Borrowing it
Nothing to install: this file belongs to andrew-yangy/gru-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/skills/smoke-test/SKILL.mdgit clone --depth 1 https://github.com/andrew-yangy/gru-aiWrote 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.
[](https://agentmods.dev/skills/andrew-yangy/gru-ai/smoke-test)<a href="https://agentmods.dev/skills/andrew-yangy/gru-ai/smoke-test"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/smoke-test/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.
<a href="https://agentmods.dev/skills/andrew-yangy/gru-ai/smoke-test"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/smoke-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00053 | $0.00821 |
| Opus 5 | $0.00026 | $0.00411 |
| Sonnet 5 | $0.00011 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
smoke-test 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smoke Test -- Pipeline E2E Verification
Run a real directive through the full pipeline and verify every step produces correct output.
Arguments: $ARGUMENTS (passed as $1 to the script)
- Empty or
medium-- run a medium-weight smoke test (brainstorm skipped, clarification/approve auto-approved) lightweight-- run a lightweight smoke test (brainstorm skipped, clarification/approve auto-approved)
What This Does
- Creates a disposable test directive (
smoke-test-{timestamp}) with a trivial task - Spawns a real
/directivesession that executes the full pipeline - Polls
directive.jsonevery 10 seconds to track step progression - Validates each completed step via
validate-gate.sh - Enforces a 10-minute overall timeout
- Prints a pass/fail table per pipeline step with evidence
- Cleans up the test branch and directive artifacts on exit
Step 1: Run the Smoke Test
Execute the bash runner script. It handles everything -- directive creation, agent spawning, polling, validation, reporting, and cleanup.
bash .claude/skills/smoke-test/run-smoke-test.sh $ARGUMENTS
The script will output real-time progress as each step completes and a final summary table.
Step 2: Present Results
After the script finishes, present the results to the CEO in this format:
# Smoke Test Results
## Summary
- Weight: {lightweight | medium}
- Duration: {X}m {Y}s
- Result: {PASS | FAIL}
## Step Results
| # | Step | Status | Gate | Evidence |
|---|-------------------|-----------|----------|----------------------------------|
| 1 | triage | completed | PASS | weight=medium, directive.json ok |
| 2 | checkpoint | completed | PASS | No prior checkpoint |
| ... |
|15 | completion | completed | PASS | test_mode auto-approved |
## Failures (if any)
- Step {name}: {what went wrong, gate violations, missing artifacts}
## Cleanup
- Test branch: deleted
- Test directive: deleted
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 85 lines · 53 tokens per session scan A dd28990a42f1
smoke-test is a skill published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 821 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.
agent-tester
Agent skill for tester - invoke with $agent-tester.
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
gsd-verify-work
Validate built features through conversational UAT.
gsd-add-tests
Generate tests for a completed phase based on UAT criteria and implementation.