validate

A validation command that runs the project's automated quality checks and produces one PASS or FAIL report.

In plain words
What is it for?
Use it after implementation to validate Java, Kotlin, and Angular changes and write a Markdown validation report.
Why use it?
It brings test, coverage, architecture, traceability, and other checks into one result, so you do not have to inspect each check separately.

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/loiane/specs-driven-development-spring-angular/validate
Clone the repo
git clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angular

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 639 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 $0.00018 $0.00639
Opus 5 $0.00009 $0.00319
Sonnet 5 $0.00004 $0.00128
Haiku 4.5 $0.00002 $0.00064

Measured 2d ago against content hash 12564d4fdb23, 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/validate

Phase: 5 — validate (run the harness) Owning agent: .claude/agents/spring-validator.md Skills used: harness-report-parsing, jacoco-coverage-policy, pit-mutation-tuning, requirements-traceability, archunit-rules

Stack routing

Changed source Agent
Java/Kotlin only spring-validator (this agent)
Angular (.ts, .html, .scss) only angular-validator
Both Run both validators; merge results into a single 07-validation-report.md

Determine scope from 04-tasks.md file lists or git diff --name-only. If only frontend files changed, delegate entirely to angular-validator.

Purpose

Run the full 10-layer harness, parse the output, and write 07-validation-report.md with a single PASS / FAIL verdict.

Inputs

  • <feature-id> (optional; if omitted, reports across all changes since origin/main).

Reads

  • .github/scripts/harness.sh, .github/scripts/check-new-code-coverage.sh, .github/scripts/traceability.sh.
  • target/harness-summary.json (after the run).
  • 01-spec.md, 04-tasks.md, 06-test-plan.md (for AC mapping).

Writes

  • .specs/<feature-id>/07-validation-report.md
  • .specs/<feature-id>/07a-traceability.md (regenerated)
  • target/harness-summary.json, target/new-code-coverage.json

Process

  1. Run .github/scripts/harness.sh --report > /dev/null (writes target/harness-summary.json).
  2. Run .github/scripts/check-new-code-coverage.sh (must be ≥ 95% on changed lines).
  3. Run .github/scripts/traceability.sh <feature-id>. Any AC with zero tests = FAIL.
  4. Aggregate the 10 gates plus the new-code-coverage and traceability checks. Verdict is PASS only if every gate is pass (mutation may be warn if explicitly justified in the report).
  5. Write 07-validation-report.md with: verdict, gate table, top failing items, links to artifacts, recommended next action.

Refuse if

  • 04-tasks.md shows any task not done.
  • The harness was bypassed (e.g. local cache showed stale results) — always re-run.
  • forbid-skip-flags.sh would have blocked the underlying Maven invocation.

Read the full file on GitHub · 52 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 · 52 lines · 18 tokens per session scan A 12564d4fdb23

Subscribe to this mod's changes

validate is a command published in the GitHub repository loiane/specs-driven-development-spring-angular (57 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 639 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.