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/ai-swiss/base/preparer-evaluationnpx skills add ai-swiss/base --skill preparer-evaluationgit clone --depth 1 https://github.com/ai-swiss/baseWrote 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/ai-swiss/base/preparer-evaluation)<a href="https://agentmods.dev/skills/ai-swiss/base/preparer-evaluation"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/preparer-evaluation.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 5.1 | $0.00028 | $0.01279 |
| Opus 5 | $0.00014 | $0.00639 |
| Sonnet 5 | $0.00006 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
preparer-evaluation 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Préparer une évaluation
Préparer une évaluation alignée sur une séquence: reprendre les objectifs, construire la grille de critères et le barème, rédiger les tâches et un corrigé proposé. L'assistant prépare le matériel d'évaluation; évaluer les élèves demeure un acte de l'enseignant.
Inputs
Demande à l'utilisateur:
- La séquence concernée: pour la lire dans
sequences/ - Le type d'évaluation: formative (pour apprendre) ou sommative (pour attester)
- La durée et le format: écrit, oral, travail pratique
Si aucune séquence n'existe pour ce sujet, demande directement les objectifs visés, ou propose de préparer d'abord la séquence.
Lis la compétence skills/competences/metier-enseignement/SKILL.md pour l'alignement et le feedback.
Si .ai/journal/ contient des entrées récentes, lis-les pour le contexte.
Étapes
1. Reprendre les objectifs
Lis la séquence dans sequences/ et résume:
«Pour rappel, la séquence [titre] vise ces objectifs: [liste]. Lesquels voulez-vous évaluer? Tous, ou une sélection?»
← Reformulation
2. Vérifier l'alignement
Pour chaque objectif évalué, vérifie qu'une activité de la séquence l'a effectivement travaillé. Signale tout écart:
«[ATTENTION: l'objectif 3 n'a été travaillé que dans le prolongement pour élèves avancés. L'évaluer pour toute la classe serait inéquitable.] On le garde, on l'adapte, ou on le retire?»
← Reformulation
3. Construire la grille de critères
Propose une grille reliant chaque objectif à des critères observables:
«Voici la grille que je propose:
Objectif évalué Critère observable Points [objectif 1] [ce qu'une réussite montre concrètement] [n] [objectif 2] [critère] [n] Les critères sont-ils justes et observables?»
← Reformulation
4. Barème
Propose la répartition des points et le seuil de suffisance, marqués [A VALIDER: ...]:
«[A VALIDER: total de 30 points, seuil de suffisance à 18 points, conformément à votre pratique habituelle]. Le barème final relève de votre responsabilité et des règles de votre établissement. Cette répartition vous convient-elle?»
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 · 118 lines · 28 tokens per session scan A 99211ec4ba31
preparer-evaluation is a skill published in the GitHub repository ai-swiss/base (43 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 1,279 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
academic-leadership-advisor
Strategic thinking partner and document drafter for university leadership decisions, academic policy, accreditation, and institutional governance.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).