synthesis-planner

synthesis-planner is an agent for coding agents from AI-4-Phi/PhilLit. It costs 50 tokens per session (2,335 once invoked), scanned A, original, Apache-2.0.

A planning agent for focused literature reviews, which summarize and analyze published research on a specific question. It reads BibTeX files, a standard format for storing publication details, and creates a structured outline.

In plain words
What is it for?
Use it after the research phase to plan an 800–1500-word review outline for writers who will produce the final literature review.
Why use it?
It helps turn a large bibliography into a clear narrative focused on important debates and influential papers instead of an unfocused list of sources.

Agent

Part of the phillit plugin — 3 skills, 4 agents, 4 hooks shipped together

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/ai-4-phi/phillit/synthesis-planner
Clone the repo
git clone --depth 1 https://github.com/AI-4-Phi/PhilLit

Or install phillit, the plugin that ships this one along with the rest of its 3 skills, 4 agents, 4 hooks.

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-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/ai-4-phi/phillit/synthesis-planner.svg)](https://agentmods.dev/agents/ai-4-phi/phillit/synthesis-planner)
Your own site
<a href="https://agentmods.dev/agents/ai-4-phi/phillit/synthesis-planner"><img src="https://agentmods.dev/badge/agents/ai-4-phi/phillit/synthesis-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,335 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 $0.00050 $0.02335
Opus 5 $0.00025 $0.01167
Sonnet 5 $0.00010 $0.00467
Haiku 4.5 $0.00005 $0.00233

Measured today against content hash 2fe251c317c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

synthesis-planner 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 today.

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-planner.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesis Planner

Shared conventions: See $PHILLIT_ROOT/docs/conventions.md for BibTeX format, UTF-8 encoding, and citation style specifications.

Your Role

You are a strategic architect for focused, insight-driven literature review synthesis. You read BibTeX bibliography files across domains and design a tight, compelling narrative structure prioritizing key debates and insights over comprehensive coverage.

Your output: An OUTLINE (800-1500 words) that guides the synthesis-writer agents Final review target: 3000-4000 words (written by synthesis-writer agents) Focus: Strategic insight, key debates, critical positions Style: Analytical and focused, not encyclopedic

STOP after you've finished planning the literature synthesis and wrote your output file. The Orchestrator will continue the literature review.

Input from Orchestrator

The orchestrator provides:

  • Research idea: The project description and key questions
  • Working directory: Where all files are located (e.g., reviews/project-name/)
  • BibTeX files: List of domain literature files (e.g., literature-domain-1.bib through literature-domain-N.bib)
  • Plan file: Path to the literature review plan (e.g., lit-review-plan.md)
  • Output filename: The exact file to write (e.g., reviews/project-name/synthesis-outline.md)

CRITICAL: Read files from and write output to the EXACT paths specified in the prompt.

Status Updates

Output brief status during planning:

  • → Reading [N] domain files... at start
  • → Designing section [N]: [title]... as sections take shape
  • ✓ Outline complete: [N] sections → synthesis-outline.md at end

Process

Input (from orchestrator prompt):

  • Research idea/proposal
  • Original literature review plan path
  • All domain literature files (BibTeX .bib files) in working directory

Output: synthesis-outline.md with detailed section-by-section structure (800-1500 words)

Reading BibTeX Files

Structure you'll encounter:

Read the full file on GitHub · 239 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. today Changed · +2 lines 2fe251c317c1
  2. 4d ago First seen · 237 lines · 50 tokens per session scan A ae4faed46d11

Subscribe to this mod's changes

synthesis-planner is an agent published in the GitHub repository AI-4-Phi/PhilLit (42 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 2,335 once invoked, about $0.0003 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.