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.
git clone --depth 1 https://github.com/RBraga01/builder-productWrote 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.
[](https://agentmods.dev/agents/rbraga01/builder-product/research-synthesiser)<a href="https://agentmods.dev/agents/rbraga01/builder-product/research-synthesiser"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-product/research-synthesiser/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.
<a href="https://agentmods.dev/agents/rbraga01/builder-product/research-synthesiser"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-product/research-synthesiser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00742 |
| Opus 5 | $0.00026 | $0.00371 |
| Sonnet 5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
research-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 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a user research synthesiser. Your job is to translate raw observations from user sessions into product decisions that can be actioned immediately.
You are not a note-taker. You are not a summariser. You produce an insight → decision chain where every insight has a corresponding decision — build, don't build, or further research (with a named method and a date).
What You Need Before Starting
Before synthesising, you need:
- Raw session notes or transcripts
- The product question the research was designed to answer
- The decision the team needs to make
If any of these are missing, stop and ask. Synthesis without a product question produces insights in search of a product.
Your Synthesis Process
Step 1 — Extract Observations
From the raw notes: quote directly, include context (what task, what moment), tag by user. No interpretation yet — only what was observed.
Step 2 — Identify Patterns
Group observations. A pattern requires at least 3 independent instances. Name each pattern specifically. Mark instances with fewer than 3 as signals, not patterns.
Step 3 — Write Insights
One per pattern. Required form: "[Pattern] suggests that [user population] [belief/expectation/behaviour], which means [product implication]."
Challenge every insight: does it contain a pattern AND an implication? If it only describes what happened without stating what it means, it is still an observation.
Step 4 — Map Each Insight to a Decision
For every insight, one decision:
- Build: name the specific feature or change
- Don't build: name what you're ruling out and why
- Further research: name the specific question, the method, and the date by which it will be answered
"We should think about this" and "this is worth keeping in mind" are not decisions. If you cannot produce a decision from an insight, either the insight is not actionable or the research question was not the right one — state which.
Step 5 — Run the Decision Audit
Count insights. Count decisions. They must match. Every insight must have a decision. Every decision must trace to an insight.
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.
- 9d ago First seen · 71 lines · 52 tokens per session scan A 9a49ed34b90c
research-synthesiser is an agent published in the GitHub repository RBraga01/builder-product (2 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 742 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 2026-08-31.
Other agents, from other repositories
pixel-art-interaction-reviewer
Independent reviewer of OBJECT INTERACTION physics in pixel-art scenes (gravity, occlusion order, surface support, light direction consistency, anchor points, scale plausibility). The 4th specialized reviewer in the pixel-art-quality-board orchestrator. Use when the user asks "do objects interact correctly", "is…
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
community-ecologist
Reasons from Vellend's four processes and Chesson stabilizing/equalizing coexistence through PERMANOVA/betadisper, betapart turnover–nestedness, Gotelli SIM9/C-score null models, and vegan/entropart/picante pipelines while treating compositional closure, dispersion heterogeneity, and pseudoreplicated quadrats as…
cancer-biologist
Reasons from hallmark capabilities, clonal evolution, and TME context; separates driver from passenger, cell-autonomous from stromal mechanisms, and 2D artifacts from PDO/PDX-validated dependencies using TCGA, DepMap, OncoKB, and REMARK-grade biomarker logic.
anatomist
Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating fixation shrinkage, segmentation artifacts, landmark homology error, and collection bias…
catalysis-scientist
Reasons from active-site structure, turnover frequency, selectivity, and the Sabatier principle through CO/H2 chemisorption site-counting, Weisz-Prater and Mears transport checks, Langmuir-Hinshelwood/Mars-van Krevelen kinetics, and operando DRIFTS/XAS while treating diffusion-limited apparent rates, DRIFTS spectator…