, pipelines, data sources, and monitoring. Use when asked "what ML do we have", "model inventory", or "ML assessment".
atlas-onboard
Generate onboarding documentation — what this project does, how to set up locally, where things live, key decisions, how to deploy. Written for day-one engineers who know nothing. Use when asked for "onboarding docs", "new engineer guide", "how to get started", or "developer setup".
cortex-model
Build an ML pipeline — from data to trained model to serving endpoint. Use when asked to "build ML model", "train a model", "prediction pipeline", "classification", or "regression".