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 cyrusagents/cyrus --skill f1-test-drivegit clone --depth 1 https://github.com/cyrusagents/cyrusWrote 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/cyrusagents/cyrus/f1-test-drive)<a href="https://agentmods.dev/skills/cyrusagents/cyrus/f1-test-drive"><img src="https://agentmods.dev/badge/skills/cyrusagents/cyrus/f1-test-drive/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/cyrusagents/cyrus/f1-test-drive"><img src="https://agentmods.dev/badge/skills/cyrusagents/cyrus/f1-test-drive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00035 | $0.01988 |
| Opus 5.5 | $0.00014 | $0.00795 |
| Sonnet 5.5 | $0.00007 | $0.00398 |
| Haiku 4.5 | $0.00003 | $0.00199 |
Grade A, and why
f1-test-drive 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 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.
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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
F1 Test Drive
Applicability (required before setup)
This is the canonical F1 applicability policy. Inspect the actual diff against the PR base and identify the behavior that needs validation before starting F1, selecting a fixture, or creating a report. Task size, issue labels, filenames, and a generic request to verify/ship are not sufficient reasons to run F1.
- Required: product/runtime changes exercised by F1 (issue tracking, authentication, routing, runner/session lifecycle, activity rendering), and functional changes to the F1 harness itself. Choose scenarios with assertions that exercise the changed behavior; a generic health check or unrelated fixture does not establish correctness.
- Not applicable: documentation, agent instructions, CI/release tooling, installer/build/packaging metadata, or other changes with no relevant product workflow behavior. Run appropriate documentation, script, unit, integration, build, package inspection, or isolated install smoke checks instead. Do not run F1 or create, attach, or commit an F1 test-drive report. A brief PR note stating why F1 is not applicable and what checks passed is enough.
- Mixed changes: exercise only the relevant functional portion with F1; validate other portions with their targeted checks. A docs, infrastructure, or metadata path is never an exemption for a real runtime behavior change (including dependencies, generated prompts, or installed defaults).
- Actual releases: assess the entire released payload against the previous
release, not merely the version-bump PR. Runtime-bearing payloads retain
relevant F1 validation. Payloads with no F1-covered behavior change use the
non-F1 release verification described in
apps/cli/RELEASING.md. Editing release tooling is not itself preparing or publishing a functional release.
If F1 is not applicable, stop this protocol before setup and reporting. If it is applicable but blocked, report the missing coverage and blocker honestly; do not relabel it as not applicable or substitute an unrelated passing drive. Preserve historical reports.
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 Changed · +40 lines · +2 tokens per session 0edaf75efb1e
- 1mo ago First seen · 185 lines · 33 tokens per session scan A 3b1a7e01ece3
f1-test-drive is a skill published in the GitHub repository cyrusagents/cyrus (868 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,988 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 2026-08-30.
Other skills, from other repositories
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
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.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
langbot-testing
Test LangBot WebUI and core product flows with an automated browser and backend logs. Use when validating the configured LangBot frontend, pipeline Debug Chat, model provider setup and test buttons, bot and knowledge-base UI flows, or troubleshooting failed LangBot end-to-end tests.