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.
npx skills add makifbaysal/tasktrooper --skill worker-job-testinggit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/worker-job-testing)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/worker-job-testing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/worker-job-testing/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/makifbaysal/tasktrooper/worker-job-testing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/worker-job-testing.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 | $0.00042 | $0.00596 |
| Opus 5.5 | $0.00017 | $0.00238 |
| Sonnet 5.5 | $0.00008 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
worker-job-testing 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worker & Async Job Testing
Overview
A worker has no HTTP response to assert on. You verify it the way the product uses it: fire the real trigger, then observe the side effects. Reading the worker's source to convince yourself it works is not testing.
The Pattern
- Identify the worker processes the repo defines (a
cmd/worker, a queue consumer, a scheduler) and start them alongside the API with logs captured to a file. - Trigger through the product path. Prefer the API call or user action that enqueues the job over inserting queue rows by hand — the enqueue side is part of what you are testing. Hand-crafted messages are a fallback for hard-to-reach cases and must match the real schema.
- Assert on observable outcomes: the DB state the job must produce, the outbound request it must make (assert against the stub's received requests — test-data-and-stubs), the file/notification/event it must emit, and the log line that marks completion.
- Poll, don't guess. Async means eventually: loop with a timeout (
for i in $(seq 30); do check && break; sleep 1; done) instead of one arbitrary sleep. A job that needs longer than the product's own expectation is a finding.
The scenarios a worker always owes you
| Scenario | How | PASS looks like |
|---|---|---|
| Happy path | real trigger → poll | expected side effect appears, completion logged |
| Idempotency / duplicate delivery | fire the same trigger twice | effect applied once, no double-charge/double-send |
| Dependency failure | WireMock returns 5xx/timeout | retries with backoff per config, then DLQ/parked state — not an infinite hot loop |
| Poison message | malformed payload | job fails contained: logged, quarantined, worker keeps processing others |
| Restart mid-work | kill the worker during a job, restart | job resumes or reruns safely; nothing half-applied |
Skip a row only if the task's scope genuinely excludes it — say so in the scenario plan rather than silently.
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.
- 8d ago First seen · 40 lines · 42 tokens per session scan A b1db242cf1f8
worker-job-testing is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 596 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
proof-api
Build API test suites — endpoint testing, contract testing, load testing for REST/GraphQL/gRPC APIs. Use when asked to "test this API", "API tests", "endpoint testing", "contract tests", or "load test".
ambient-healthcare-agent-with-nemotron-voice-agent
Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend.
earth2studio-create-datasource
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
nemo-fabric-build-adapter
Build, migrate, review, and maintain third-party NVIDIA NeMo Fabric adapters against the public adapter contract. Use when creating adapter or target descriptors, mapping AgentConfig into an agent harness or custom-agent runtime, implementing start/invoke/stop, declaring schemas and capabilities, packaging discovery…