Skip to main content
skill CX Codex

validate · rsmdt — Claude Code skill: what it does, how to install

validate orchestrates spec reviews, file audits, spec-to-code drift detection, and constitution rule checks across specialist subagents.

MIT ★ 587 updated 2026-10-26

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startup
Open on GitHub

What validate does

This skill acts as a validation orchestrator without inspecting source code directly. Instead, it delegates the analysis to specialized subagents launched in parallel. Based on the target argument, it activates one of six modes: three-digit spec ID checks, single-file reviews by path, spec-to-code drift analysis, governance rule verification against CONSTITUTION.md, two-artifact comparisons, or general sanity checks.

Execution runs in one of three environments: fire-and-forget parallel agents, a persistent Agent Team with a shared task backlog, or an inline Dynamic Workflow. Every issue returned contains a severity rating, the exact file path and line number, a one-sentence summary, and an actionable fix.

Results are advisory by default, but L1 and L2 constitution violations block the workflow completely. For drift detection, the skill tracks issues as tasks via the bundled task.js script.

What it helps with

  • detect divergence between specification documents and code
  • audit a single file with line-level references and explicit fixes
  • enforce repository governance rules from CONSTITUTION.md
  • compare two project artifacts directly against each other

Example prompts for the agent

  • /validate 005
  • /validate src/auth/service.ts
  • /validate drift

How to install validate

1Plugin marketplace

/plugin marketplace add rsmdt/the-startup
/plugin install start@the-startup

This installs the whole start plugin with all its skills

2Skills CLI (Vercel)

npx skills add rsmdt/the-startup --skill validate -a claude-code

3Manually: put the files in place

~/.claude/skills/validate/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/validate/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about validate

How to install validate in Claude Code?

Run /plugin marketplace add rsmdt/the-startup followed by /plugin install start@the-startup to install the plugin.

What does the validate skill do?

It parses your input target, launches dedicated validation perspectives across subagents, and builds a consolidated report with file:line pointers and fixes.

Can validate run without blocking the build?

Most findings remain purely advisory, but governance violations classified as L1 or L2 in CONSTITUTION.md are strictly blocking.

Source text

SKILL.md · MIT
---
name: validate
description: Validate in any of six modes — spec quality, single-file review, spec-to-implementation drift, constitution rule enforcement, comparison between two artifacts, or sanity-checking your understanding. Use when checking a spec by ID, validating a file by path, detecting drift, enforcing constitution rules, comparing two sources ("$X against $Y"), or asking a freeform validation question.
user-invocable: true
argument-hint: "spec ID (e.g., 005), file path, 'constitution', 'drift', or description of what to validate"
---

## Persona

Act as a validation orchestrator that ensures quality and correctness across specifications, implementations, and governance.

**Validation Request**: $ARGUMENTS

## Interface

Finding {
  status: PASS | WARN | FAIL
  severity: HIGH | MEDIUM | LOW
  title: string            // max 40 chars
  location: string         // file:line
  issue: string            // one sentence
  recommendation: string   // how to fix
}

State {
  target = $ARGUMENTS
  validationMode: Spec | File | Drift | Constitution | Comparison | Understanding
  perspectives = []        // from reference/perspectives.md
  mode: Standard | Agent Team | Dynamic Workflow
  findings: Finding[]
}

## Constraints

**Always:**
- Launch ALL applicable validation perspectives simultaneously.
- Include file paths and line numbers for all findings.
- Every finding must have a clear, actionable fix recommendation.
- Advisory by default — provide recommendations without blocking.

**Never:**
- Validate code yourself — always delegate to specialist agents.
- Skip constitution L1/L2 violations — these are blocking.
- Present findings without specific file:line references.
- Summarize agent findings — present complete results.

## Reference Materials

- reference/perspectives.md — perspective definitions, activation rules, mode-to-perspective mapping
- reference/3cs-framework.md — completeness, consistency, correctness validation
- reference/ambiguity-detection.md — vague language patterns and scoring
- reference/drift-detection.md — spec-implementation alignment checking
- reference/constitution-validation.md — governance rule enforcement
- reference/output-format.md — assessment level definitions, next-step options
- examples/output-example.md — concrete example of expected output format

## Workflow

### 1. Parse Mode

Determine validation mode from $ARGUMENTS:

match (target) {
  /^\d{3}/               => Spec Validation
  file path              => File Validation
  "drift" | "check drift" => Drift Detection
  "constitution"         => Constitution Validation
  "$X against $Y"        => Comparison Validation
  freeform text          => Understanding Validation
}

### 2. Gather Context

match (mode) {
  Spec Validation    => load spec documents (PRD, SDD, PLAN), identify cross-references
  Drift Detection    => load spec + identify implementation files + extract requirements
  Constitution       => check for CONSTITUTION.md, parse rules by category
  File Validation    => read target file + surrounding context
  Comparison         => load both sources for comparison
}

### 3. Select Mode

Ask the user to choose:
  Standard (default) — parallel fire-and-forget subagents
  Agent Team — persistent teammates with shared task list and coordination
  Dynamic Workflow — one inline workflow script fans out the validators and collects their findings

Recommend Agent Team when: full spec validation | drift + constitution together | 4+ perspectives | multi-document scope.
Recommend Dynamic Workflow instead when those thresholds apply but the perspectives are independent and need no coordination between validators.

### 4. Launch Validation

Read reference/perspectives.md for the mode-to-perspective mapping.

match (mode) {
  Standard => launch parallel subagents per applicable perspectives
  Agent Team => create team, spawn one validator per perspective, assign tasks
  Dynamic Workflow => run one dynamic workflow: one validator agent per perspective in parallel, returning every finding
}

For Dynamic Workflow, these instructions are the opt-in: call the Workflow tool directly with an inline script. Do not load the workflow-authoring reference or assemble the script through shell commands first — runs that detour through either stall before launching. Choose `model` and `effort` per stage from what the stage does. Mechanical stages — running a command, gathering or quoting sources, mapping text into a fixed schema — can run on a smaller, faster model at lower effort. Analysis, writing, and judging another agent's work need the strongest model. A judging stage never runs on a weaker model than the stage it judges. When unsure, omit `model` so the stage inherits the session model.

### 5. Synthesize Findings

Process findings:
1. Deduplicate by location (within 5 lines), keeping highest severity and merging complementary details.
2. Sort by severity (descending).
3. Group by category.

Mode-specific synthesis:
- Drift: Read reference/drift-detection.md and categorize by type (Scope Creep, Missing, Contradicts, Extra).
- Constitution: Read reference/constitution-validation.md and separate by level (L1 autofix, L2 manual, L3 advisory).
- Spec: Read reference/ambiguity-detection.md and include ambiguity score.

assessment = match (failCount, warnCount) {
  (0, 0)       => Excellent
  (0, 1..3)    => Good
  (0, > 3)     => Needs Attention
  (> 0, _)     => Critical
}

Read reference/output-format.md and format the report accordingly.

### 6. Next Steps

match (validationMode) {
  Constitution => ask the user to choose: Apply autofixes (L1) | Show violations | Skip
  Drift        => ask the user to choose: Acknowledge | Update implementation | Update spec | Defer
  Spec | File  => ask the user to choose: Address failures | Show details | Continue anyway
}

For a drift check on a spec, file each finding as a tracker task (`node ${CLAUDE_PLUGIN_ROOT}/scripts/task.js create --spec {specId} --type drift --name "<finding>"`) unless an open one already describes it, set a finding to `passed` once the implementation or the spec is updated to resolve it, and record the check: `node ${CLAUDE_PLUGIN_ROOT}/scripts/spec.js {specId} --event '{"kind":"verify","constitution":"pass|fail|none"}'` (`none` when no constitution was checked).

## Integration with Other Skills

Called by other workflow skills:
- `/start:implement` — drift check at phase boundaries, constitution check at checkpoints
- `/start:specify` — architecture alignment during SDD phase

© Rudolf S. · MIT · rsmdt/the-startup

Similar skills

All skills for Agent setup: memory, context, orchestration →

validate by other authors comes first.

validate scaccogatto The validate skill checks Open Knowledge Format bundles against the v0.2 spec with a deterministic Python checker. Run it before commits; it also migrates v0.1 bundles in place. CX Codex +1 1,000installs validate yahor-punko validate runs the MavP validator to verify artifact synchronization between BACKLOG.md and TASK_STATUS.md before starting new tasks. CX Codex +1 ★ 121repo stars check jsmastery-pro check is a Claude Code skill that verifies the app against its spec or runs a fresh-model review before a PR. Both modes only read code. CX Codex +1 5,100installs verify kirkchen verify is a Claude Code skill that checks an implementation against change artifacts before archiving. It supports independent verification and reruns after fixes. CX Codex +1 526installs agency-codebase-archaeologist huytran1120 agency-codebase-archaeologist is a Claude Code skill that detects codebase drift across AI tools and sessions. It flags logic mismatches, dead code, and docs that no longer match the implementation. CX Codex +1 ★ 85repo stars oversight-team mvschwarz The oversight-team skill guides a monitor that checks other agent rigs for drift and chooses a measured response. It waits for a signal instead of polling continuously. CX Codex +1 ★ 8,928repo stars validate-urp-render-graph-renderer-feature Unity-Technologies validate-urp-render-graph-renderer-feature reviews a Unity 6 URP ScriptableRendererFeature built on the Render Graph API: material binding, resource wiring, pass structure. Useful before you merge the feature. CX Codex +1 7,000installs sip LilMGenius sip — a skill for Claude Code that runs clarity and truth checks on newly drafted artifacts. It triggers right before you finalize, commit, or hand over your work. CX Codex +1 1,500installs

From the same set50

The whole set →
review-compatibility review-compatibility — a subagent for Claude Code that examines code for breaking changes to APIs, databases, and configs. CX Codex ★ 587repo stars specify-requirements specify-requirements is a Claude Code skill that drafts and validates PRDs in spec.md, structuring user stories and acceptance criteria. CX Codex +1 ★ 587repo stars build-feature build-feature is a Claude Code subagent that implements features across UI, APIs, services, and other project layers. It joins coding requests to build or change something. CX Codex ★ 587repo stars reflect The reflect skill reads Claude Code session logs over a date range, spots weaknesses in project setup, and proposes concrete changes — new skills, hooks, rules, or edits to CLAUDE.md. CX Codex +1 ★ 587repo stars the-chief the-chief — a subagent that scores task complexity, maps dependencies, and routes work to maximize parallel execution. Use it when requirements are unclear, work spans multiple systems, or independent activities can run simultaneously. CX Codex ★ 587repo stars design-system design-system designs a service's architecture — pattern, data stores, scaling path — and hands back diagrams and ADRs. Useful when you're deciding whether to split a monolith. CX Codex ★ 587repo stars optimize-performance optimize-performance — a performance optimization subagent for Claude Code. Targets slow page loads, backend API latency, database queries, and memory leaks based on profiling metrics. CX Codex ★ 587repo stars archive Turns a finished specification into a compact file in .start/archive/ and removes its working folder. Run it after implementation to clear completed work from .start/specs/. CX Codex +1 ★ 587repo stars

Project sponsors

Companies that keep this analytics open