Borrowing it
Nothing to install: this file belongs to benshapyro/cadre-devkit-claude. 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/benshapyro/cadre-devkit-claude/main/CLAUDE.mdgit clone --depth 1 https://github.com/benshapyro/cadre-devkit-claudeWrote 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/benshapyro/cadre-devkit-claude/claude-md)<a href="https://agentmods.dev/instructions/benshapyro/cadre-devkit-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/benshapyro/cadre-devkit-claude/claude-md.svg" alt="Measured on agentmods" 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 | $0.01312 | $0.01312 |
| Opus 5 | $0.00656 | $0.00656 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade D, and why
cadre-devkit-claude CLAUDE.md scanned grade D with 2 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 7d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Dangerous Command Blocker**: Prevents `rm -rf /`, `chmod 777`, force push, etc. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Dangerous Command Blocker**: Prevents `rm -rf /`, `chmod 777`, force push, etc. How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cadre DevKit for Claude Code
This plugin provides a comprehensive productivity and quality system for Claude Code.
Features
Pre-Implementation Confidence Check
Before starting ANY non-trivial implementation, assess confidence across 5 criteria (0.0-1.0 scale):
Assessment Criteria
| Criterion | Weight | Key Questions |
|---|---|---|
| Requirements Clarity | 25% | Are requirements explicit? Acceptance criteria defined? Edge cases identified? |
| Technical Feasibility | 25% | Is approach verified? APIs available? Stack compatible? |
| Dependency Verification | 20% | Dependencies accessible? Versions compatible? Infrastructure ready? |
| Test Strategy | 15% | How will this be tested? Tools available? Test cases defined? |
| Risk Assessment | 15% | Failure modes known? Mitigation defined? Rollback possible? |
Decision Matrix
| Overall Score | Status | Action |
|---|---|---|
| ≥0.90 | GREEN | Proceed with implementation |
| 0.70-0.89 | YELLOW | Investigate alternatives, clarify ambiguity, document assumptions |
| <0.70 | RED | STOP - Ask clarifying questions, research unknowns, then re-assess |
Enforcement
NEVER proceed with confidence <0.90 without explicit user approval.
If confidence is below 0.90:
- State current confidence score with breakdown
- Identify weak areas (any criterion <0.80)
- Ask specific questions OR conduct research
- Recalculate after new information
- Only proceed when ≥0.90 or user explicitly approves lower confidence
When to Skip
Skip confidence check for:
- Simple edits (typos, formatting, comments)
- Direct user instructions with clear scope
- Tasks where requirements are already verified in conversation
Post-Implementation SelfCheck
After completing ANY non-trivial implementation, answer these 4 questions with evidence:
Q1: Are tests passing?
- Provide actual test output (not "tests pass" without proof)
- Show test command executed and pass/fail counts
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.
- 7d ago First seen · 162 lines · 1,312 tokens per session scan D 22e4b02b10fe
cadre-devkit-claude CLAUDE.md is an instructions file published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 9mo ago), licensed MIT. It adds 1,312 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
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).
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.
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.
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).
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.