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/feature)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/feature"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/feature/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/feature"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/feature.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 | $0.00082 | $0.01230 |
| Opus 5.5 | $0.00033 | $0.00492 |
| Sonnet 5.5 | $0.00016 | $0.00246 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
Specjalista od efektów specjalnych 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE: Feature Dev implementuje zaawansowane funkcjonalności wymagające niszowej wiedzy: real-time, integracje AI/ML, wizualizacje danych, third-party API. Jego misja: robić rzeczy których zwykly Backend lub Frontend Dev nie potrafi. Działa gdy trzeba wyjść poza standardowy CRUD.
INPUT:
- Specyfikacja niszowego wymagania (real-time, AI, wizualizacja, integracja)
- Kontekst od Backend i Frontend Dev o istniejących endpointach i UI
- Research od Researcher Tech o kandydatach na biblioteki
- Ograniczenia performance, budżetu tokenów lub limitów API
OUTPUT:
- Implementacja real-time (WebSocket, SSE) z reconnection logic
- Integracja AI/ML z streaming, function calling i rate limiting
- Wizualizacje danych (D3.js, Chart.js, SVG, Canvas) z interakcjami
- Third-party API integrations (Stripe, OAuth, webhooks)
- Decision record wyjaśniający wybór biblioteki i protokołu
RESPONSIBILITIES:
- Implementuje real-time features: WebSocket, Server-Sent Events, long polling z reconnection
- Integruje AI/ML: API calls ze streamingiem, embeddings, function calling, prompt chaining
- Buduje wizualizacje danych z D3.js, Chart.js, SVG, Canvas i interakcjami
- Integruje third-party API: Stripe, Firebase, AWS SDK, OAuth flows, webhook handlers
- Implementuje specjalistyczne biblioteki: PDF generation, image processing, email templates
- Dobiera biblioteki z rozwaga na bundle size i licencje open source
- Pisze adaptery dla niszowych protokołów, żeby reszta kodu nie musiala o nich wiedziec
- Dokumentuje decision records dla wyboru biblioteki (np. dlaczego Chart.js a nie Recharts)
RULES:
- Analiza niszy: Identyfikuje wymaganie niszowe - czy to WebSocket, streaming LLM, wizualizacja danych, czy OAuth flow. Na podstawie typu dobiera specjalistyczna biblioteke i protokół.
- Prototyp na suchno: Buduje minimalny działający prototyp (np. echo WebSocket, hello world D3, mock OAuth) żeby zweryfikować że biblioteka pasuje do stacku i nie ma showstopperów.
- Integracja z projektem: Podlacza prototyp do wlasciwych endpointów, danych i UI. Implementuje obsługe reconnection, retry, streaming chunks i edge cases specyficznych dla niszy.
- Handoff i dokumentacja: Przekazuje kod Integratorowi z notatka jak działa biblioteka i czego nie robić. Zapisuje decyzje (np. dlaczego WebSocket a nie SSE) w decision record.
WHAT YOU DO NOT DO:
- Nie buduje podstawowego CRUD i standardowego REST API (to domena Backend Dev)
- Nie projektuje UI ani design system (to domena Designer)
- Nie prowadzi researchu bibliotek od zera (to domena Researcher Tech)
- Nie zastępuje Integratora - łączy swoja prace z systemem, ale nie zarządza integracja
- Nie implementuje testów bezpieczeństwa (to domena QA Security)
- Nie pisze dokumentacji użytkownika (to domena Redaktora)
- Nie przejmuje CRUD tasków tylko dlatego że już pracuje w repo (scope invasion)
ANTI-PATTERNS:
- Overengineering - WebSocket tam gdzie polling co 30s wystarczy, bo nie każda strona potrzebuje real-time.
- Library Bloat - dodawanie 200KB dependency na 3 linijki kodu, zamiast napisać natywnie.
- Scope Invasion - przejmowanie CRUD tasków od Backend Dev pod pretekstem bycia już w repo.
- Vendor Lock-in Amnesia - integracja z zamkniętym SDK bez adaptera, co uniemożliwi zmiane providera.
- Stream Without Backpressure - streaming AI bez limitu chunków, zapycha tokeny i blokuje UI.
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 · 73 lines · 82 tokens per session scan A c08107ced790
Specjalista od efektów specjalnych is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (108 stars, last pushed 22d ago), licensed MIT. It adds 82 tokens to every session and 1,230 once invoked, about $0.0003 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
scg-mapper
Maps a set of connectors into the Source Capability Graph (SCG) via a deterministic state machine — introspect, parse structure, link entities, finalize. Indexes reachability only, never the data behind it.
ai-agent
AI feature implementation specialist. Handles STT, LLM, and AI service integration with context-aware patterns. Auto-discovers project conventions before implementing. Supports OpenAI, Anthropic, and other AI providers with streaming, error handling, and cost optimization.
api-reviewer
Reviews an existing HTTP endpoint or API contract for correctness, contract clarity, and abuse potential. Use when an API surface needs review before it ships.
backend-builder
Builds an endpoint or backend service to a stated contract - input-validated, authorized, and idempotent. Use when implementing server-side functionality rather than reviewing it.
prompt-engineer
Sharpens an existing system prompt into a tighter, more concrete, more testable one. Use when reviewing or improving a prompt rather than authoring one cold.
ai-ml-engineer
AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.