validate

validate is a command for Claude Code from ThibautBaissac/rails_ai_agents. It costs 24 tokens per session (2,211 once invoked), scanned A, original, MIT.

A read-only command that checks whether a codebase matches what a feature specification promises. It combines file checks, test-to-requirement mapping, code analysis, and optional acceptance-test generation.

In plain words
What is it for?
Use it after implementing a feature to produce a validation report without changing the implementation files.
Why use it?
It finds requirements that were missed, broken, or changed after implementation, helping detect drift between a specification and the code.

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/thibautbaissac/rails_ai_agents/validate
Clone the repo
git clone --depth 1 https://github.com/ThibautBaissac/rails_ai_agents

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.

agentmods badge for validate

README.md
[![agentmods](https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/validate.svg)](https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/validate)
Your own site
<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/validate"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/validate.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,211 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 $0.00024 $0.02211
Opus 5 $0.00012 $0.01105
Sonnet 5 $0.00005 $0.00442
Haiku 4.5 $0.00002 $0.00221

Measured 5d ago against content hash 2ccd63787741, 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 5d 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/sdd/validate.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Goal

Verify that the codebase implements what the feature specification promises. This command runs AFTER /sdd:implement to detect spec drift — requirements that are unimplemented, broken, or diverged from the spec.

Uses a 4-layer hybrid approach :

  1. Structural scan — Rails convention-based file existence checks
  2. Test coverage mapping — RSpec description and metadata matching
  3. AI semantic analysis — LLM-powered code search for uncovered requirements
  4. Acceptance test generation — On-demand, user-approved

Operating Constraints

READ-ONLY for source code: Do not modify implementation files. The only files this command may write are the validation report (in FEATURE_DIR) and optionally the spec header (to record validation status).

Constitution Authority: If .specify/memory/constitution.md exists, check whether any constitution principles are violated by the implementation.

Execution Steps

1. Initialize Validation Context

Run .specify/scripts/bash/check-prerequisites.sh --json --paths-only from repo root once. Parse JSON for:

  • FEATURE_DIR
  • FEATURE_SPEC
  • TASKS

If FEATURE_SPEC does not exist, abort: "Run /sdd:specify first." For single quotes in args, use escape syntax: e.g 'I'''m Groot' (or double-quote if possible).

2. Load Spec and Extract Requirements

Read FEATURE_SPEC and extract:

  • Functional Requirements: All FR-### identifiers with their full text
  • Success Criteria: All SC-### identifiers with their full text
  • Acceptance Criteria: All Given/When/Then scenarios from user stories
  • Key Entities: Entity names mentioned in the spec

Build an internal requirements inventory — a list of requirement IDs, their text, and the entity/domain they relate to.

Also load:

  • IF EXISTS: .specify/memory/constitution.md for principle validation
  • IF EXISTS: .specify/memory/lessons-learned.md — filter to [phase:implement] or [phase:all]
  • IF EXISTS: FEATURE_DIR/tasks.md — to cross-reference completed tasks with requirements

Read the full file on GitHub · 214 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. 5d ago First seen · 214 lines · 24 tokens per session scan A 2ccd63787741

Subscribe to this mod's changes

validate is a command published in the GitHub repository ThibautBaissac/rails_ai_agents (659 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 2,211 once invoked, about $0.0001 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 2026-08-30.