fire-research-synthesizer

fire-research-synthesizer is an agent for Claude Code from ThierryN/fire-flow. It costs 18 tokens per session (1,144 once invoked), scanned A, original, MIT.

An autonomous agent that combines four separate research documents into one synthesis document. The documents cover technology choices, features, the surrounding ecosystem, and architecture patterns.

In plain words
What is it for?
Use it after the specified FIRE research workflows finish, when four research files need to be read, cross-checked, deduplicated, and merged.
Why use it?
It reduces duplicated findings and brings parallel research into one organized result for project planning.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the dominion-flow plugin — 5 skills, 51 commands, 13 agents shipped together

Good fit Use it after the specified FIRE research workflows finish, when four research files need to be read, cross-checked, deduplicated, and merged.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thierryn/fire-flow/fire-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/ThierryN/fire-flow

Made for: Claude Code.

Or install dominion-flow, the plugin that ships this one along with the rest of its 5 skills, 51 commands, 13 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 fire-research-synthesizer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/thierryn/fire-flow/fire-research-synthesizer"><img src="https://agentmods.dev/badge/agents/thierryn/fire-flow/fire-research-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,144 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 $0.00018 $0.01144
Opus 5 $0.00009 $0.00572
Sonnet 5 $0.00004 $0.00229
Haiku 4.5 $0.00002 $0.00114

Measured 9d ago against content hash 34e59593d697, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

fire-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 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.

agents/fire-research-synthesizer.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fire Research Synthesizer Agent

<command_wiring>

Command Integration

This agent is spawned by:

  • fire-1-new (new project) — After 4 researchers complete, synthesizer merges their outputs
  • fire-new-milestone (new milestone) — Same merge step after parallel research

The synthesizer receives paths to all 4 research documents and produces a single merged output.

</command_wiring>


Configuration

name: fire-research-synthesizer
type: autonomous
color: cyan
description: Merges 4 research documents into unified synthesis
tools:
  - Read
  - Write
  - Glob
  - Grep
allowed_references:
  - "@.planning/research/"
  - "@.planning/"
  - "@skills-library/"

Process

Step 1: Read All Research Documents

ls .planning/research/*.md

Read all 4 documents:

  • 01-stack.md — Technology stack research
  • 02-features.md — Feature scope research
  • 03-ecosystem.md — Integration/ecosystem research
  • 04-patterns.md — Patterns and architecture research

Step 2: Cross-Reference and Deduplicate

For each finding across all 4 documents:

  1. Deduplicate — Same finding from multiple researchers gets merged (note it was found by N researchers = higher confidence)
  2. Resolve conflicts — If researchers disagree (e.g., different framework recommendations), document both positions with pros/cons
  3. Map dependencies — Stack findings inform feature feasibility; ecosystem choices constrain patterns

Step 3: Prioritize Findings

Score each finding:

Priority = Impact × Confidence × Urgency

Impact:    HIGH=3, MEDIUM=2, LOW=1
Confidence: Found by 3+ researchers=3, 2=2, 1=1
Urgency:   Blocks other work=3, Should do early=2, Can defer=1

Read the full file on GitHub · 167 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 · 167 lines · 18 tokens per session scan A 34e59593d697

Subscribe to this mod's changes

fire-research-synthesizer is an agent published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 26d ago), licensed MIT. It adds 18 tokens to every session and 1,144 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 2026-08-30.