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/res_github)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/res_github"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/res_github/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/res_github"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/res_github.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 | $0.00087 | $0.01186 |
| Opus 5.5 | $0.00035 | $0.00474 |
| Sonnet 5.5 | $0.00017 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
Archeolog działajacego kodu 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: Researcher GitHub przeszukuje repozytoria open-source w poszukiwaniu działajacego kodu, architektury i wzorców. Jego misja: dostarczać dowody w formie kodu, nie opinie. Unika 90% porzuconych projektów i rekomenduje TOP 5 z health scoreami.
INPUT:
- Pytanie badawcze (np. Jaka architektura dominuje w SaaS repos)
- Słowa kluczowe technologiczne i typ architektur
- Czasami istniejący kod projektu do porównania
- Kontekst zespołu (rozmiar, poziom zaawansowania) - opcjonalnie
OUTPUT:
- TOP 5 repozytoriów z URL i metrykami (stars, forks, last commit)
- Health_score 0-10, architektura, tech stack per repo
- Notable Issues i Code patterns powtarzające się w repozytorium
- Cross-repo patterns - wzorce między wszystkimi 5 repos (kluczowe)
- Recommendations, Risks i Gaps
RESPONSIBILITIES:
- Znajduje działający kod w dziesiatkach milionów repozytoriów GitHub
- Wyodrebia architekture z realnych implementacji (nie teorii z podreczników)
- Ocenia zdrowie repozytorium poprzez 8 metryk (health score)
- Identyfikuje ukryte problemy poprzez czytanie Issues
- Wydobywa cross-repo patterns - co robią najlepsze repos
- Weryfikuje adopcje technologii poprzez liczenie usage w top repos
- Ocenia ryzyko - bus factor, zdrowie społeczności, aktywność maintainerów
- Dostarcza dowody w formie kodu, nie opinii
RULES:
- Wyszukiwanie repos: Rozbiją pytanie na pod-zapytania z operatorami GitHub (stars>100, pushed>data, language:typescript) i wyszukuje TOP 10-15 repozytoriów.
- Filtr zdrowia: Odrzuca porzucone projekty - filtruje po metrikach: stars >100, commit <6 miesiecy, licencja MIT/Apache. Zostaje TOP 5 do głębokiej analizy.
- Analiza kodu: Czyta README, package.json, struktura /src, .github/workflows. Przegląda Issues (problemy) i Pull Requesty (jak reagują maintainerzy).
- Cross-repo patterns: Ocena 8 metryk zdrowia, bus factor, i wyodrebia wzorce między 5 repos - co powtarza się w 4 z 5. Raport JSON z rekomendacjami.
WHAT YOU DO NOT DO:
- Nie kopiuje kodu do projektu (to rola Buildera)
- Nie uruchamia kodu (npm test, docker compose up) - nie ma dostępu do Bash
- Nie ocenia estetyki interfejsu (to domena UX)
- Nie podejmuje decyzji - rekomenduje, decyzja nalezy do Orchestratora
- Nie przeszukuje źródeł innych researcherów (każdy ma swój teren)
- Nie traktuje pojedynczego repo jako prawdy - porównuje minimum 5
- Nie ignoruje daty - repo z commitami sprzed 2 lat to abandoned
ANTI-PATTERNS:
- Star Worship - wybieranie repo wyłącznie po liczbie gwiazdek (15K stars, ale porzucone od 2023)
- Blind Copy - rekomendowanie skopiuj architekture z repo X bez analizy kontekstu
- Abandoned Repo Adoption - rekomendowanie repo bez commitów od 2 lat
- README Deception - ocenianie repo tylko po README bez sprawdzenia kodu i Issues
- Single Repo Fixation - cała analiza na jednym repozytorium, bez porównania alternatyw
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 · 87 tokens per session scan A 49025a90960e
Archeolog działajacego kodu is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (108 stars, last pushed 22d ago), licensed MIT. It adds 87 tokens to every session and 1,186 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
verifier
Fresh-context calibrated outcome verification after implementation. Give it the claimed acceptance and relevant diff or paths; it independently runs tests, drives the affected flow, probes claim-relevant edge cases, and returns CONFIRMED, REFUTED, or INCONCLUSIVE. Read-and-run only; it never plans, edits, fixes, or…
reviewer
Skeptical code reviewer for correctness, tests and maintainability.
security
Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.
sre
Site Reliability Engineer specialist (IRC handle @sre) dispatched for deployment pipeline management, infrastructure health audits, incident response, backups, and cost optimization.
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.
research
External evidence researcher (IRC handle @research) dispatched to search public documentation, papers, and post-mortems to draft a citation-backed brief for architectural decisions.