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.
git clone --depth 1 https://github.com/rhuss/cc-spexWrote 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/commands/rhuss/cc-spex/speckit.spex.smoke-test)<a href="https://agentmods.dev/commands/rhuss/cc-spex/speckit.spex.smoke-test"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex.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/commands/rhuss/cc-spex/speckit.spex.smoke-test"><img src="https://agentmods.dev/badge/commands/rhuss/cc-spex/speckit.spex.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 | $0.00009 | $0.02999 |
| Opus 5 | $0.00005 | $0.01499 |
| Sonnet 5 | $0.00002 | $0.00600 |
| Haiku 4.5 | $0.00001 | $0.00300 |
Grade A, and why
speckit.spex.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 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.
How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Focused Interactive Smoke Test (speckit-spex-smoke-test)
Overview
Walk through curated smoke test scenarios defined in the feature spec's ## Smoke Test section. Claude automates all setup, execution, and evidence collection. The human only provides pass/fail judgment on each scenario. Results are persisted as SMOKE-TEST.md in the spec directory.
If the spec has no ## Smoke Test section, the command skips automatically — no human interaction needed.
You MUST NOT simulate, fake, or manually reproduce what the system under test would do. Every scenario must exercise the actual system (run the real command, call the real API, invoke the real skill). If a scenario cannot be properly tested in the current session (e.g., requires a separate run, external infrastructure, or state that cannot be set up), you MUST:
- Mark it as skip immediately
- State clearly why it cannot be tested (e.g., "Requires two independent distillation runs")
- Provide concrete manual test instructions the user can follow later (exact commands, expected output, what to verify)
A simulated test that manually edits files to mimic system output is worse than no test. It creates false confidence.
Ship Pipeline Guard
If .specify/.spex-state exists and its status is running, this command is part of a ship pipeline. The smoke test is always interactive regardless of the ask level. It never runs autonomously. However, it should not output a completion summary or ask "Shall I proceed?" after finishing. Complete the walkthrough and return.
PIPELINE_MODE=false
if [ -f ".specify/.spex-state" ]; then
STATUS=$(jq -r '.status // empty' .specify/.spex-state 2>/dev/null)
if [ "$STATUS" = "running" ]; then
PIPELINE_MODE=true
fi
fi
Prerequisites
Spec Resolution
Resolve the feature spec using the standard check-prerequisites script:
PREREQS=$(.specify/scripts/bash/check-prerequisites.sh --json --paths-only 2>/dev/null)
FEATURE_DIR=$(echo "$PREREQS" | jq -r '.FEATURE_DIR')
SPEC_FILE="$FEATURE_DIR/spec.md"
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.
- 10d ago First seen · 380 lines · 9 tokens per session scan A 865c03176808
speckit.spex.smoke-test is a command published in the GitHub repository rhuss/cc-spex (116 stars, last pushed 21d ago), licensed Apache-2.0. It adds 9 tokens to every session and 2,999 once invoked, about $0.0000 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 commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
paul:verify
Guide manual user acceptance testing of recently built features.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.