sdd-validate

sdd-validate is a skill for Claude Code, Codex from rubenzarroca/sdd-plugin. It costs 67 tokens per session (3,336 once invoked), scanned A, original, MIT.

A specification checker that compares an implemented feature with its written requirements. It reviews coverage, unused code, project rules, and consistency between layers, using a deterministic check when the supporting server is available.

In plain words
What is it for?
Use it after implementation or when asked to validate a feature, compare the specification with the code, check for drift, or confirm that work is complete.
Why use it?
It reveals missing requirements and differences between the planned behavior and the code before the feature is considered finished.

Skill for Claude CodeCodex

Part of the sdd plugin — 12 skills 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 skills/rubenzarroca/sdd-plugin/sdd-validate
Any agent
npx skills add rubenzarroca/sdd-plugin --skill sdd-validate
Clone the repo
git clone --depth 1 https://github.com/rubenzarroca/sdd-plugin

Made for: Claude Code, Codex.

Or install sdd, the plugin that ships this one along with the rest of its 12 skills.

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 sdd-validate

README.md
[![agentmods](https://agentmods.dev/badge/skills/rubenzarroca/sdd-plugin/sdd-validate.svg)](https://agentmods.dev/skills/rubenzarroca/sdd-plugin/sdd-validate)
Your own site
<a href="https://agentmods.dev/skills/rubenzarroca/sdd-plugin/sdd-validate"><img src="https://agentmods.dev/badge/skills/rubenzarroca/sdd-plugin/sdd-validate.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,336 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 $0.00067 $0.03336
Opus 5 $0.00034 $0.01668
Sonnet 5 $0.00013 $0.00667
Haiku 4.5 $0.00007 $0.00334

Measured 4d ago against content hash 32207376750c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-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 4d 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.

skills/sdd-validate/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd:validate — Verify implementation against spec

You are a validation auditor. Your job is to verify that the implementation matches the spec and complies with the constitution. You perform two layers of validation: a deterministic baseline from the MCP server, and a code-level audit that verifies the implementation exists and is correct. Follow these steps exactly, in order. Do NOT auto-fix anything — report findings and let the user decide.

MCP Server integration: This command uses two MCP tools — sdd_validate for deterministic coverage data and sdd_transition for state changes. If the MCP server is not available, fall back to reading artifacts directly.

Step 1: Identify feature and validate state

Parse the feature name from $ARGUMENTS. If no argument is provided, call sdd_get_state (no feature argument) to get the active_feature.

If neither yields a feature name, ask the user to specify one.

Call sdd_get_state with the feature name. Check the feature state:

  • If in validating state: this is the expected state (set automatically when all tasks complete). Proceed normally.
  • If in implementing state: the user wants an early check. Proceed normally but note in the report that not all tasks may be complete.
  • If in any other state: tell the user the current state and explain that validation is intended for features in validating or implementing state. Do NOT proceed.

Step 2: Get deterministic baseline from MCP

Call the sdd_validate tool with the feature name. This returns:

  • deterministic.requirement_coverage: For each requirement ID (FR/NFR/EC), which tasks cover it and their completion status (covered, partial, pending, uncovered).
  • deterministic.task_progress: How many tasks are completed, in progress, pending, and blocked.
  • deterministic.orphan_requirements: Requirements not assigned to any task.
  • heuristic.constitution_compliance: Best-effort structural check of constitution.md.
  • summary.can_complete: Boolean — are there any blockers?

Read the full file on GitHub · 276 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. 4d ago First seen · 276 lines · 67 tokens per session scan A 32207376750c

Subscribe to this mod's changes

sdd-validate is a skill published in the GitHub repository rubenzarroca/sdd-plugin (6 stars, last pushed 6mo ago), licensed MIT. It adds 67 tokens to every session and 3,336 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

fix

Use to drive a bug fix from first report through close, with a "why didn't we catch it?" loop at the end. Triggers — "/engineer.fix", "a bug came in", "this is broken", "a user reported X", "there's a defect", "we have a regression", "this needs a fix", "another report", "more issues", "still failing", "validation…

swingerman/engineer · 100 tokens

next

Use at the start of a work session, or any time the question is "what should I pick up now" across the whole project. Triggers — "/engineer.next", "what's next", "what should I work on", "what should I do next", "where do I pick up".

swingerman/engineer · 64 tokens

crap-analyzer

Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …

swingerman/engineer · 109 tokens

post-merge

Use immediately after a PR is merged to clean up the local feature branch and resync main. Triggers — "/engineer.post-merge", "did we merge", "did we push", "PR merged", "post-merge cleanup", or right after a gh pr merge succeeds in the same session.

swingerman/engineer · 68 tokens

session-summary

Use at the end of a work session on a DAE feature, so the next session picks up cleanly. Triggers — "/engineer.session-summary", "wrap up the session", "write the session log", "I'm stopping for the day".

swingerman/engineer · 54 tokens

onboard

Use to bring a project into the DAE methodology, or to check an onboarded project for gaps. Triggers — "/engineer.onboard", "onboard this project", "set up DAE here", "adopt the methodology", or when a DAE skill fails because no manifest exists.

swingerman/engineer · 64 tokens