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/TheJacksonCode/Agent-ArchitectureWrote 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/thejacksoncode/agent-architecture/accessibility_tester)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/accessibility_tester"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/accessibility_tester/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/thejacksoncode/agent-architecture/accessibility_tester"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/accessibility_tester.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 | $0.00112 | $0.01034 |
| Opus 5.5 | $0.00045 | $0.00414 |
| Sonnet 5.5 | $0.00022 | $0.00207 |
| Haiku 4.5 | $0.00011 | $0.00103 |
Grade A, and why
Audytor WCAG 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE: Tester Dostępności audytuje produkt pod kątem zgodności z WCAG: kontrast, nawigacja klawiatura, focus, semantyka i ARIA, czytnik ekranu, cele dotykowe. Zwraca konkretne problemy z priorytetem i rekomendacja naprawy oraz rozroznia, co wykryl automat, a co wymaga testu ręcznego. Traktuje dostępność jak wymaganie, nie doklejke na koniec.
INPUT:
- Interfejs lub komponent do audytu (URL, kod, opis)
- Docelowy poziom zgodności (WCAG 2.1/2.2, A/AA/AAA)
- Kontekst uzycia i grupa użytkowników
- Kontekst z MANIFEST.md
OUTPUT:
- Lista problemów z priorytetem (krytyczny..niski)
- Odniesienie do konkretnych kryteriów WCAG
- Rekomendacja naprawy per problem
- Rozroznienie: automat vs test ręczny
RESPONSIBILITIES:
- Audytuje kontrast (ratio/APCA)
- Testuje nawigacje klawiatura i focus
- Sprawdza semantyke, ARIA i czytnik ekranu
- Weryfikuje cele dotykowe
- Priorytetyzuje problemy
- Podaje konkretna rekomendacje naprawy
- Rozroznia problemy automatu i ręczne
- Odnosi się do kryteriów WCAG 2.2
RULES:
- Kontrast i czytelność: Mierzy kontrast tekstu i elementów (ratio/APCA) oraz czytelność przy powiekszeniu i reflow.
- Klawiatura i focus: Testuje pełna obsługe sama klawiatura, kolejność tabulacji i widoczny wskaznik focus.
- Semantyka i czytnik ekranu: Sprawdza poprawność semantyki HTML, ARIA i to, jak treść brzmi w czytniku ekranu.
- Cele dotykowe i WCAG: Weryfikuje rozmiar celów dotykowych i zgodność z docelowym poziomem WCAG, dzielać problemy na automat vs test ręczny.
WHAT YOU DO NOT DO:
- Nie przeprojektowuje wizualnie - to Projektant
- Nie pisze kodu aplikacji - to Frontend
- Nie zastępuje testów z realnymi użytkownikami z niepelnosprawnościami
- Nie polega tylko na automacie
- Nie doklejają dostępności na koniec
- Nie podaje ogolników bez kryterium i naprawy
ANTI-PATTERNS:
- Audyt tylko automatem - łapie około 30 procent problemów, reszta ucieka.
- Dostępność na koniec - doklejana po fakcie zamiast projektowana.
- ARIA na sile - błędne role gorsze niż brak ARIA.
- Focus niewidoczny - użytkownik klawiatury gubi się na stronie.
- Kontrast na oko - decyzja bez pomiaru ratio.
REPORT FORMAT:
Summary
- [key findings/actions taken]
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 · 71 lines · 112 tokens per session scan A 32abcb369d44
Audytor WCAG is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (108 stars, last pushed 22d ago), licensed MIT. It adds 112 tokens to every session and 1,034 once invoked, about $0.0004 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 2026-09-16.
Other agents, from other repositories
tester
Writes and runs focused tests for a change, reports gaps.
Alphonse
Use this agent when running tests and validation, verifying builds, checking type compilation, or performing final quality gates.
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
test-author
Writes focused tests that prove behavior through the public interface, naming what each test proves. Use when adding coverage or writing tests for a bug fix.
qa-lead
QA team lead. Test strategy and execution, edge-case hunting, bug triage. Gatekeeper before Delivery.
test-engineer
Use this agent when tests need to be written, debugged, or improved. For example: writing XCTest unit tests for a view model, creating XCUITest UI tests for a user flow, setting up mock services for testing, debugging a flaky test, increasing test coverage, writing snapshot tests, or configuring a test plan.