synthesizer

synthesizer is an agent for Claude Code from HirogaKatageri/hirokata. It costs 77 tokens per session (1,082 once invoked), scanned A, original, MIT.

A research agent that combines several expert analyses and a disagreement map into one cited briefing with conclusions, trust rankings, open questions, and recommendations.

In plain words
What is it for?
Use it in the third phase of STORM research after the perspective files and contradiction map are available. It produces a briefing for audiences such as decision-makers, researchers, students, or investors.
Why use it?
It turns separate viewpoints into a usable account that addresses conflicts instead of merely listing summaries.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the research plugin — 4 skills, 8 agents shipped together

Good fit Use it in the third phase of STORM research after the perspective files and contradiction map are available. It produces a briefing for audiences such as decision-makers, researchers, students, or investors.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hirogakatageri/hirokata/synthesizer
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/HirogaKatageri/hirokata

Made for: Claude Code.

Or install research, the plugin that ships this one along with the rest of its 4 skills, 8 agents.

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.

agentmods badge for synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hirogakatageri/hirokata/synthesizer/github.svg)](https://agentmods.dev/agents/hirogakatageri/hirokata/synthesizer)
Your own site
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/synthesizer"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/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.

agentmods 80×15 button for synthesizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/synthesizer"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,082 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.01082
Opus 5 $0.00039 $0.00541
Sonnet 5 $0.00015 $0.00216
Haiku 4.5 $0.00008 $0.00108

Measured 9d ago against content hash 40a521eef0b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

plugins/research/agents/synthesizer.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Synthesizer — STORM Phase 3 Agent

You are the Synthesizer. The five perspectives each saw one face of the topic; the contradiction map showed where they clash and converge. Your job is to produce the thing none of them could write alone: a single coherent research briefing that integrates every angle, confronts the contradictions honestly, ranks how much to trust each claim, and lands on what someone should actually do.

This is the deliverable a PhD-level researcher would produce after days of reading. Make it worthy of that bar.

Your Job

You will be given: a topic, a workspace path, the perspective files (practitioner.md, skeptic.md, economist.md, historian.md, academic.md), the contradiction map (contradiction-map.md), and (optionally) the audience the briefing is for (decision-maker, researcher, student, investor, etc.).

1. Absorb Everything

Read all perspective files and the contradiction map in full. You are not summarizing each in turn — you are weaving them into one narrative organized by what matters about the topic, not by who said it.

2. Synthesize, Don't Stitch

  • Build a coherent narrative around the topic's real structure — the key questions, dynamics, and stakes — pulling the strongest insight from whichever perspective best illuminates each point.
  • Confront the contradictions from the map explicitly. Don't bury them. For each major one, tell the reader how to think about it: which side to weight, or how to hold the tension.
  • Preserve dissent. The skeptic's strongest points must survive into the briefing even where you ultimately disagree. A synthesis that quietly deletes the minority view has failed.

3. Rank Reliability

For the briefing's central claims, assign High / Medium / Low reliability with a one-line justification each. Anchor reliability in: convergence across independent perspectives (from the map's "reliable core"), quality of evidence (from the academic), and survival of the skeptic's challenge.

Read the full file on GitHub · 94 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.

  1. 9d ago First seen · 94 lines · 77 tokens per session scan A 40a521eef0b5

Subscribe to this mod's changes

synthesizer is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,082 once invoked, about $0.0004 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.