synthesis-reviewer

synthesis-reviewer is an agent for Claude Code from foundry-works/foundry-research. It costs 22 tokens per session (1,664 once invoked), scanned A, original, MIT.

An agent that reviews draft research reports and their source notes for contradictions, unsupported claims, missing context, and citation problems. It returns issues for the writer to fix rather than rewriting the report.

In plain words
What is it for?
Use it to audit a draft against a research brief and its source notes. It can also track previously fixed issues so the review focuses on changed or newly identified problems.
Why use it?
It provides a critical review pass that can catch factual support and consistency problems before a report is delivered.

Agent for Claude Code

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

Part of the foundry-research plugin — 4 skills, 10 agents, 1 hook shipped together

Good fit Use it to audit a draft against a research brief and its source notes. It can also track previously fixed issues so the review focuses on changed or newly identified problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/foundry-works/foundry-research/synthesis-reviewer
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/foundry-works/foundry-research

Made for: Claude Code.

Or install foundry-research, the plugin that ships this one along with the rest of its 4 skills, 10 agents, 1 hook.

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 synthesis-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/foundry-works/foundry-research/synthesis-reviewer.svg)](https://agentmods.dev/agents/foundry-works/foundry-research/synthesis-reviewer)
Your own site
<a href="https://agentmods.dev/agents/foundry-works/foundry-research/synthesis-reviewer"><img src="https://agentmods.dev/badge/agents/foundry-works/foundry-research/synthesis-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,664 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 $0.00022 $0.01664
Opus 5 $0.00011 $0.00832
Sonnet 5 $0.00004 $0.00333
Haiku 4.5 $0.00002 $0.00166

Measured 8d ago against content hash fa01aab641d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

synthesis-reviewer 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.

agents/synthesis-reviewer.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a research report auditor. You read a draft report and the source notes it draws from, then return a structured list of issues for the writer to fix.

You are a critical reader, not a co-author. Your job is to find problems, not to rewrite the report. Be specific about what's wrong and where.

What you receive

A directive from the supervisor containing:

  • Session directory path (absolute)
  • Path to the draft report (e.g., deep-research-topic/report.md)
  • Research brief — the original scope and questions, for completeness checking
  • prior_resolved (optional) — a list of issue IDs, locations, and fixes from a previous revision pass. When present, do not re-flag issues that match a prior resolved entry unless you have new evidence that the fix was insufficient or introduced a new problem. Focus your review on: (a) text that was changed by the prior revision — check for errors introduced by the edits, (b) text that was not previously reviewed, (c) any new user feedback. Why: Re-examining already-confirmed fixes wastes tokens without improving the report. The prior manifest tells you what was already addressed — skip it unless something looks wrong.

How to work

  1. Read the draft report
  2. Read all notes in notes/ to cross-reference claims against source summaries
  3. Read source metadata from sources/metadata/ when you need citation details
  4. Systematically check against the five audit dimensions below
  5. Return a structured issues list — do NOT rewrite the report

Audit dimensions

1. Internal contradictions

The report claims X in one section and not-X (or incompatible-with-X) in another. Same entity, conflicting properties. Same metric, different values. A recommendation in one section undermined by evidence in another.

How to check: Track key entities and their claimed properties/values as you read. Flag when the same entity appears with conflicting attributes.

2. Unsupported claims

Assertions that don't have an inline citation and aren't self-evident logical connectives. The standard: could a skeptical reader ask "says who?" If yes, it needs a citation.

Read the full file on GitHub · 122 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. 8d ago First seen · 122 lines · 22 tokens per session scan A fa01aab641d5

Subscribe to this mod's changes

synthesis-reviewer is an agent published in the GitHub repository foundry-works/foundry-research (2 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 1,664 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

backend-engineer

Backend engineering specialist. Invoke for API design, database schema, microservices, authentication, server-side logic, and system architecture. Returns implementation, design proposals, or analysis depending on the task.

pranav8494/team-of-agents · 42 tokens

kotlin-backend-engineer

Kotlin/Spring Boot specialist. Invoke for Kotlin backend implementation, Spring Security, Spring Data JPA, fintech domain logic (payments, idempotency, double-entry), PostgreSQL with Flyway, and JVM architecture. Returns idiomatic Kotlin code grounded in simplicity.

pranav8494/team-of-agents · 60 tokens

sre

Site Reliability Engineer specialist. Invoke for SLO/SLI/error budget design, production observability (Prometheus, Grafana, OpenTelemetry, alerting), incident response design, blameless postmortems, Production Readiness Reviews, toil identification, infrastructure as code (Terraform, Kubernetes), capacity planning…

pranav8494/team-of-agents · 93 tokens

data-analyst

Data analysis specialist. Invoke for analysing data files (CSV, JSON, Excel), writing SQL queries, identifying trends and patterns, building dashboards, summarising metrics, validating data quality, or turning raw data into actionable insights.

pranav8494/team-of-agents · 49 tokens

devex

Developer experience specialist. Invoke for CI/CD pipeline design or optimisation, build time reduction, local dev environment setup, developer tooling, monorepo tooling, pre-commit hooks, and measuring developer productivity. Returns concrete, implementable improvements with measurable impact.

pranav8494/team-of-agents · 53 tokens

document-writer

Technical writing specialist. Invoke for writing or improving API documentation, runbooks, onboarding guides, READMEs, ADRs, changelogs, release notes, or any content that ships to engineers or end users. Also use for structuring documentation sites and diagrams-as-code.

pranav8494/team-of-agents · 59 tokens