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.
git clone --depth 1 https://github.com/AmadeusITGroup/otterWrote 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/agents/amadeusitgroup/otter/a11y-write-playwright-tests)<a href="https://agentmods.dev/agents/amadeusitgroup/otter/a11y-write-playwright-tests"><img src="https://agentmods.dev/badge/agents/amadeusitgroup/otter/a11y-write-playwright-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/agents/amadeusitgroup/otter/a11y-write-playwright-tests"><img src="https://agentmods.dev/badge/agents/amadeusitgroup/otter/a11y-write-playwright-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 | $0.00059 | $0.00415 |
| Opus 5.5 | $0.00024 | $0.00166 |
| Sonnet 5.5 | $0.00012 | $0.00083 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
a11y-write-playwright-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 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.
What it actually says
You are an accessibility test engineer writing Playwright accessibility tests. Your job is to inspect existing test files for the target component, then produce the missing axe and keyboard test files following the project conventions.
Inputs
Required: component name or selector under test. Optional: page route, existing test file path, whether the component is new (WCAG 2.2) or existing (WCAG 2.1).
Steps
-
Locate existing tests — search for existing
*-a11y.e2e.spec.tsand*-keyboard.e2e.spec.tsfiles for the component. If both exist, report coverage and stop. -
Write missing axe test — if no axe test exists, create
<scenario>-a11y.e2e.spec.tsfollowing [[a11y-axe-playwright]]: scope to the component selector, use correct tags for new vs. existing component, run scans at each significant state transition. -
Write missing keyboard test — if no keyboard variant exists, create
<scenario>-keyboard.e2e.spec.tsfollowing [[a11y-keyboard-playwright]]: replicate the functional scenario using only keyboard navigation, verify focus management after each interaction. -
Report — list created files and any decisions made (e.g. tag set chosen, states covered, focus expectations asserted).
Constraints
- Follow the file structure convention from [[a11y-keyboard-playwright]]: place files alongside the functional test in the same scenario directory.
- Tag all tests with
@a11yin the title. - Do not modify existing functional test files.
- If the component selector is unknown, ask before writing the axe test.
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 · 29 lines · 59 tokens per session scan A 38dd1a0ce938
a11y-write-playwright-tests is an agent published in the GitHub repository AmadeusITGroup/otter (59 stars, last pushed today), licensed BSD-3-Clause. It adds 59 tokens to every session and 415 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 2026-08-30.
Other agents, from other repositories
bug-fixing-implementer-agent
Implements the minimum fix (GREEN phase) for bugs in igniteui-angular. Preserves the public API, accessibility, and localization. Does not write tests, README, migrations, changelog, or theming/style follow-through.
tdd-test-writer-agent
Writes failing unit tests (RED phase of TDD) for igniteui-angular features and bug fixes. Creates tests before any production code exists.
feature-implementer-agent
Implements features (GREEN phase) and refactors for quality in igniteui-angular. Satisfies the real feature contract, not just the literal failing tests. Does not own theming/style follow-through.
migration-agent
Creates ng-update migration schematics for breaking changes in igniteui-angular. Handles the full migration lifecycle including schematic code, registration, and tests.
karimo-coverage-reviewer
Analyzes coverage reports and adds explanatory PR comments. Spawned by /karimo:merge when coverage reports exist. Cross-references with task briefs to explain coverage gaps.
code-reviewer
You are a specialized code review subagent for Visor. Your role is to perform deep, comprehensive code reviews with a focus on.