validate

validate is a command for coding agents from benshapyro/cadre-devkit-claude. It costs 4 tokens per session (742 once invoked), scanned A, original, MIT.

An automated pre-release check that detects the project’s programming language and runs relevant type checks, linting, tests, and builds.

In plain words
What is it for?
Use it after code review to check Node.js, TypeScript, Python, Rust, or Go projects before release.
Why use it?
It finds common implementation problems before code is shipped, without making you choose the right commands manually.

Command

Part of the cadre-devkit-claude plugin — 10 skills, 10 commands, 7 agents, 3 hooks shipped together

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.

agentmods
npx agentmods add commands/benshapyro/cadre-devkit-claude/validate
Clone the repo
git clone --depth 1 https://github.com/benshapyro/cadre-devkit-claude

Or install cadre-devkit-claude, the plugin that ships this one along with the rest of its 10 skills, 10 commands, 7 agents, 3 hooks.

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 validate

README.md
[![agentmods](https://agentmods.dev/badge/commands/benshapyro/cadre-devkit-claude/validate.svg)](https://agentmods.dev/commands/benshapyro/cadre-devkit-claude/validate)
Your own site
<a href="https://agentmods.dev/commands/benshapyro/cadre-devkit-claude/validate"><img src="https://agentmods.dev/badge/commands/benshapyro/cadre-devkit-claude/validate.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 742 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00004 $0.00742
Opus 5 $0.00002 $0.00371
Sonnet 5 $0.00001 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 3d ago against content hash 0e7418cf2d09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate 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 3d 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.

commands/validate.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate Command

Purpose: Quantitative validation - runs automated checks (types, lint, tests, build).

Distinct from /review: This command runs automated tooling. Use /review first for qualitative code review (style, security, best practices).

Workflow: /review/validate/ship

Run all validations before shipping code. Automatically detects the project's tech stack and runs only relevant checks.

1. Detect Tech Stack

First, check which config files exist to determine the project type:

  • package.json → Node.js/TypeScript project
  • tsconfig.json → TypeScript
  • pyproject.toml or requirements.txt → Python
  • Cargo.toml → Rust
  • go.mod → Go

Use Glob to check for these files before running language-specific checks.

2. Run Relevant Checks

TypeScript/Node.js (if package.json exists)

Type checking: !npx tsc --noEmit 2>&1 || true

Linting (if lint script exists): !npm run lint 2>&1 || true

Tests: !npm test 2>&1 || true

Build: !npm run build 2>&1 || true

Python (only if pyproject.toml or requirements.txt exists)

Linting: !ruff check . 2>&1 || true

Type checking: !mypy . 2>&1 || true

Tests: !pytest -q 2>&1 || true

Rust (only if Cargo.toml exists)

Check: !cargo check 2>&1 || true

Clippy: !cargo clippy -- -D warnings 2>&1 || true

Tests: !cargo test 2>&1 || true

Go (only if go.mod exists)

Build: !go build ./... 2>&1 || true

Vet: !go vet ./... 2>&1 || true

Tests: !go test ./... 2>&1 || true

3. SelfCheck Protocol

Answer these questions with evidence:

Q1: Are tests passing?

  • Show actual test output
  • Report pass/fail counts

Q2: Are all requirements met?

  • Map requirements to implementation
  • Confirm nothing missed

Q3: No unverified assumptions?

  • External APIs verified
  • Libraries documented

Q4: Is there evidence?

  • Include validation output
  • Show build success

Report Format

## Validation Report

### Tech Stack Detected
[List detected languages/frameworks]

### Type Checking
[✅ Passed / ❌ Failed / ⏭️ Skipped (not applicable)]
[Details if failed]

### Linting
[✅ Passed / ❌ Failed / ⏭️ Skipped (not applicable)]
[Details if failed]

### Tests
[✅ X passed, Y failed / ❌ Failed to run / ⏭️ Skipped]
[Failure details if any]

### Build
[✅ Passed / ❌ Failed / ⏭️ Skipped (not applicable)]
[Details if failed]

### Summary
[READY TO SHIP / NEEDS FIXES]

Read the full file on GitHub · 129 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. 3d ago First seen · 129 lines · 4 tokens per session scan A 0e7418cf2d09

Subscribe to this mod's changes

validate is a command published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 9mo ago), licensed MIT. It adds 4 tokens to every session and 742 once invoked, about $0.0000 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.