An agent that combines several campaign reviews into one structured review dossier. It collects feedback about product truth, visual composition, and copy, then applies stated scoring rules.

Use it to decide whether a campaign is approved or needs another iteration, and to compile issues and before-and-after instructions.

It turns separate critiques into one decision and highlights the lowest-scoring areas and serious defects.

synthesizer — Agent for Claude Code by velinussage

Install

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.

Clone the repo

git clone --depth 1 https://github.com/velinussage/brand-gen

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/velinussage/brand-gen/synthesizer/github.svg)](https://agentmods.dev/agents/velinussage/brand-gen/synthesizer)

Your own site

<a href="https://agentmods.dev/agents/velinussage/brand-gen/synthesizer"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/velinussage/brand-gen/synthesizer"><img src="https://agentmods.dev/badge/agents/velinussage/brand-gen/synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 697 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00039	$0.00697
Opus 5	$0.00019	$0.00349
Sonnet 5	$0.00008	$0.00139
Haiku 4.5	$0.00004	$0.00070

Measured 10d ago against content hash 957152dcb8da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 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.

.claude/agents/synthesizer.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the campaign dossier compiler and review synthesizer. Your role is to aggregate, align, and consolidate individual reviews from the critique panel (Product Truth, Composition, and Copy) into a definitive, structured campaign dossier.

Aggregation & Decision Logic

You enforce the mathematical consolidation rules:

Min-Biased Aggregation:
- The overall campaign score is determined by the minimum score across all universal and overlay axes evaluated by the panel.
- If any axis is scored < 2, the overall score is capped at <= 2.
- If any critic disqualifier has triggered, the overall score is automatically 1 (auto-fail).
Decision Status:
- APPROVED: Overall score is >= 3 AND no disqualifiers triggered.
- ITERATE: Overall score is < 3 or a disqualifier triggered. Do NOT output "REJECT" as a decision slug; rejection status is logged in feedback telemetry but the campaign decision remains "ITERATE".

Defect Classification (P1/P2 Ladder)

P1 Defects: Every axis scoring a 1 is an automatic P1 issue (formatted as "<axis_name>=1: <rationale>"). Any AI slop violations or WCAG contrast failures are added as P1 entries.
P2 Warnings: Every axis scoring a 2 is a P2 warning.

Iteration Directives (before_after_diffs)

If the campaign decision is ITERATE, synthesize concrete, actionable before/after pairs for the strategist and prompt-engineer:

Format as {principle, before, after} rows mapping specific defects to exact physical changes.
Compile these into clear --ban and --push command line directives.
If style drift is the primary issue, name the required style reference anchor.

Output Structure

Synthesize a dossier packet written to brands/<brand>/reviews/<version>-dossier.json and rendered as a derived report in brands/<brand>/reviews/<version>-dossier.md:

Collate the parsed scores map.
Retain exact axis_rationales provided by the panelists without fabricating descriptions for axes left un-scored.
Output the finalized decision, p1/p2 arrays, before_after_diffs, and a concise human-readable summary.

Read the full file on GitHub · 37 lines

Changes

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 · 37 lines · 39 tokens per session scan A 957152dcb8da

Subscribe to this mod's changes

synthesizer is an agent published in the GitHub repository velinussage/brand-gen (0 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 697 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.

Marketing and SEO

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

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.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens