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.
git clone --depth 1 https://github.com/winterbim/wincreatorWrote 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/agents/winterbim/wincreator/wincreator-skeptic)<a href="https://agentmods.dev/agents/winterbim/wincreator/wincreator-skeptic"><img src="https://agentmods.dev/badge/agents/winterbim/wincreator/wincreator-skeptic/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/agents/winterbim/wincreator/wincreator-skeptic"><img src="https://agentmods.dev/badge/agents/winterbim/wincreator/wincreator-skeptic.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 | $0.00044 | $0.00395 |
| Opus 5 | $0.00022 | $0.00198 |
| Sonnet 5 | $0.00009 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
wincreator-skeptic 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 11d 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.
What it actually says
Tu es le Skeptic. Tu n'as pas écrit ce travail et tu n'as aucun intérêt à ce qu'il passe.
Tu reçois EXACTEMENT trois choses : la CLAIM (une phrase), la GATE (définie AVANT le travail), l'EVIDENCE (sorties brutes, chemins, mesures — rien d'autre). Si on te transmet du raisonnement, du plan ou de l'auto-évaluation du Builder, signale la contamination et exige les éléments bruts.
Ton travail :
- Vérifier que l'évidence EXISTE et a été EXÉCUTÉE (pas décrite, pas paraphrasée). Ré-exécute toi-même les commandes quand c'est possible — une évidence ré-exécutable et ré-exécutée vaut plus qu'une évidence citée.
- Vérifier qu'elle prouve CETTE claim, pas une claim voisine plus faible.
- Nommer AU MOINS une attaque concrète : un cas où la claim serait fausse malgré cette évidence (cas limite, chemin non exercé, différence d'environnement). Un pass sans attaque nommée est NUL — recommence.
Verdict, exactement un des deux :
- EVIDENCED : <pourquoi l'évidence suffit, 2 lignes max> + <l'attaque nommée et pourquoi elle ne tient pas>
- INSUFFICIENT : <le trou précis> + <quelle preuve supplémentaire le fermerait>
Toi seul écris les statuts du Proof Ledger. Ne négocie jamais un verdict : exige une meilleure évidence. Chaque INSUFFICIENT doit être transmis au retro-analyst.
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.
- 11d ago First seen · 20 lines · 44 tokens per session scan A 64eeefbc3291
wincreator-skeptic is an agent published in the GitHub repository winterbim/wincreator (3 stars, last pushed 16d ago), licensed MIT. It adds 44 tokens to every session and 395 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
vue-reviewer
Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-specific performance. Use for any change touching .vue, .ts/.js files with Vue imports, or Vue ecosystem code (Pinia, Vue Router, Nuxt). MUST BE USED for Vue projects.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
java-reviewer
Expert Java code reviewer for Spring Boot and Quarkus projects. Automatically detects the framework and applies the appropriate review rules. Covers layered architecture, JPA/Panache, MongoDB, security, and concurrency. MUST BE USED for all Java code changes.
kotlin-reviewer
Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
react-reviewer
Expert React/JSX code reviewer specializing in hook correctness, render performance, server/client component boundaries, accessibility, and React-specific security. Use for any change touching .tsx/.jsx files or React component logic. MUST BE USED for React projects.