A post-deployment check that tests a deployed environment with a health check, browser smoke tests using Playwright, and log scanning. It verifies the service after deployment but does not deploy or roll back anything.

Use it after deploying to staging or production to check basic service health, key browser flows, and recent logs.

It quickly shows whether a deployment is working and surfaces failures without changing the running environment.

deploy-gate — Command by rajconnects

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/rajconnects/founder-stack/deploy-gate

Clone the repo

git clone --depth 1 https://github.com/rajconnects/founder-stack

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 384 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	$0.00023	$0.00384
Opus 5	$0.00012	$0.00192
Sonnet 5	$0.00005	$0.00077
Haiku 4.5	$0.00002	$0.00038

Measured yesterday against content hash fa2840d7b98e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy-gate 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 yesterday.

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.

workflow/commands/deploy-gate.md · 32 lines

What it actually says

You are running the deploy gate AFTER a deploy has completed.

Arguments: $ARGUMENTS

Steps

If $ARGUMENTS is empty, default to staging. If the argument is prod, confirm with the user: "Run deploy-gate against prod? Smoke tests are read-only but add load. (yes/no)" — do NOT proceed without explicit yes.
Launch the deploy-verifier subagent with a self-contained prompt:
- The environment name.
- Instruct it to read .claude/project.json for deploy_targets[<env>] and stack.supabase_project_ref.
- Ask for the standard verdict output.
Print the output verbatim.
Record the gate pass/fail for this session (lightweight marker: touch .claude/.deploy-gate-passed-<env> on PASS).
If verdict is FAIL, do NOT suggest code changes — the user's next step is diagnosis and rollback decision. Surface the failure details and stop.
Session hygiene hint (PASS only). Append one line: Deploy verified. If you're moving to a different feature next, consider a session reset (in Claude Code: /clear). See docs/session-hygiene.md. Skip on FAIL.

Notes

This is a READ-ONLY gate. The verifier cannot deploy, restart, or roll back. If the user wants those, they invoke their deploy tooling separately.
Prod gate runs only with explicit confirmation — that's a safety rail, not an annoyance.
Health check + smoke + logs is the full scope. Do not extend into load tests or long-running assertions; those belong in CI.

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.

yesterday First seen · 32 lines · 23 tokens per session scan A fa2840d7b98e

Subscribe to this mod's changes

deploy-gate is a command published in the GitHub repository rajconnects/founder-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 384 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.

Browser automation DevOps and cloud Testing

deploy-gate

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Steps

Notes

What this file has done since we first saw it

Other commands, from other repositories

e2e

auto-browse

research-perplexity

review

graphify

laravel-playwright