What is cadre-devkit-claude CLAUDE.md?

A set of Claude Code development instructions that requires a confidence check before substantial implementation work. The check covers requirements, technical approach, dependencies, testing, and risks.

Use it to assess whether an implementation is ready to start, decide whether to proceed or investigate further, and document assumptions or rollback plans.

It helps identify unclear requirements, unavailable dependencies, weak test plans, and likely failure points before coding begins.

How benshapyro/cadre-devkit-claude configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/benshapyro/cadre-devkit-claude/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/benshapyro/cadre-devkit-claude

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/benshapyro/cadre-devkit-claude/claude-md/github.svg)](https://agentmods.dev/instructions/benshapyro/cadre-devkit-claude/claude-md)

Your own site

<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/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,312 This file is loaded in full into every session.

When invoked 1,312 The same file — it is already loaded in full.

Security scan D 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.01312	$0.01312
Opus 5.5	$0.00525	$0.00525
Sonnet 5.5	$0.00262	$0.00262
Haiku 4.5	$0.00131	$0.00131

Measured 2mo ago against content hash 22e4b02b10fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

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.

CLAUDE.md · 162 lines

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

Read the full file on GitHub · 162 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.

2mo ago First seen · 162 lines · 1,312 tokens per session scan D 22e4b02b10fe

Subscribe to this mod's changes

cadre-devkit-claude CLAUDE.md is an instructions file published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 11mo ago), licensed MIT. It adds 1,312 tokens to every session, about $0.0052 per session on Opus 5.5. 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.

Planning

cadre-devkit-claude CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cadre-devkit-claude CLAUDE.mdbenshapyro/cadre-devkit-claude	Instructions file	9	11mo ago	MIT	D	1,312	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	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

cadre-devkit-claude: Instructions file for Claude Code