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 mattwynne/yaks --skill exploratory-testinggit clone --depth 1 https://github.com/mattwynne/yaksWrote 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/mattwynne/yaks/exploratory-testing)<a href="https://agentmods.dev/skills/mattwynne/yaks/exploratory-testing"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/exploratory-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/mattwynne/yaks/exploratory-testing"><img src="https://agentmods.dev/badge/skills/mattwynne/yaks/exploratory-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00037 | $0.01726 |
| Opus 5.5 | $0.00015 | $0.00690 |
| Sonnet 5.5 | $0.00007 | $0.00345 |
| Haiku 4.5 | $0.00004 | $0.00173 |
Grade A, and why
exploratory-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 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploratory Testing
Overview
Exploratory testing discovers what automated tests miss. The agent
acts as a curious, methodical user - running yx commands in a
sandbox, observing output, trying edge cases, and logging findings.
Each session is guided by a charter that focuses exploration on a
specific area with specific heuristics.
When to Use
- After implementing a new feature or fixing a bug
- Before a release, to shake out edge cases
- When a command's behaviour feels under-tested
- When you want to stress-test error handling or output formatting
- Periodically, to discover regressions or UX papercuts
Don't use when:
- You need deterministic, repeatable test coverage (write Cucumber scenarios)
- The area has no working implementation yet
Phase 1: Charter
Agree on a Target
The user provides (or the agent suggests) a target area to explore. Good targets are specific commands, workflows, or quality attributes:
- "the
yx addcommand" - "yak hierarchy and the
--underflag" - "output formatting across
--formatoptions" - "error messages when things go wrong"
- "a full workflow: add, organise, work, complete, prune"
Select Heuristics
Pick 2-4 heuristics from the menu below that suit the target:
| Heuristic | CLI Application |
|---|---|
| CRUD | Add, list, show, update, remove yaks through full lifecycle |
| Zero, One, Many | Empty state, single yak, many yaks, deep nesting |
| Boundary Values | Long names, special chars, spaces, empty strings, unicode |
| Never and Always | Invariants (done yaks always show done, removed yaks never listed) |
| Follow the Data | Add -> list -> modify -> list -> verify consistency |
| Some, None, All | Filters with matching/non-matching/all items |
| Starve | Missing .yaks directory, non-existent directories, no permissions |
| Interrupt | Broken pipes (yx ls | head -1), partial stdin, Ctrl-C |
| Configuration Tour | --format options, --only filters, env vars |
| Claims Tour | Does --help text match actual behaviour? |
| Sequence Variation | Unusual command orders (done before add, prune with no done) |
| User Tour | Common real-world workflows end-to-end |
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 · 210 lines · 37 tokens per session scan A f7923599ead2
exploratory-testing is a skill published in the GitHub repository mattwynne/yaks (61 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,726 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
browser-tdd
Browser-based visual TDD using Playwright — verify UI produces correct visual output, not just syntactic correctness.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
emulate-seed
Generate emulate seed configs for stateful API emulation. Wraps Vercel's emulate tool for GitHub, Vercel, Google OAuth, Slack, Apple Auth, Microsoft Entra, AWS, Okta, Clerk, Resend, Stripe, and MongoDB Atlas APIs — full state machines, not mocks. Use when setting up test environments, CI pipelines, integration tests…