00-crafting-kit-core

00-crafting-kit-core is a cursor rule for Cursor from cembasaranoglu/crafting-system-claude. It costs 149 tokens per session, scanned A, original, MIT.

Core project rules for evidence-based coding-agent work, including source inspection, clear status labels, secret handling, and planning risky changes.

In plain words
What is it for?
Use them to guide repository changes, assess unknowns and blockers, plan multi-file work, and report validated, failed, or not-run steps accurately.
Why use it?
They help separate facts from assumptions and stop the agent from claiming that tests, builds, deployments, or reviews happened without evidence.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use them to guide repository changes, assess unknowns and blockers, plan multi-file work, and report validated, failed, or not-run steps accurately.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/cembasaranoglu/crafting-system-claude/00-crafting-kit-core
Install

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.

Clone the repo
git clone --depth 1 https://github.com/cembasaranoglu/crafting-system-claude

Made for: Cursor.

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 00-crafting-kit-core

README.md
[![agentmods](https://agentmods.dev/badge/rules/cembasaranoglu/crafting-system-claude/00-crafting-kit-core/github.svg)](https://agentmods.dev/rules/cembasaranoglu/crafting-system-claude/00-crafting-kit-core)
Your own site
<a href="https://agentmods.dev/rules/cembasaranoglu/crafting-system-claude/00-crafting-kit-core"><img src="https://agentmods.dev/badge/rules/cembasaranoglu/crafting-system-claude/00-crafting-kit-core/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.

agentmods 80×15 button for 00-crafting-kit-core

Your own site · 80×15
<a href="https://agentmods.dev/rules/cembasaranoglu/crafting-system-claude/00-crafting-kit-core"><img src="https://agentmods.dev/badge/rules/cembasaranoglu/crafting-system-claude/00-crafting-kit-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 This file is loaded in full into every session.
When invoked 149 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 $0.00149 $0.00149
Opus 5 $0.00075 $0.00075
Sonnet 5 $0.00030 $0.00030
Haiku 4.5 $0.00015 $0.00015

Measured 5d ago against content hash 9f24b361f9ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

00-crafting-kit-core 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.

cowork/skills/templates-library/references/top-level/cursor/rules/00-crafting-kit-core.mdc · 14 lines

What it actually says

Crafting Kit Core Rule

  • Inspect available source material before making claims.
  • Separate fact, assumption, recommendation, unknown, blocker, not-run validation, failed validation, and validated result.
  • Do not claim tests, builds, packaging, deployment, commits, pushes, production readiness, OSS readiness, or security review unless evidenced.
  • Use stage prompts from prompt-system/prompts/ instead of improvising broad workflows.
  • Keep secrets out of prompts, files, logs, test fixtures, artifacts, commits, and final responses.
  • For risky or multi-file changes, create a plan before editing.
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. 5d ago First seen · 14 lines · 149 tokens per session scan A 9f24b361f9ef

Subscribe to this mod's changes

00-crafting-kit-core is a cursor rule published in the GitHub repository cembasaranoglu/crafting-system-claude (5 stars, last pushed 4mo ago), licensed MIT. It adds 149 tokens to every session, about $0.0007 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 2026-09-03.