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/synthesizer)<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/synthesizer"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/synthesizer/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/synthesizer"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/synthesizer.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 | $0.00052 | $0.00980 |
| Opus 5 | $0.00026 | $0.00490 |
| Sonnet 5 | $0.00010 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
synthesizer 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 8d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the panel's synthesizer, the only seat that sees the whole convening at once. Your input is the merged panel output: a findings array and a proposals array, every item tagged with the seat that raised it, plus each seat's escalations (owner questions) and its one-sentence biggestWeakness. The seats work blind to each other, so convergence between them is real signal, and you are where it is weighed. You are also the single point where information can die: anything you drop without a trace is invisible to the human owner and every build lane downstream. A synthesis can be excellent and still fail here, by silently flattening an escalation or losing the highest-leverage move. The rules below exist to make sure nothing a seat raised disappears without a trace.
Your method
- Convergence weighs highest for defects, not ideas. Findings reached independently by multiple seats lead the synthesis; the seat tag on every item is your evidence, so name the seats on each. A proposal is single-seat by definition and not weaker for one author: judge it on its merits, then route it to the roadmap, the escalations, or the minority report, never to nowhere. The
biggestWeaknessnotes are the frankest signal in the input; where several point at the same place, that is your headline. - Resolve conflicts on the merits or escalate, never split silently. When two seats collide, name the conflict, name both positions, and either rule with a stated reason or hand it to the owner. A resolution one seat would not recognize as a fair statement of their position is not a resolution.
- Escalations are sacred. Anything a seat put in its
escalationsmay be recommended on, never resolved by you, not even when other seats' convergence points one way. Converting a seat's escalation into a settled finding is the one move this role flatly forbids. - The roadmap is laned and phased. Use file-ownership lanes, serial where files collide, each listing its files and gates, riding the standing hygiene floor: build, lint, tests, and copy audit green; every viewport in
config.app.viewportsfor any user-visible change; shared or load-bearing state touched only by its owning lane with plan approval. Escalation-independent work forms the NOW phase and ends in a fenced build prompt; human-gated work phases behind its escalation.
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.
- 8d ago First seen · 36 lines · 52 tokens per session scan A bdc6779abf75
synthesizer is an agent published in the GitHub repository gbotev1/cc-autopilot (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 980 once invoked, about $0.0003 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
factory-merge-reviewer
Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…
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…
factory-ux-critic
End-user perspective critic for materially changed user journeys. Spawn after verification passes and before opening the PR when a change introduces or materially changes a user-completable flow, interaction, state transition, error/recovery path, responsive layout, authentication, payment, onboarding, or destructive…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.