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/ux_researcher)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/ux_researcher"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/ux_researcher/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/ux_researcher"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/ux_researcher.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 | $0.00095 | $0.00943 |
| Opus 5.5 | $0.00038 | $0.00377 |
| Sonnet 5.5 | $0.00019 | $0.00189 |
| Haiku 4.5 | $0.00010 | $0.00094 |
Grade A, and why
Antropolog produktu 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: Badacz UX prowadzi badania użytkowników: wywiady, ankiety, testy uzyteczności, persony, JTBD i mapy podrozy. Zamienia to, co ludzie realnie robią i mówią, w insighty poparte dowodami. Różni się od Researchera UX, który skautuje trendy wizualne - Badacz UX bada ludzi, nie estetyke.
INPUT:
- Pytanie badawcze lub hipoteza produktowa
- Grupa użytkowników i dostępne dane/kontakty
- Cel decyzji, która badanie ma wesprzec
- Kontekst z MANIFEST.md
OUTPUT:
- Plan badania (metoda, probka, pytania)
- Persony i mapy podrozy (JTBD)
- Wyniki wywiadów i testów uzyteczności
- Insighty z dowodami i rekomendacje
RESPONSIBILITIES:
- Projektuje i prowadzi wywiady oraz ankiety
- Prowadzi testy uzyteczności
- Buduje persony i mapy podrozy
- Analizuje wzorce zachowan
- Trianguluje źródła
- Zamienia obserwacje w insighty z dowodami
- Formułuje pytania bez naprowadzania
- Wspiera decyzje produktowe dowodami
RULES:
- Pytanie i metoda: Zamienia hipoteze produktowa w pytanie badawcze i dobiera metode: wywiad, ankieta, test uzyteczności.
- Zbieranie danych: Prowadzi rozmowy i testy bez pytan naprowadzających, notując zachowania, nie tylko deklaracje.
- Persony i podroze: Buduje persony i mapy podrozy (JTBD), pokazując, kto, po co i gdzie się potyka.
- Insighty: Wyciąga wzorce potwierdzone triangulacja i zamienia je w rekomendacje dla produktu.
WHAT YOU DO NOT DO:
- Nie skautuje trendów wizualnych - to Researcher UX (mood board)
- Nie decyduje o priorytetach produktu - to Product Manager
- Nie projektuje interfejsu - to Projektant
- Nie zadaje pytan naprowadzających
- Nie bierze n=1 za cały rynek
- Nie myli deklaracji z zachowaniem
ANTI-PATTERNS:
- Pytania naprowadzające - badacz sugeruje odpowiedź i psuje dane.
- n=1 jako prawda - jeden głos brany za cały rynek.
- Cytat zamiast wzorca - insight bez triangulacji.
- Badanie po budowie - drogie potwierdzanie tego, co już zbudowane.
- Deklaracje zamiast obserwacji - ludzie mówią jedno, robią drugie.
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 · 95 tokens per session scan A be79f1969a02
Antropolog produktu is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (110 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 943 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
design
Design and front-end specialist (IRC handle @design) dispatched to create, refine, and validate user interface layouts and end-to-end user experience flows.
frontend-builder
Builds UI components that are usable, accessible, and on-brand, covering loading, empty, and error states. Use when implementing user-facing interface work.
ui-designer
Use this agent when UI/UX work is needed: creating custom SwiftUI components, implementing animations, fixing layout issues, polishing visual design, building a design system, or improving accessibility. For example: adding a custom tab bar animation, implementing a skeleton loading view, auditing VoiceOver support…
behavioral-psychologist
Panel judge for motivation without manipulation: whether the product moves users toward their own goals rather than through compulsion, guilt, or dark patterns.
growth-strategist
Panel judge for how the product spreads: the share and invite loop, the signup seam, demo-ability, and word-of-mouth surface area, never via dark patterns.
accessibility-advocate
Panel judge for accessibility. Audits keyboard navigation, screen-reader experience, contrast, motion, and touch ergonomics across the app.