Borrowing it
Nothing to install: this file belongs to dixus/claudeframework. 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/dixus/claudeframework/main/.claude/skills/smoke/SKILL.mdgit clone --depth 1 https://github.com/dixus/claudeframeworkWrote 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/dixus/claudeframework/smoke)<a href="https://agentmods.dev/skills/dixus/claudeframework/smoke"><img src="https://agentmods.dev/badge/skills/dixus/claudeframework/smoke/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/dixus/claudeframework/smoke"><img src="https://agentmods.dev/badge/skills/dixus/claudeframework/smoke.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 | $0.00030 | $0.00771 |
| Opus 5.5 | $0.00012 | $0.00308 |
| Sonnet 5.5 | $0.00006 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
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 2mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run smoke tests against the running Docker stack for a spec.
$ARGUMENTS is the spec name (e.g. prd-45-file-virus-scanning). If omitted, uses the most recently modified spec in .claude/specs/.
Prerequisites
- Docker stack must be running (
docker compose up -d) - A smoke test file must exist in the project (auto-detected in Step 2)
- The spec's API routes must already be implemented
Steps
1. Health check
Run docker compose ps to verify all containers are running. Then poll the project's health endpoint (read from CLAUDE.md, default: GET http://localhost:8000/health) every 5 seconds, up to 60 seconds.
- If all containers are healthy → proceed
- If any container is down or health check fails → stop and report. Do NOT attempt to fix Docker infrastructure — that is out of scope for this skill.
2. Detect and write smoke tests
Detect the smoke test file and runner:
- Check CLAUDE.md for a
smoke_testorsmokecommand/path - If not specified, auto-detect by looking for:
smoke_test.py,smoke_test.ts,smoke.test.ts,tests/smoke.py,tests/smoke.ts,test/smoke.* - Determine the runner from the file extension:
.py→python,.ts→npx tsxornpx ts-node,.js→node - If no smoke test file exists, create one following the project's primary language (read from CLAUDE.md or
package.json/pyproject.toml)
Read the smoke test file, the spec at .claude/specs/<name>.md, and the response schemas referenced in the spec's Affected/New files list.
Add smoke test coverage for the spec's API routes:
- Follow existing patterns in the smoke test file
- Match field names exactly to response schemas — do not guess
- Test happy-path only (smoke tests verify routes respond, not edge cases)
3. Run and fix loop (max 3 attempts)
Maintain an attempt counter starting at 0.
- Run the smoke test file with its detected runner and capture output
- If all checks pass → proceed to Step 4
- If any check fails → increment counter. If counter ≥ 3, run
git checkout <smoke-test-file>to restore the original file, then stop and report the failure output - On failure, fix only the smoke test assertions — do not modify API code. Common causes: wrong field names, wrong response structure (object vs list), wrong status codes
- Loop back to step 1
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.
- 2mo ago First seen · 69 lines · 30 tokens per session scan A c2fa22343d38
smoke is a skill published in the GitHub repository dixus/claudeframework (10 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 771 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.