synthesizer

synthesizer is an agent for coding agents from AMDResearch/ai4science-studio. It costs 0 tokens per session (1,206 once invoked), scanned A, original, MIT.

A task-specific helper that combines verified findings from Tracelens and Omnistat into one bottleneck report. It removes duplicate findings and ranks the remaining issues.

In plain words
What is it for?
Use it after a performance run to create a combined_report.md from the two verified-claims files.
Why use it?
It avoids manually comparing two performance reports and makes disagreements or uncertain findings visible.

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/amdresearch/ai4science-studio/synthesizer
Clone the repo
git clone --depth 1 https://github.com/AMDResearch/ai4science-studio

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 synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/amdresearch/ai4science-studio/synthesizer.svg)](https://agentmods.dev/agents/amdresearch/ai4science-studio/synthesizer)
Your own site
<a href="https://agentmods.dev/agents/amdresearch/ai4science-studio/synthesizer"><img src="https://agentmods.dev/badge/agents/amdresearch/ai4science-studio/synthesizer.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 1,206 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 $0.01206
Opus 5 $0.00000 $0.00603
Sonnet 5 $0.00000 $0.00241
Haiku 4.5 $0.00000 $0.00121

Measured 5d ago against content hash 989dd91c66e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

earth_science/models/ORBIT-2/recipes/perf-analysis/agents/synthesizer.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

synthesizer subagent

Merge tracelens/verified_claims.json and omnistat/verified_claims.json into a single ranked, deduplicated bottleneck report.

Inputs

  • <perf_run_dir>/manifest.json
  • <perf_run_dir>/tracelens/verified_claims.json
  • <perf_run_dir>/omnistat/verified_claims.json
  • (Optional) <perf_run_dir>/tracelens/report_summary.md, <perf_run_dir>/omnistat/report_summary.md

Outputs

  • <perf_run_dir>/combined_report.md

Steps

1. Load and filter

import json
tl = json.load(open(f"{perf_run}/tracelens/verified_claims.json"))
om = json.load(open(f"{perf_run}/omnistat/verified_claims.json"))
all_claims = [{"src":"TL", **c} for c in tl] + [{"src":"OS", **c} for c in om]

Drop verdict == "refuted". Keep inconclusive claims but tag them so the user sees the gap.

2. Deduplicate by class + topic

Group claims by class. Within each group, merge claims that look like the same finding from two sources. Heuristic:

  • Both have class=comm_scaleout → almost certainly the same finding viewed from trace (NCCL kernels) and telemetry (network rates). Merge into one entry that lists both src values and both magnitudes.
  • One says gpu_compute low TFLOP/s, the other says gpu_memory_hbm high HBM% — these are likely the same root cause (memory-bound kernel) seen two ways. The synthesizer should call this out as a single finding with both signatures.

3. Rank

Score = magnitude.value × confidence_weight × (corroborated ? 1.5 : 1.0). confidence_weight: high=1.0, medium=0.7, low=0.4. corroborated = both TL and OS contributed to the merged entry.

4. Tag "system limit reached"

A claim is a system limit if any of:

  • proposed_remedy is null
  • both verdict=verified and remedy_probe.delta_pct is small (< 5%)
  • the metric matches a documented MI355X spec ceiling (e.g. fp64 39 TFLOP/s, HBM 8 TB/s, ANP scale-out ~25 GB/s)

Mark these explicitly so the report doesn't promise a fix that won't materialize.

5. Write combined_report.md

Read the full file on GitHub · 132 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 · 132 lines · 0 tokens per session scan A 989dd91c66e4

Subscribe to this mod's changes

synthesizer is an agent published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,206 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 2026-08-31.