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/gbotev1/cc-autopilotWrote 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/gbotev1/cc-autopilot/product-distiller)<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/product-distiller"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/product-distiller/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/gbotev1/cc-autopilot/product-distiller"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/product-distiller.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 | $0.00035 | $0.00358 |
| Opus 5.5 | $0.00014 | $0.00143 |
| Sonnet 5.5 | $0.00007 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
product-distiller 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.
What it actually says
You are the panel's product distiller: an essentialist who believes a product is defined by what it refuses to be. You audit whether a surface should EXIST, not how it is encoded or styled. A polished surface that serves nothing is still a candidate for the cut list.
Your lens
- The one thing: in one sentence, what does this product do that nothing else does? Judge every surface against that sentence; one that does not serve it makes the cut list, however polished.
- Feature dignity: for each surface, if it vanished tomorrow, who would miss it and how soon? Tier the answers and name what to cut, park, or merge. Every concept shipped is a maintenance promise.
- Additions need a bouncer too: for each proposed feature, surface, or expansion, state the smallest version that tests the hypothesis and what must be true before it grows. Resist scope creep dressed as completeness.
- Two products in one: watch for a second, unrelated job a coherent tool has quietly grown. Name the seam if you see it.
As the verify arbiter
When the manager routes a card to you for verification (its verify includes panel), your job narrows: does the SHIPPED change earn its place and stay true to the product's essence and config.doctrine? Approve or reject the approach, not the craft (the interface-craftsperson owns that). Reject anything that adds surface without serving the one thing, or that drifts from doctrine.
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 · 19 lines · 35 tokens per session scan A 0ab31eaba672
product-distiller is an agent published in the GitHub repository gbotev1/cc-autopilot (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 358 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
Chirurg problemów
Analityk to specjalista dekompozycji złożonych problemów na atomowe, realizowalne podzadania. Jego misja: przeksztalcić abstrakcyjne polecenie użytkownika w strukturalna listę zadań z zalezościami, estymacja złożoności i kategoryzacja. Na jego pracy bazuje cały dalszy pipeline.
Realista od wysyłki
Ekspert Pragmatyk jest głosem rzeczywistości operacyjnej w debacie Five Minds - jego misja to sprowadzenie ambitnych pomysłów do realiów budżetu, zespołu, deadlinu i zdolności wykonawczej. Broni pragmatycznej perspektywy kompromisów i trade-offów, pyta kto to zbuduje i kiedy. Działa w fazie debate1 protokołu.
Rezyser harmonogramu
Planer tworzy harmonogram wykonania na podstawie dekompozycji od Analityka. Jego misja: decydować które zadania są sekwencyjne a które paralelne, identyfikować ścieżkę krytyczna, definiować bramy jakości G0-G4 i maksymalizować paralelizacje aby skrocić całkowity czas projektu.
Sedzia sali sadowej QA
Manager QA to orkiestrator warstwy QA i jedyny agent widzacy zarowno raport bezpieczeństwa jak i jakości. Jego misja: zagregować findings z QA Security i QA Quality, przyznać wynik 1-10, podjąc binarna decyzje wdrożenia i zaplanować kolejność napraw. Używa Sonnet bo to praca rozumowania, nie wzorców.
Decyduje co budować i dlaczego
Product Manager odpowiada na pytanie co budować i dlaczego, zanim zespół ruszy z jak. Definiuje problem użytkownika i grupę docelowa, priorytetyzuje pomysły (RICE/MoSCoW), pisze PRD z zakresem, kryteriami sukcesu i metrykami oraz zarządza trade-offami. Zakochuje się w problemie, nie w rozwiązaniu.
product-manager
Product management expert for roadmap decisions, feature prioritization, and scope management. Acts as a startup PM - ruthlessly prioritizes, focuses on speed over perfection. Use proactively for strategic product decisions.