A command that checks a set of IPA project documents for missing parts, consistency, and links between requirements, screens, data, batches, and reports. IPA is Japan's Information-technology Promotion Agency, whose documentation format is used here.

Use it after editing requirements documents, after document-generation workflows, or before planning work to confirm that the required files and traceability IDs are present.

It catches broken or incomplete project documentation before planning or implementation begins. It also verifies changes made manually after the documents were generated.

validate — Command for Claude Code by nguyennguyenit: A command that checks a set of IPA project…

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/nguyennguyenit/multiclaude/validate

Clone the repo

git clone --depth 1 https://github.com/nguyennguyenit/MultiClaude

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/validate.svg)](https://agentmods.dev/commands/nguyennguyenit/multiclaude/validate)

Your own site

<a href="https://agentmods.dev/commands/nguyennguyenit/multiclaude/validate"><img src="https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/validate.svg" alt="Measured on agentmods" height="20"></a>

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 653 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.

Model	Per session	Once invoked
Fable 5	$0.00007	$0.00653
Opus 5	$0.00003	$0.00327
Sonnet 5	$0.00001	$0.00131
Haiku 4.5	$0.00001	$0.00065

Measured 5d ago against content hash b938b7363416, 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/ipa/validate.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Run IPA validation to check documentation consistency, traceability, and completeness.

When to Use

Scenario	Auto/Manual	Notes
After `/ipa:all`	Auto	Built-in, runs automatically
After `/ipa:init`	Auto	Built-in, runs automatically
After manual doc edits	Manual	Run `/ipa:validate` explicitly
Before `/plan`	Manual	Recommended quality gate
After `/ipa-docs:sync`	Manual	Verify sync completeness

Note: /ipa:all and /ipa:init run validation automatically. Use this command manually only when you edit docs or want to re-verify.

Prerequisites

IPA docs must exist:

docs/SRD.md
docs/UX_SPEC.md
docs/INTERFACE_SPEC.md
docs/DB_DESIGN.md

Workflow

Step 1: Load Skill

Activate ipa-validator skill from .claude/skills/ipa-validator/

Step 2: Check Docs Exist

docs/
├── SRD.md           ✓ or ✗
├── UX_SPEC.md       ✓ or ✗
├── INTERFACE_SPEC.md ✓ or ✗
└── DB_DESIGN.md     ✓ or ✗

If any missing, report and stop.

Step 3: Extract IDs from SRD

Parse tables for:

FR-xx (Feature List)
S-xx (Screen List)
E-xx (Entity List)
B-xx (Batch List)
R-xx (Report List)
IF-xx (Integration List)

Step 4: Validate Cross-References

Check each doc references valid SRD IDs:

UX_SPEC.md → S-xx refs
INTERFACE_SPEC.md → FR-xx, S-xx refs
DB_DESIGN.md → E-xx refs

Step 5: Check Status Tracking

Verify INTERFACE_SPEC.md Endpoint Matrix has status column with valid values: ⏳, ✅, 🔄

Step 6: Generate Report

Output validation report with:

Summary (counts, status)
Errors (blocking issues)
Warnings (non-blocking)
Recommendations
Traceability Matrix

Output

## IPA Validation Report

### Summary
- Total Features (FR): X
- Total Screens (S): X
- Total Entities (E): X
- Errors: X
- Warnings: X
- Status: PASS / FAIL

### Details
[...see ipa-validator skill for format...]

Usage

# After manual edits to docs
/ipa:validate

# Before planning (quality gate)
/ipa:validate
/plan

# After sync to verify
/ipa-docs:sync
/ipa:validate

Read the full file on GitHub · 106 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.

5d ago First seen · 106 lines · 7 tokens per session scan A b938b7363416

Subscribe to this mod's changes

validate is a command published in the GitHub repository nguyennguyenit/MultiClaude (22 stars, last pushed 24d ago), licensed MIT. It adds 7 tokens to every session and 653 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 2026-08-30.

Documents

validate