Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/secondsky/claude-skillsnpx agentmods add commands/secondsky/claude-skills/workers-test-setupWrote 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/secondsky/claude-skills/workers-test-setup)<a href="https://agentmods.dev/commands/secondsky/claude-skills/workers-test-setup"><img src="https://agentmods.dev/badge/commands/secondsky/claude-skills/workers-test-setup/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/secondsky/claude-skills/workers-test-setup"><img src="https://agentmods.dev/badge/commands/secondsky/claude-skills/workers-test-setup.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 | $0.00037 | $0.02166 |
| Opus 5.5 | $0.00015 | $0.00866 |
| Sonnet 5.5 | $0.00007 | $0.00433 |
| Haiku 4.5 | $0.00004 | $0.00217 |
Grade A, and why
cloudflare-workers:test-setup scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await worker.fetch(request, env, ctx); How it starts
The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workers Test Setup Command
Set up comprehensive testing for Cloudflare Workers using Vitest and @cloudflare/vitest-pool-workers.
Execution Workflow
Phase 1: Detection - Analyze Current Setup
Read the project to understand its current state:
- Check if
package.jsonexists - Check if
vitest.config.tsorvitest.config.jsexists - Check if
wrangler.jsoncorwrangler.tomlexists - Detect bindings used in the Worker (D1, KV, R2, DO, Queues, AI)
- Check if any tests already exist (
**/*.test.ts,**/*.spec.ts)
Store findings for later phases.
Phase 2: User Preferences - Ask Questions
Use AskUserQuestion to gather preferences:
Question 1: "What type of tests do you want to set up?"
- Options:
- Unit tests only (fast, isolated function testing)
- Integration tests only (full request/response testing)
- Both unit and integration tests (Recommended)
Question 2: "Which bindings do you need to mock?"
- MultiSelect: true
- Options (based on detection):
- D1 (SQLite database)
- KV (key-value storage)
- R2 (object storage)
- Durable Objects (stateful coordination)
- Queues (message queues)
- Workers AI (AI inference)
- Vectorize (vector database)
- None (no bindings used)
Question 3: "Do you want code coverage reporting?"
- Options:
- Yes, with coverage thresholds (Recommended)
- Yes, without thresholds
- No
Phase 3: Validation - Check Prerequisites
Before proceeding, validate:
-
Node.js/Bun installed: Run
node --versionorbun --version- If neither exists, abort with error: "Node.js or Bun required. Install from https://nodejs.org/ or https://bun.sh/"
-
package.json exists:
- If not, abort with error: "No package.json found. Run
npm initorbun initfirst."
- If not, abort with error: "No package.json found. Run
-
Wrangler configured:
- If no wrangler.jsonc/toml, warn: "No wrangler config found. Tests may need manual binding configuration."
-
No existing vitest.config:
- If exists, ask: "vitest.config already exists. Overwrite?"
- If user says no, abort gracefully
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.
- 1mo ago First seen · 340 lines · 37 tokens per session scan A 6a796f103a75
cloudflare-workers:test-setup is a command published in the GitHub repository secondsky/claude-skills (231 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,166 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
verify
Run a repository verification loop with runner-first execution, deterministic stages, and explicit PASS/FAIL/SKIP output. Use for fast or full validation of a consumer repository. Not for: mutation, fixing failures, dependency remediation, or merge approval. Output: runner summary or a complete fallback stage table.
generate-tests
Generate unit, integration, and e2e test suites from scaffolded project with framework-appropriate coverage.
correlate
Find related failures through pattern matching.
diff
Compare two command outputs with intelligent diff.
open
Open/retrieve an offloaded output by ID or shortcut.
search
Search through offloaded outputs with hard caps.