agentmods.dev

wincreator: Instructions file for Claude Code

CLAUDE.md

wincreator CLAUDE.md is an instructions file for Claude Code from winterbim/wincreator. It costs 574 tokens per session, scanned A, original, MIT.

Repository instructions for WinCreator, a workflow for evolving the project through classification, review and recorded evidence. They describe the required roles, verdicts and rules for changing the workflow itself.

In plain words
What is it for?
Classifying work, recording proof for claims, handling failed reviews, running retrospectives and proposing controlled updates to the WinCreator process.
Why use it?
They make non-trivial changes traceable and require claims to be checked by a separate reviewer instead of accepted by the same agent that made them.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is winterbim/wincreator's own configuration. It tells Claude Code how to work on wincreator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wincreator configures →

not rated 3repo 12d ago A scan 574 tokens original MIT
View source ↗ winterbim/wincreator skills.sh
Reuse

Borrowing it

Nothing to install: this file belongs to winterbim/wincreator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/winterbim/wincreator/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/winterbim/wincreator

Made for: Claude Code.

Wrote 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.

agentmods badge for wincreator CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/winterbim/wincreator/claude-md.svg)](https://agentmods.dev/instructions/winterbim/wincreator/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/winterbim/wincreator/claude-md"><img src="https://agentmods.dev/badge/instructions/winterbim/wincreator/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 574 This file is loaded in full into every session.
When invoked 574 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00574 $0.00574
Opus 5 $0.00287 $0.00287
Sonnet 5 $0.00115 $0.00115
Haiku 4.5 $0.00057 $0.00057

Measured 8d ago against content hash 7704ad26ccd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wincreator CLAUDE.md 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 8d 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.

CLAUDE.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — wincreator repository

The skill lives in skill/wincreator/. Paths below are relative to that skill root unless stated otherwise; project-level machinery (.claude/agents/, EVOLUTION_QUEUE.md, this file) lives at the repo root.

WinCreator — boucle d'évolution active

  • Toute tâche non triviale suit wincreator (classification, gate annoncée, Panel).
  • Chaque claim est validée par le subagent wincreator-skeptic (jamais d'auto-notation).
  • À chaque verdict INSUFFICIENT et à chaque fermeture de boucle Meso+ : invoquer wincreator-retro-analyst.
  • Quand EVOLUTION_QUEUE.md contient ≥1 proposition avec pattern confirmé, OU tous les 10 catches, OU sur demande : invoquer wincreator-skill-surgeon (une proposition = une boucle Meso).
  • Jamais de réécriture du skill hors de ce circuit. Les invariants (les 8 statuts, Builder/Skeptic, no-upward-propagation, Two-Failure) ne bougent qu'avec waiver explicite de l'utilisateur. Le passage de 4 à 8 statuts (DISPROVEN, SUPERSEDED, BLOCKED, INSUFFICIENT) est couvert par le waiver de l'audit du 2026-08-02.
  • Une preuve se capture puis se révise : utiliser wincreator.py prove <ID> -- <commande>, puis wincreator.py review <ID> --verdict ... --reviewer .... Un code retour nul ne devient pas EVIDENCED sans review en Standard/Regulated.

Fichiers de la boucle (chemins réels dans ce dépôt)

  • Catches capitalisés : skill/wincreator/SKEPTIC_CATCHES.md
  • File de propositions : EVOLUTION_QUEUE.md (racine du dépôt)
  • Gate mécanique : python3 skill/wincreator/scripts/ledger_check.py (--self-test avant de faire confiance à la gate)
  • Capture/review : python3 skill/wincreator/scripts/wincreator.py prove, puis review, puis verify (--self-test avant confiance)
  • Conformité du package : python3 skill/wincreator/scripts/package_check.py skill/wincreator

La chaîne complète : usage réel → catch (Skeptic) → capitalisation (Retro-Analyst) → récurrence prouvée → proposition → chirurgie gated (Surgeon) → skill vN+1 → usage réel. La télémétrie de l'amélioration, c'est SKEPTIC_CATCHES.md : pas de catches, pas d'évolution.

Read the full file on GitHub · 30 lines

Changes

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.

  1. 8d ago First seen · 30 lines · 574 tokens per session scan A 7704ad26ccd3

Subscribe to this mod's changes

wincreator CLAUDE.md is an instructions file published in the GitHub repository winterbim/wincreator (3 stars, last pushed 12d ago), licensed MIT. It adds 574 tokens to every session, about $0.0029 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.

Claude CodeLLMPlanningagent-skillsai-agentsclaude-skillsdeveloper-tools
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens