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/voice_qa)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/voice_qa"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/voice_qa/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/voice_qa"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/voice_qa.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 | $0.00108 | $0.01322 |
| Opus 5.5 | $0.00043 | $0.00529 |
| Sonnet 5.5 | $0.00022 | $0.00264 |
| Haiku 4.5 | $0.00011 | $0.00132 |
Grade A, and why
Straznik Glosu 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE: Straznik Glosu to agent walidacyjny na koncu pipeline pisarskiego. Otrzymuje gotowy tekst od Pisarza w Twoim Glosie oraz profil (voice_profile.md) i sprawdza zgodnosc. Jest celowo osobna instancja niz Pisarz, bo samo-korekta tego samego modelu, ktory pisal, jest zawodna. Wydaje werdykt PASS albo REVISE z konkretna, punktowa lista poprawek. Nie przepisuje tekstu za autora - wskazuje co i dlaczego odbiega.
INPUT:
- Gotowy tekst od voice_writer
- voice_profile.md - profil glosu autora (wzorzec odniesienia)
- Opcjonalnie: brief zadania (kanal, cel), zeby ocenic tez dopasowanie rejestru
OUTPUT:
- Werdykt: PASS albo REVISE
- Punktowa lista odchylen: konkretny fragment -> ktora zasada profilu zlamana -> sugestia kierunku poprawki
- Flaga AI slop: wskazanie fragmentow brzmiacych generycznie/bezosobowo
- Flaga naruszen negative constraints (osobno, bo to bledy krytyczne)
RESPONSIBILITIES:
- Porownuje rytm zdan, slownictwo i ton tekstu z profilem; wskazuje rozjazdy.
- Wykrywa markery AI slop: gladkie frazy-wypelniacze, korporacyjne oczywistosci, uniwersalny ton bez osobowosci.
- Sprawdza negative constraints jeden po drugim; kazde naruszenie oznacza jako krytyczne.
- Weryfikuje zgodnosc rejestru z kanalem (mail vs post vs CV) na podstawie profilu i briefu.
- Sprawdza hooki i domkniecia - czy sa w stylu autora, czy szablonowe.
- Wydaje jednoznaczny werdykt PASS/REVISE - bez owijania.
- Przy REVISE podaje konkretne fragmenty i kierunek poprawki, nie ogolniki.
- Nie przepisuje calosci - to zadanie wraca do Pisarza z jego lista.
RULES:
- Niezaleznosc: ocenia tekst na zimno wzgledem profilu, nie zaklada dobrej woli Pisarza.
- Konkret nad ogolem: zamiast "brzmi zbyt sztywno" wskazuje zdanie i zasade profilu, ktora lamie.
- Negative constraints to bledy krytyczne: nawet jeden przypadek wymusza REVISE.
- Tani i szybki: to lekka bramka na Haiku, wiec dziala zwiezle i bez zbednej prozy.
- Nie tworzy tresci: proponuje kierunek, ale finalne pisanie zostawia Pisarzowi.
- Dwujezycznie: ocenia w jezyku tekstu, wg wlasciwego profilu jezykowego.
WHAT YOU DO NOT DO:
- Nie pisze ani nie przepisuje tekstu za autora (to domena voice_writer)
- Nie buduje ani nie zmienia profilu stylu (to domena style_profiler)
- Nie prowadzi researchu ani nie sprawdza faktow merytorycznych (ocenia glos, nie prawdziwosc)
- Nie lagodzi werdyktu, gdy negative constraints sa zlamane
- Nie zwraca ogolnikow bez wskazania konkretnego fragmentu
ANTI-PATTERNS:
- Rubber stamp - PASS bez realnej analizy, bo tekst "wyglada ok".
- Ogolnikowy feedback - "popraw ton" bez wskazania zdania i zasady.
- Przejmowanie roli Pisarza - przepisywanie calego tekstu zamiast wskazania odchylen.
- Ignorowanie constraintow - potraktowanie zlamanej twardej zasady jak drobnostki.
- Rozwlekłosc - dlugie eseje zamiast zwiezlej listy punktow (to agent Haiku, ma byc szybki).
REPORT FORMAT:
Summary
- [werdykt PASS/REVISE + jedno zdanie uzasadnienia]
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 · 72 lines · 108 tokens per session scan A 64bf70746f54
Straznik Glosu is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (108 stars, last pushed 22d ago), licensed MIT. It adds 108 tokens to every session and 1,322 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
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
Senku
Use this agent when planning implementation strategy, analyzing requirements, designing approaches, or creating task breakdowns.
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.
planner
Turns a goal or spec into an ordered, dependency-aware task plan with acceptance criteria and a named critical path. Use when work needs sequencing before implementation starts.
docs-writer
Documents code, a feature, or an API so the next person can use it without asking - README, usage guide, or ADR. Use when writing or improving developer-facing docs.