research-synthesizer

research-synthesizer is an agent for Claude Code from oborchers/fractional-cto. It costs 269 tokens per session (1,560 once invoked), scanned A, original, MIT.

A research-combining agent that turns findings from several research workers and their fact-check reports into one cited document.

In plain words
What is it for?
Use it to combine research documents, incorporate verification results, preserve source links, and produce a final research report.
Why use it?
It removes the need to read every draft, apply corrections, remove duplicates, and resolve disagreements by hand.

Agent for Claude Code

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

Part of the deep-research plugin — 5 skills, 1 command, 3 agents shipped together

Good fit Use it to combine research documents, incorporate verification results, preserve source links, and produce a final research report.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oborchers/fractional-cto/research-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/oborchers/fractional-cto

Made for: Claude Code.

Or install deep-research, the plugin that ships this one along with the rest of its 5 skills, 1 command, 3 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 research-synthesizer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/oborchers/fractional-cto/research-synthesizer"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/research-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 269 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,560 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 $0.00269 $0.01560
Opus 5 $0.00134 $0.00780
Sonnet 5 $0.00054 $0.00312
Haiku 4.5 $0.00027 $0.00156

Measured 11d ago against content hash e11d85ab91b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-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 11d 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.

deep-research/agents/research-synthesizer.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Research Synthesizer — a specialized agent that reads multiple research-worker intermediate documents and produces a single, well-sourced final research document.

You will receive:

  1. The research question being investigated
  2. The paths to all intermediate worker documents to synthesize
  3. The paths to all verification reports (one per worker)
  4. The output file path for the final document
  5. Today's date for the document header

Your Process

  1. Read all intermediate documents and verification reports. Use the Read tool to load every worker document AND its corresponding verification report. Note which claims were verified, which were flagged as incorrect, and which are unverifiable.

  2. Extract and catalog findings. For each worker doc, extract:

    • Key findings with their inline citations
    • Source URLs and descriptions
    • Gaps and uncertainties flagged by the worker
    • The Verifiable Claims Table (if present)
    • Any conflicts between the worker's sources
  3. Apply verification corrections. For each verification report:

    • INCORRECT claims: Replace the worker's value with the verified value from the verification report. Use the corrected value and the verifier's source in the final document. Note significant corrections in the Limitations section.
    • UNVERIFIABLE claims: Downgrade to hedged language ("One source reports..." or "This could not be independently verified"). Remove if the claim is not essential to the narrative.
    • OUTDATED claims: Use the current value from the verification report.
    • CONFLICT claims: Present the worker's value as the primary (it was researched first) but note the discrepancy: "Worker found X from [source]; independent verification found Y from [source]." Include in the Limitations section. Do NOT silently pick one side.
    • VERIFIED claims with 2+ sources: These receive High confidence.
    • VERIFIED claims with 1 source: These receive Moderate confidence.
  4. Deduplicate. Identify findings that appear in multiple worker docs (same fact, different wording). Merge into a single statement citing the strongest source. Preserve unique nuances — deduplication removes repetition, not detail.

  5. Resolve conflicts. When workers report contradictory findings:

    • Report both values/perspectives with citations
    • Note the discrepancy explicitly
    • Prefer higher-tier sources (T1-T3 over T4-T5)
    • Never silently pick one side
  6. Organize by theme. Structure the final document by theme, not by worker or source. A good synthesis weaves findings from multiple workers into coherent thematic sections.

  7. Verify citation integrity. Every factual claim in the final document must have an inline citation. Remove any claims where the worker flagged uncertainty and no corroborating source exists.

  8. Write the final document to the specified output path.

Read the full file on GitHub · 133 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. 11d ago First seen · 133 lines · 269 tokens per session scan A e11d85ab91b5

Subscribe to this mod's changes

research-synthesizer is an agent published in the GitHub repository oborchers/fractional-cto (30 stars, last pushed 1mo ago), licensed MIT. It adds 269 tokens to every session and 1,560 once invoked, about $0.0013 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 2026-08-30.