VerifiMind-PEAS: Command for Claude Code

.claude/commands/verifimind-deploy.md

verifimind-deploy is a command for Claude Code from creator35lwb-web/VerifiMind-PEAS. It costs 23 tokens per session (538 once invoked), scanned A, original, MIT.

A guarded recovery command for deploying VerifiMind-PEAS when the normal authorised release trigger is unavailable or has failed before producing an acceptable serving artifact.

In plain words
What is it for?
It is for authorised recovery deployments from an exact reviewed merge, after proving the checkout and release conditions, and then running one canonical recovery carrier.
Why use it?
It prevents recovery deployment from being treated as a second release process and requires checks on the repository, commit, versions, worktree, serving revision, rollback source, and other release state.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is creator35lwb-web/VerifiMind-PEAS's own configuration. It tells Claude Code how to work on VerifiMind-PEAS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything VerifiMind-PEAS configures →

Reuse

Borrowing it

Nothing to install: this file belongs to creator35lwb-web/VerifiMind-PEAS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/creator35lwb-web/VerifiMind-PEAS/main/.claude/commands/verifimind-deploy.md
Clone the repo
git clone --depth 1 https://github.com/creator35lwb-web/VerifiMind-PEAS

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 verifimind-deploy

README.md
[![agentmods](https://agentmods.dev/badge/commands/creator35lwb-web/verifimind-peas/verifimind-deploy/github.svg)](https://agentmods.dev/commands/creator35lwb-web/verifimind-peas/verifimind-deploy)
Your own site
<a href="https://agentmods.dev/commands/creator35lwb-web/verifimind-peas/verifimind-deploy"><img src="https://agentmods.dev/badge/commands/creator35lwb-web/verifimind-peas/verifimind-deploy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verifimind-deploy

Your own site · 80×15
<a href="https://agentmods.dev/commands/creator35lwb-web/verifimind-peas/verifimind-deploy"><img src="https://agentmods.dev/badge/commands/creator35lwb-web/verifimind-peas/verifimind-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 538 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00023 $0.00538
Opus 5 $0.00012 $0.00269
Sonnet 5 $0.00005 $0.00108
Haiku 4.5 $0.00002 $0.00054

Measured 10d ago against content hash d9052d6baf00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

verifimind-deploy 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 10d 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/verifimind-deploy.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verifimind-deploy

This public command is a recovery wrapper, not a second release recipe. Normal production releases use the Cloud Build trigger created by an authorized merge. That trigger already counts as the one deployment execution; do not run this command after it starts or succeeds.

The private Command Central release orchestrator owns review, authorization, provenance, smoke, Release, registry, post-deploy truth, and the private receipt. This repository owns the executable recovery carrier.

Use only for an authorized recovery

Run the recovery carrier only when the normal trigger is unavailable or failed before producing an acceptable serving artifact, and Alton has authorized recovery from an exact reviewed merge.

Before execution, prove all of the following:

  • this checkout is creator35lwb-web/VerifiMind-PEAS;
  • HEAD is the exact authorized merge on current origin/main;
  • the worktree is clean, including untracked files;
  • the intended version matches every discovered version assertion;
  • the current serving revision and rollback source are recorded;
  • no merge-trigger deployment for the same release is still running.

Execute one canonical carrier

cd mcp-server
./deploy-cloudrun.sh

Do not reproduce or bypass the carrier's build, source-archive, image-identity, or Cloud Run commands. If a guard fails closed, repair the cause and rebind the authorization to any changed SHA.

Required verification

After the single recovery execution:

  1. Bind the source merge, build ID, immutable image identity, serving revision, traffic percentage, and rollback target.
  2. Verify /health, /setup, and the server card agree on version, availability, routing, protocol, and failover semantics.
  3. Run the versioned external smoke oracle and record PASS / STOP / INSTRUMENT separately.
  4. Prepare exact deployment facts through a bounded docs-only truth PR. Do not push directly to public main or to the live Wiki.
  5. Complete the GitHub Release, registry, and private receipt only through the Command Central release gate.

Read the full file on GitHub · 67 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. 10d ago First seen · 67 lines · 23 tokens per session scan A d9052d6baf00

Subscribe to this mod's changes

verifimind-deploy is a command published in the GitHub repository creator35lwb-web/VerifiMind-PEAS (2 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 538 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 2026-08-31.