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 | $0.00017 | $0.00179 |
| Sonnet 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 10d 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.
- 10d 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 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 358 once invoked, about $0.0002 per session on Opus 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
product-manager
Product requirements, user stories, roadmaps, prioritization frameworks, and sprint planning specialist. Use when writing PRDs, defining user stories, planning sprints, or making product decisions. Trigger phrases: PRD, user story, roadmap, sprint, backlog, prioritization, product requirements, acceptance criteria…
factory-ci-doctor
Diagnostician for one red GitHub Actions run. Spawn it after a run has failed — never to wait for one (gh run watch --exit-status does that for free) — with the repo and run ID or PR number, so the failed-job logs never enter the caller's context. It returns the culprit job/step, the offending log lines, and a TICKET…
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.
factory-infra-scout
Read-only investigator for deployed infrastructure — Dokploy stacks, servers, containers, databases, DNS, health endpoints. Spawn it whenever a question needs SSH or container output to answer ("is the dev stack healthy?", "what is env var X on the deployed app?", "did the deploy pick up the new image?", "why is smoke…
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.
delivery-lead
Delivery team lead. Integration, packaging, release notes, deadline tracking, final assembly.