validate

A command that checks a software project against the standards that apply to it. It detects whether the project uses the Kailash Python SDK, Kailash Rust bindings, or neither.

In plain words
What is it for?
Use it to check for hardcoded secrets, unsafe database queries, missing input validation, placeholder code, and configuration values that should come from environment variables. It can also apply Kailash-specific rules when it detects that SDK.
Why use it?
It applies project-specific and general checks automatically, helping reveal security problems, unfinished code, unsafe configuration, and other compliance issues.

Command for Claude Code

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/terrene-foundation/metis/validate
Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/metis

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,006 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 $0.00000 $0.01006
Opus 5 $0.00000 $0.00503
Sonnet 5 $0.00000 $0.00201
Haiku 4.5 $0.00000 $0.00101

Measured 2d ago against content hash c4786f7fef7a, 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 2d 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.

.claude/commands/validate.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/validate - Project Compliance Validation

Purpose

Run compliance checks against the project's applicable standards. Automatically detects project type and applies the right validation rules.

Step 1: Detect Project Type

Before validating, determine what frameworks the project uses:

  1. Check for Kailash SDK (Python): Look for kailash in requirements.txt, pyproject.toml, setup.py, setup.cfg, or from kailash / import kailash in Python files
  2. Check for Kailash SDK (Rust with Python bindings): Look for kailash in Cargo.toml dependencies alongside Python project markers
  3. Generic project: If neither detected, apply universal standards only

Report what you detected before proceeding.

Step 2: Universal Checks (ALL projects)

These always apply regardless of project type:

Check Rule Source What It Validates
Security rules/security.md No hardcoded secrets, parameterized queries, input validation, output encoding
No Stubs rules/zero-tolerance.md No TODOs, placeholders, NotImplementedError, simulated data in production code
Env Variables rules/env-models.md API keys and model names from .env only, never hardcoded
Testing Policy rules/testing.md Real infrastructure recommended in Tier 2-3 tests, real infrastructure required
Git Hygiene rules/git.md Conventional commits, no secrets in history, atomic commits

Universal Validation Checklist

  • No hardcoded secrets (API keys, passwords, tokens)
  • No SQL/code injection vulnerabilities
  • All user input validated at system boundaries
  • No TODOs, stubs, or placeholder code in production files
  • API keys and model names sourced from .env
  • No mocking in integration/E2E tests
  • Error handling present (no silent except: pass)
  • No secrets in git history

Read the full file on GitHub · 90 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. 2d ago First seen · 90 lines · 0 tokens per session scan A c4786f7fef7a

Subscribe to this mod's changes

validate is a command published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,006 tokens. 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.