smoke

A command that builds the project, deploys a numbered preview, and checks whether key web addresses and login-related endpoints respond as expected.

In plain words
What is it for?
Use it after a build to test health, version, configuration, authentication, OAuth metadata, the MCP connection, and the sign-in page.
Why use it?
It catches basic deployment and availability problems before a preview is shared.

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/stevenn/ctxlayer/smoke
Clone the repo
git clone --depth 1 https://github.com/stevenn/ctxlayer

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 237 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 $0.00015 $0.00237
Opus 5 $0.00008 $0.00118
Sonnet 5 $0.00003 $0.00047
Haiku 4.5 $0.00002 $0.00024

Measured yesterday against content hash 97437e0ed5cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smoke 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.

.claude/commands/smoke.md · 22 lines

What it actually says

Run a full smoke pass and report back as a compact text table — no screenshots, mobile-friendly.

Steps:

  1. bun run build — abort and report if this fails.
  2. bun --filter='@ctxlayer/worker' run deploy:preview — capture the preview URL.
  3. bun scripts/smoke.mjs <preview-url> — runs the checks defined in scripts/smoke.mjs:
    • GET /api/health
    • GET /api/version
    • GET /api/config
    • GET /api/me (expects 401 anon; set SMOKE_ME_OK=1 for sessioned CI)
    • GET /.well-known/oauth-authorization-server
    • POST /mcp initialize JSON-RPC frame
    • GET /sign-in (SPA fallback)
  4. The script prints one row per check: ✓/✗ name status ms.
  5. If anything fails, surface the response body in a code fence.
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. yesterday First seen · 22 lines · 15 tokens per session scan A 97437e0ed5cd

Subscribe to this mod's changes

smoke is a command published in the GitHub repository stevenn/ctxlayer (9 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 237 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.