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 munch2u-a11y/Helix-AGI --skill run-agent-testsgit clone --depth 1 https://github.com/munch2u-a11y/Helix-AGIWrote 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/munch2u-a11y/helix-agi/run-agent-tests)<a href="https://agentmods.dev/skills/munch2u-a11y/helix-agi/run-agent-tests"><img src="https://agentmods.dev/badge/skills/munch2u-a11y/helix-agi/run-agent-tests/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/munch2u-a11y/helix-agi/run-agent-tests"><img src="https://agentmods.dev/badge/skills/munch2u-a11y/helix-agi/run-agent-tests.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 | $0.00029 | $0.00292 |
| Opus 5.5 | $0.00012 | $0.00117 |
| Sonnet 5.5 | $0.00006 | $0.00058 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
run-agent-tests 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 4d 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.
What it actually says
Run agent tests
Use this workflow only when the user asks to test or compare coding agents.
- Call
inspect_environmentfor the selected project. - State which agents and suite will run. Explain that prompts or code context may be sent to the chosen provider.
- Prefer
auth_mode="account". It uses the official CLI's cached login and removes API-key environment variables from the child process. Never ask for credentials. - Use
start_helix_benchmarkfor a Helix-AGI checkout containingscripts/cross_agent_benchmark.py. - Use
start_prompt_evalfor user-authored JSON/JSONL prompt cases. - Poll
get_rununtil the run reachespassed,failed, orcancelled. - Report the suite, agents, auth mode, pass/fail counts, artifact location, and important errors. Do not claim one agent is generally superior from a small or single-domain suite.
Important billing note: account mode avoids silently inheriting API keys, but it does not guarantee that a provider will charge nothing. Provider entitlements and current CLI billing rules still apply.
Never modify provider credential caches, export OAuth tokens, scrape authenticated web sessions, or call provider backends directly.
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.
- 4d ago First seen · 21 lines · 29 tokens per session scan A 0fe0f53fcbda
run-agent-tests is a skill published in the GitHub repository munch2u-a11y/Helix-AGI (61 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 292 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 2026-10-12.
Other skills, from other repositories
playwright-testing
Playwright E2E tests: page objects, cross-browser projects, traces and CI setup. Use when writing or debugging Playwright specs, or configuring Playwright in CI.
vitest-testing
Vitest gotchas for mocking, timers, type tests and coverage. Use when writing or debugging Vitest tests, configuring vitest.config, or a coverage threshold fails.
cypress-testing
Cypress E2E and component tests: cy.intercept(), cy.session(), custom commands and CI artifacts. Use when writing or debugging Cypress specs, or running Cypress in CI.
testing-workflow
How to test a change: test first, what to cover, what to mock, and the anti-patterns that let tests pass without proving anything. Use when writing or planning tests, mocking a dependency, fixing a flaky test, or checking coverage.
validation-gates
The checks a change passes before it is done or merged: secrets, the project's tests, lint and build, size, new dependencies, the browser for UI, review, regression and a smoke test. Use when deciding which checks a change needs, or whether work is ready to merge or deploy.
browser-testing
Browser testing through the Chrome DevTools MCP: navigation, DOM snapshots, scripted assertions, responsive checks, console and performance traces. Use when verifying a UI change in Chrome, checking breakpoints, or reading console errors.