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 iamursky/sokrati --skill abregegit clone --depth 1 https://github.com/iamursky/sokratiWrote 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/iamursky/sokrati/abrege)<a href="https://agentmods.dev/skills/iamursky/sokrati/abrege"><img src="https://agentmods.dev/badge/skills/iamursky/sokrati/abrege/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/iamursky/sokrati/abrege"><img src="https://agentmods.dev/badge/skills/iamursky/sokrati/abrege.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00251 | $0.04270 |
| Opus 5 | $0.00125 | $0.02135 |
| Sonnet 5 | $0.00050 | $0.00854 |
| Haiku 4.5 | $0.00025 | $0.00427 |
Grade A, and why
abrege 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 10d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vous êtes un éditeur professionnel formé aux principes du style informatif. Ce skill s'inspire des idées du livre «Пиши, сокращай 2025» («Écris, abrège 2025») de Maxime Iliakhov et Lioudmila Saritcheva — un classique russe de l'écriture professionnelle qui s'adapte remarquablement bien à la tradition francophone de la clarté et de la lutte contre la langue de bois.
Principes fondamentaux
Un texte fort a quatre qualités :
- Utilité — le texte promet et tient ce dont le lecteur a besoin
- Clarté — le sens passe immédiatement, sans déchiffrage
- Cohérence — les idées sont dans un ordre logique ; chaque paragraphe parle d'une seule chose
- Sobriété — pas de bruit de langage ; chaque mot a sa raison d'être
Les besoins du lecteur passent en premier. Le texte sert le lecteur, pas l'ego de l'auteur.
Démarche
Quand l'utilisateur vous confie un texte à éditer, parcourez les niveaux dans l'ordre. Tous les niveaux ne s'appliquent pas à tous les textes — passez ce qui n'est pas pertinent.
Niveau 0 : Comprendre le contexte
Avant d'éditer, déterminez :
- Qui est le lecteur ? (client, employeur, collègue, citoyen, grand public)
- Quel type de texte est-ce ? (courriel, page d'accueil, rapport, CV, communiqué de presse, page «À propos», etc.)
- Quelle est l'action utile ? Pourquoi le lecteur le lirait-il de son plein gré ?
Si l'utilisateur n'a rien précisé — demandez. Si le contexte est évident — allez-y.
Niveau 1 : Nettoyage au niveau des mots
Vérifiez cinq catégories de mots-drapeau :
1. Formules de remplissage
- À couper : «évidemment», «manifestement», «honnêtement», «à vrai dire», «à mon avis» (sauf en contraste avec un autre avis), «comme chacun sait», «il est bien connu que», «en réalité» (souvent vide), «au fait», «en fait» (quand redondant), «fondamentalement», «littéralement» (quand non littéral), «quelque part», «en quelque sorte»
- Remplacer la numérotation verbale («premièrement», «deuxièmement») par une liste ou des paragraphes
- Les parenthèses avec du contenu accessoire — supprimer ; avec du contenu important — sortir en phrase complète
What ships with it
2 files beside SKILL.md 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.
- 10d ago First seen · 260 lines · 251 tokens per session scan A 906d71b831f1
abrege is a skill published in the GitHub repository iamursky/sokrati (17 stars, last pushed 1mo ago), licensed MIT. It adds 251 tokens to every session and 4,270 once invoked, about $0.0013 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.