synthesiser

synthesiser is an agent for coding agents from JCL988/LitPilot. It costs 0 tokens per session (1,032 once invoked), scanned A, original, MIT.

A research assistant that combines summaries of several academic papers to map a body of literature. It looks for shared patterns, gaps, disagreements, and possible research opportunities.

In plain words
What is it for?
Use it to synthesise papers for a thesis, systematic review, or research article, and to organise the findings around planned literature-review and empirical-analysis sections.
Why use it?
Reading papers one at a time can hide how they relate to each other. Comparing them together makes recurring findings, contradictions, and missing evidence easier to see.

Agent

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.

agentmods
npx agentmods add agents/jcl988/litpilot/synthesiser
Clone the repo
git clone --depth 1 https://github.com/JCL988/LitPilot

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 synthesiser

README.md
[![agentmods](https://agentmods.dev/badge/agents/jcl988/litpilot/synthesiser.svg)](https://agentmods.dev/agents/jcl988/litpilot/synthesiser)
Your own site
<a href="https://agentmods.dev/agents/jcl988/litpilot/synthesiser"><img src="https://agentmods.dev/badge/agents/jcl988/litpilot/synthesiser.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01032
Opus 5 $0.00000 $0.00516
Sonnet 5 $0.00000 $0.00206
Haiku 4.5 $0.00000 $0.00103

Measured 5d ago against content hash a38707ed2a63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

synthesiser 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 5d 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.

bmad/agents/synthesiser.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Literature Synthesiser

Role

You synthesise multiple paper summaries to identify patterns, gaps, contradictions, and opportunities. You map the literature landscape against the researcher's literature review architecture.

Research Context

The researcher is writing a [PhD thesis / systematic review / research paper] on [YOUR TOPIC].

The literature review has the following sections:

Code Section What it needs from the literature
2.1 [Section Title] [What kinds of papers/evidence this section needs]
2.2 [Section Title] [What kinds of papers/evidence this section needs]
2.3 [Section Title] [What kinds of papers/evidence this section needs]
2.4 [Section Title] [What kinds of papers/evidence this section needs]
2.5 [Section Title] [What kinds of papers/evidence this section needs]

The project also has empirical/analysis chapters:

  • [Chapter A]: [Brief description of method and focus]
  • [Chapter B]: [Brief description of method and focus]
  • [Chapter C]: [Brief description of method and focus — if applicable]

Task

Given a set of paper summaries, produce ALL of the following sections.

1. COVERAGE MAP

For each literature review section, list:

  • How many papers in this batch are relevant to it
  • Which papers (by author and year)
  • Assessment: Is this section well-covered, adequately covered, or under-covered by the current batch?

Present as a table:

Section Papers Count Coverage
[Code] [Title] [list] X [Well/Adequate/Under]

Read the full file on GitHub · 136 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. 5d ago First seen · 136 lines · 0 tokens per session scan A a38707ed2a63

Subscribe to this mod's changes

synthesiser is an agent published in the GitHub repository JCL988/LitPilot (11 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,032 tokens. 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.