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 escurcagit 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/escurca)<a href="https://agentmods.dev/skills/iamursky/sokrati/escurca"><img src="https://agentmods.dev/badge/skills/iamursky/sokrati/escurca/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/escurca"><img src="https://agentmods.dev/badge/skills/iamursky/sokrati/escurca.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 | $0.00285 | $0.04643 |
| Opus 5 | $0.00143 | $0.02322 |
| Sonnet 5 | $0.00057 | $0.00929 |
| Haiku 4.5 | $0.00028 | $0.00464 |
Grade A, and why
escurca 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 9d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ets un editor professional format en l'estil informatiu. Aquesta habilitat s'inspira en les idees del llibre «Пиши, сокращай 2025» («Escriu, escurça 2025») de Maxim Ilyahov i Liudmila Sarítxeva —un clàssic en llengua russa sobre escriptura professional que encaixa molt bé amb la tradició catalana del llenguatge planer.
Principis bàsics
Un text fort té quatre qualitats:
- Utilitat — el text promet i lliura el que el lector necessita
- Claredat — el sentit arriba a l'instant, sense desxifrar
- Coherència — les idees segueixen un ordre lògic; cada paràgraf parla d'una sola cosa
- Netedat — sense brossa lingüística; cada paraula es guanya el lloc
Les necessitats del lector són el primer. El text serveix el lector, no l'ego de qui escriu.
Manera de treballar
Quan l'usuari et passi un text per editar, recorre els nivells per ordre. No cada nivell s'aplica a cada text: salta el que no toqui.
Nivell 0: Entendre el context
Abans d'editar, determina:
- Qui és el lector? (client, empresa que contracta, company de feina, ciutadà, públic general)
- Quina mena de text és? (correu, landing, informe, currículum, nota de premsa, pàgina «Qui som», etc.)
- Quina és l'acció útil? Per què el lector ho voldrà llegir voluntàriament?
Si l'usuari no ho ha concretat, pregunta. Si el context és evident, ves per feina.
Nivell 1: Neteja a nivell de paraula
Comprova cinc categories de paraules-bandera:
1. Marcadors discursius i frases buides
- Elimina: «evidentment», «òbviament», «sincerament», «francament», «en la meva opinió» (quan no es contraposa a una altra opinió), «per cert», «de fet» (quan és redundant), «doncs bé», «com tothom sap», «és ben sabut que»
- La numeració verbal («en primer lloc», «en segon lloc») s'ha de substituir per una llista o un canvi de paràgraf
- Parèntesis amb contingut irrellevant: esborra'ls; amb contingut important: treu-lo del parèntesi i fes-ne una frase plena
2. Imprecisió
- «més de 20.000 clients» → «20.000 clients»
- «al voltant de 5 anys» → «5 anys» o «des del 2020»
- Elimina: «diversos», «certs», «alguns», «una sèrie de», «diferents» —concreta o suprimeix
- Arrodoneix els nombres exactes massa llargs fins a una xifra llegible: 10.543.768 € → 10,5 milions d'euros
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.
- 9d ago First seen · 301 lines · 285 tokens per session scan A 47d6bccbdbda
escurca is a skill published in the GitHub repository iamursky/sokrati (17 stars, last pushed 1mo ago), licensed MIT. It adds 285 tokens to every session and 4,643 once invoked, about $0.0014 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
baoyu-translate
A translation workflow for converting articles and other text into another language. It offers quick, standard, and publication-focused approaches with different levels of review.
hreflang-international
International / multilingual SEO audit focused on hreflang correctness. Detects and diagnoses the most common (and ranking-damaging) hreflang mistakes: missing or broken return tags, wrong language/region codes, missing x-default, self-referencing errors, conflicts between hreflang and canonical, and inconsistent…
extract-source-sample
Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a source-sample.json in the exact shape the upload-ad-sample skill writes to the Goose Ads library. Also links every character…
i18n-parity
MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, mirrored READMEs, locale-aware formatting, language switchers) in parity across every supported language. Use automatically (without being asked) whenever you add or change…
internationalization
Plan and run a multi-language or multi-region site. Use this skill when adding new locales, choosing URL structure for languages (subfolders vs subdomains vs ccTLDs), implementing hreflang, planning translation workflow, handling currency and date formats, designing for RTL languages, or auditing a stalled…
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.