Borrowing it
Nothing to install: this file belongs to i74ifa/role-craft. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/i74ifa/role-craft/main/CLAUDE.mdgit clone --depth 1 https://github.com/i74ifa/role-craftWrote 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/instructions/i74ifa/role-craft/claude-md)<a href="https://agentmods.dev/instructions/i74ifa/role-craft/claude-md"><img src="https://agentmods.dev/badge/instructions/i74ifa/role-craft/claude-md/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/instructions/i74ifa/role-craft/claude-md"><img src="https://agentmods.dev/badge/instructions/i74ifa/role-craft/claude-md.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 | $0.01351 | $0.01351 |
| Opus 5.5 | $0.00540 | $0.00540 |
| Sonnet 5.5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
role-craft 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 2mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this package is
i74ifa/role-craft is a Laravel package that auto-generates spatie/laravel-permission permissions (and a default role) from Eloquent models found under app/Models/. It ships two artisan commands and a small set of helpers — no runtime services. PHP 8.4+, Laravel 12/13, Spatie Permission 7+.
Distributed as a Composer library; consumers composer require i74ifa/role-craft and optionally php artisan vendor:publish --tag=role-craft-config.
Commands
composer test # vendor/bin/phpunit (all suites)
composer test-coverage # HTML coverage report → ./coverage
vendor/bin/phpunit --testsuite Unit
vendor/bin/phpunit --testsuite Feature
vendor/bin/phpunit --filter ModelHelperExclusionTest # one class
vendor/bin/phpunit --filter test_wildcard_matches_subdirectory # one method
There is no lint/format step configured. The test bootstrap uses an in-memory SQLite database via Orchestra Testbench — no external DB needed.
Architecture
The package is intentionally tiny. The "big picture" is in three files:
src/RoleCraftServiceProvider.php— registers the two artisan commands and publishes config under tagrole-craft-config. UsesmergeConfigFrom, so new config keys ship as safe defaults without forcing a republish.src/Console/Commands/RoleCraftCommand.php(role-craft:generate) — the bootstrapper. Resolves the role (creates if missing), resolves the model list (--models=...shorthand orModelHelper::getAll()), then for each model × each action creates the permission if missing. Gotcha: it calls$role->syncPermissions($createdPermissions)with the newly created permissions only — a second run with nothing new effectively empties the role. Treatgenerateas a one-shot bootstrap; userole-craft:syncfor idempotent role assignment.src/Console/Commands/RoleCraftSyncCommand.php(role-craft:sync) — the idempotent assignment tool.--allshort-circuits toPermission::all(). Without it, the same model-resolution path is used (--models=or directory scan).
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.
- 2mo ago First seen · 70 lines · 1,351 tokens per session scan A de47a443282a
role-craft CLAUDE.md is an instructions file published in the GitHub repository i74ifa/role-craft (4 stars, last pushed 5mo ago), licensed MIT. It adds 1,351 tokens to every session, about $0.0054 per session on Opus 5.5. 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.
role-craft CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| role-craft CLAUDE.mdi74ifa/role-craft | Instructions file | 4 | 5mo ago | MIT | A | 1,351 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 280k | 2d ago | MIT | A | 4,325 | Codex, OpenCode |