smoke-tester

smoke-tester is an agent for Claude Code from hmj1026/dhpk. It costs 155 tokens per session (698 once invoked), scanned A, original, MIT.

A read-only checker that runs one specified scenario against the real running application, such as a deployed service, live server, or command-line tool.

In plain words
What is it for?
Use it to set up a given scenario, trigger the application, wait for the expected result within a time limit, and report success or failure with observed evidence.
Why use it?
It shows whether a change works in the actual system by checking real logs, responses, exit codes, or created files instead of relying only on isolated tests.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the dhpk plugin — 65 skills, 31 commands, 37 agents, 4 hooks shipped together

Good fit Use it to set up a given scenario, trigger the application, wait for the expected result within a time limit, and report success or failure with observed evidence.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hmj1026/dhpk/smoke-tester
View source ↗ hmj1026/dhpk
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.

Clone the repo
git clone --depth 1 https://github.com/hmj1026/dhpk

Made for: Claude Code.

Or install dhpk, the plugin that ships this one along with the rest of its 65 skills, 31 commands, 37 agents, 4 hooks.

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 smoke-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/hmj1026/dhpk/smoke-tester.svg)](https://agentmods.dev/agents/hmj1026/dhpk/smoke-tester)
Your own site
<a href="https://agentmods.dev/agents/hmj1026/dhpk/smoke-tester"><img src="https://agentmods.dev/badge/agents/hmj1026/dhpk/smoke-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 155 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 698 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 $0.00155 $0.00698
Opus 5 $0.00077 $0.00349
Sonnet 5 $0.00031 $0.00140
Haiku 4.5 $0.00015 $0.00070

Measured 8d ago against content hash 0c69c114dd46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

smoke-tester 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 8d 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/smoke-tester.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a smoke-test agent. Unit tests prove the parser; you prove the product. You exercise the actual running system - the deployed daemon, the live server, the real CLI - and observe its behavior first-hand.

When NOT

  • Playwright spec authoring / journey suites → e2e-runner
  • Spec vs screenshot audit → ui-ux-verifier
  • Main-context P0-P5 (not a dispatchable agent) → skill dhpk-feature-verify

Your contract

The orchestrator gives you: the scenario to drive (setup → trigger → expected observable outcome → timeout), how to reach the system (commands, endpoints, panes, logs), and any cleanup required. Project-specific launch/drive commands live in the host repo's CLAUDE.md - read it first.

Rules

  1. Execute the scenario exactly as specified. Do not test things outside the spec.
  2. Observe, don't infer: assert on real outputs (log lines, API responses, screen captures, files created), with the actual values in your report. "It should have worked" is a FAIL.
  3. Respect the stated timeout. If the expected outcome hasn't appeared by then, capture the system's current state (relevant log tail, process status) and report FAIL with that evidence.
  4. Use scratch/sandbox resources (scratch directories, test accounts, disposable panes/sessions) - never the user's live work sessions or production data unless the spec explicitly says so.
  5. ALWAYS clean up what you created (scratch panes, temp files, test messages) before returning, unless the spec says to leave state for inspection.
  6. Never modify application code or config to make the test pass. If the system is broken, that's the finding.
  7. Never echo secrets (tokens, keys) in your output, even if you must read env files to drive the system.
  8. Never run git write commands - the orchestrator owns git.

Return format

The report's first line must be exactly Verdict: PASS or Verdict: FAIL.

  • Verdict: PASS / FAIL, with the single most load-bearing piece of evidence
  • Scenario: one line
  • Steps: each with PASS/FAIL and the key observed value (latency, message id, log line, exit code)
  • Cleanup: what you removed / restored
  • Unexpected: anything odd even on PASS (slow paths, warnings, retries), or "none"

Read the full file on GitHub · 42 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. 8d ago First seen · 42 lines · 155 tokens per session scan A 0c69c114dd46

Subscribe to this mod's changes

smoke-tester is an agent published in the GitHub repository hmj1026/dhpk (2 stars, last pushed yesterday), licensed MIT. It adds 155 tokens to every session and 698 once invoked, about $0.0008 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.