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 test-environment-selectiongit 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/test-environment-selection)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/test-environment-selection"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/test-environment-selection/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/test-environment-selection"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/test-environment-selection.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 | $0.00045 | $0.01185 |
| Opus 5.5 | $0.00018 | $0.00474 |
| Sonnet 5.5 | $0.00009 | $0.00237 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
test-environment-selection 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Address.** Use `open_url` in the browser (`browser_navigate`) — for a protected preview it carries the bypass and sets a cookie, so the pages it links to load too. For HTTP requests (curl, an API client) use `branch_ How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Environment Selection
Overview
Before executing a single scenario, decide WHERE the product will run, in this order:
- Backend, worker or full-stack repository: local. DB rows, logs and third-party stubs are only observable there. First choice
start_task_preview— it checks out the task branch in the task workspace, detects how to run it, starts it, stops a stale server, and returns alocalhostURL for the browser tools; call it again if the URL isn't there yet. Only when it cannot run the project (e.g. a backend+frontend pair, or a worker it doesn't detect), boot by hand (backend-manual-testing). - Frontend-only repository: the task's own preview, else local. When the component is deployed with a per-branch
previewenvironment,get_task_previewreturns it — use it whenstatus: "ready"ANDbuilt_from_pr_head: true. Anything else (building,built_from_pr_head: false,error,canceled,none, or an empty list) is not the code under test: fall back tostart_task_preview. - Stage. Used when the repository is configured for stage verification, or when the app cannot boot locally (managed secrets, heavy infra the workspace lacks) — always after confirming stage is actually running the PR head (see Stage rules).
Production is never a test environment. No scenario is ever executed against the prod base URL or prod data — not a "harmless" GET, not seeding, not cleanup.
How to decide
- Identify the repository shape (backend/worker/full-stack vs frontend-only) and apply the order above.
- Read the repository settings (
list_repositories):build_command,test_command,verify_command— and any comment the developer left on the task (a clean run leaves none). These are the project's declared way of running and checking itself.get_project_briefhas the same information plus what each component talks to. - If neither a usable preview nor a local boot nor stage works, you are blocked — see below.
Preview rules
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 · 47 lines · 45 tokens per session scan A 59b8fcdfdcb6
test-environment-selection is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 1,185 once invoked, about $0.0002 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 2026-10-05.
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.
nemo-automodel-model-onboarding
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
amc-run-sample-calibration
Run end-to-end calibration on the shipped sample dataset (sdg082sampledata010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
mcore-testing
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.