verify

verify is a command for Claude Code from niels-emmer/myace. It costs 40 tokens per session (439 once invoked), scanned A, original, MIT.

A pre-merge checklist for infrastructure changes, including validation, formatting, policy checks, tests, security review, rollback, and documentation.

In plain words
What is it for?
It helps verify Terraform or Bicep changes, deployment tests, security-sensitive updates, state migrations, and rollback procedures.
Why use it?
It catches invalid, unsafe, or incomplete infrastructure changes before they reach deployment or production.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions AGENTS.md; mentions Codex; built for aider.

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/niels-emmer/myace/verify
Clone the repo
git clone --depth 1 https://github.com/niels-emmer/myace

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.

agentmods badge for verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/niels-emmer/myace/verify.svg)](https://agentmods.dev/commands/niels-emmer/myace/verify)
Your own site
<a href="https://agentmods.dev/commands/niels-emmer/myace/verify"><img src="https://agentmods.dev/badge/commands/niels-emmer/myace/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 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 5.1 $0.00040 $0.00439
Opus 5 $0.00020 $0.00219
Sonnet 5 $0.00008 $0.00088
Haiku 4.5 $0.00004 $0.00044

Measured 2d ago against content hash 653e6b999063, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

verify 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.

collections/base/devops-engineer/commands/verify.md · 15 lines

What it actually says

  1. Run plan/validate, format/lint, and policy-as-code checks and confirm an actual pass — quote the real output, don't summarize a run you didn't just do.
  2. Read the plan output and confirm it matches the intended change — no resources created or destroyed that the task didn't ask for.
  3. Confirm the change added or updated tests that cover it (pipeline unit tests, deployment integration/smoke tests), checked against the test-patterns skill's checklist — not just that some test somewhere still passes.
  4. Run the linter and type checker; both must be clean. A warning that's routinely ignored project-wide is a judgment call to note explicitly, not to silently pass over.
  5. If the change touches identity, secrets, network exposure, data, images, or dependencies, run it through the devsecops-checklist skill and resolve every FAIL before continuing — don't defer a blocking finding to "a follow-up."
  6. If the change includes a state migration or a change to a shared/critical path, confirm the rollback path has actually been exercised, not just written.
  7. Confirm documentation and runbooks — README, AGENTS.md-style rule files, inline comments describing now-stale behavior — have been updated to match the change, in this same change set.
  8. Append the decision-log entry per the memory-system skill: what was decided, how it was tested (point at the specific runs from steps 1-4), and which docs were touched.
  9. Only report the change as done once every applicable step above is actually true — not once the code compiles, and not once "most of it" is finished.
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 · 15 lines · 40 tokens per session scan A 653e6b999063

Subscribe to this mod's changes

verify is a command published in the GitHub repository niels-emmer/myace (1 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 439 once invoked, about $0.0002 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 2026-09-03.