validate-adr

A command that checks architecture decision records, or ADRs—short documents explaining important technical decisions—against enterprise rules.

In plain words
What is it for?
Use it to validate one ADR or a directory of ADRs and confirm that decisions include context, alternatives, consequences, compliance information, and valid metadata.
Why use it?
It catches missing sections, alternatives, dates, statuses, compliance details, and other requirements before an ADR is accepted.

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/exchanet/method_enterprise_builder_planning/validate-adr
Clone the repo
git clone --depth 1 https://github.com/exchanet/method_enterprise_builder_planning

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 287 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 $0.00000 $0.00287
Opus 5 $0.00000 $0.00143
Sonnet 5 $0.00000 $0.00057
Haiku 4.5 $0.00000 $0.00029

Measured 2d ago against content hash f7c084553450, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-adr 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.

agents/claude-code/.claude/commands/validate-adr.md · 44 lines

What it actually says

Command: /validate-adr

Runs the enterprise ADR Validator against one or more ADR files.

Usage

/validate-adr [path]

Examples

# Validate all ADRs in the standard directory
/validate-adr docs/adr/

# Validate a specific ADR
/validate-adr docs/adr/ADR-001-isolation.md

What it runs

node packs/enterprise-architecture-pack/validators/adr-validator/src/index.ts \
  --format=console [path]

Rules checked

  • ADR-STR-001: Required sections (Context, Decision) present
  • ADR-STR-002: ADR has a title
  • ADR-ENT-001: ≥2 alternatives documented
  • ADR-ENT-002: Alternatives include rejection reasons
  • ADR-ENT-003: Compliance Impact section present
  • ADR-ENT-004: Valid status (Proposed/Accepted/Deprecated/Superseded)
  • ADR-ENT-005: ISO 8601 date format (YYYY-MM-DD)
  • ADR-COMP-001: Security ADRs reference a compliance standard
  • ADR-COMP-002: Consequences section present
  • ADR-COMP-003: Regulated ADRs name their deciders

Gate rule

An ADR that fails any error-severity rule cannot be marked as Accepted.

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 · 44 lines · 0 tokens per session scan A f7c084553450

Subscribe to this mod's changes

validate-adr is a command published in the GitHub repository exchanet/method_enterprise_builder_planning (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 287 tokens. 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 commands, from other repositories

release-sync

Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.

yonatangross/orchestkit · 62 tokens

notebook

Local NotebookLM over a FOLDER of documents using Antigravity (agy). Sweeps each document (PDF with text, scanned PDF, image, docx) into an objective-driven Markdown summary, then builds a relevance INDEX and a cited master summary. Incremental cache (re-runs only re-summarize changed docs / changed objective) and…

MarcosNahuel/antigravity-plugin-cc · 101 tokens

report

Generate a publication-grade HTML report from a markdown source using the TRAID Design System catalog (5 templates). Agy matches content to template, you confirm, agy produces final branded HTML.

MarcosNahuel/antigravity-plugin-cc · 38 tokens

doc-to-md

Convert a PDF, docx, image, or other document to clean Markdown using Antigravity (agy) multimodal Gemini. Saves to docs/agy/converted/.

MarcosNahuel/antigravity-plugin-cc · 34 tokens

notebook-audit

Adversarial consistency audit over the notebook knowledge base — finds contradictions in a document corpus: the same category with conflicting amounts, the same person under two names, the same reference with different values, coverage gaps (unprocessed docs), unparseable amounts. Pure SQL, read-only. Writes…

MarcosNahuel/antigravity-plugin-cc · 64 tokens

notebook-status

Check the progress of a /agy:notebook sweep (for long document sets run with --background). Reports % complete, done/pending/failed counts, elapsed time and a rough ETA, and which documents are still pending — so you can resume. Read-only, no agy.

MarcosNahuel/antigravity-plugin-cc · 57 tokens