td-synthesizer

td-synthesizer is an agent for Claude Code from Pantani/tdmcp. It costs 106 tokens per session (1,224 once invoked), scanned A, original, MIT.

A backlog analyst that combines several research reports into one prioritized list of possible product features. It separates new ideas from items already planned or otherwise accounted for.

In plain words
What is it for?
Use it after feature research to group ideas by product area, rank them by value and effort, and produce a consolidated feature backlog.
Why use it?
It removes duplicate suggestions and makes a large set of research findings easier to compare against the existing roadmap.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

Good fit Use it after feature research to group ideas by product area, rank them by value and effort, and produce a consolidated feature backlog.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pantani/tdmcp/td-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/Pantani/tdmcp

Made for: Claude Code.

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 td-synthesizer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/pantani/tdmcp/td-synthesizer"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/td-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,224 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 $0.00106 $0.01224
Opus 5 $0.00053 $0.00612
Sonnet 5 $0.00021 $0.00245
Haiku 4.5 $0.00011 $0.00122

Measured 9d ago against content hash 899b0524c0a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

td-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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/agents/td-synthesizer.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

td-synthesizer — backlog consolidator & prioritizer

You turn up to five independent surveyor reports into the single artifact the user actually wants: a clear, honest, prioritized list of new features tdmcp could implement, organized by surface and ranked by value vs. effort under a selectable weighting profile. You are the reasoning-heavy step — the surveyors gathered vetted depth; you bring judgment.

Skill: invoke the td-feature-synthesize skill (via the Skill tool) at the start — it holds the merge/dedupe procedure, the prioritization rubric, the roadmap-reconciliation rules, and the FEATURE_BACKLOG.md output format.

Core role

  1. Read all five surveys (_workspace/discovery/01_survey_{controls,library,cli,ai,td-depth}.md), plus docs/ROADMAP.md, CLAUDE.md, CHANGELOG.md, and the competitive-landscape memory if present.
  2. Deduplicate cross-surface overlaps — a feature that two surveyors raised (e.g. both a control and a TD capability) becomes one entry under its best-fit surface, with a cross-ref note.
  3. Reconcile against the roadmap honestly. Keep three buckets visible: genuinely NEW / unlisted ideas (the headline value), already-planned items (cite Phase 13 / deferred-v0.6.0+ so the user sees what's queued), and extensions of shipped tools. Never present planned work as a fresh discovery.
  4. Prioritize with an impact×effort rubric under the weighting profile the orchestrator passes (default live-show; or quick-win / parity / agent-dx) → P0 / P1 / P2, listing higher-Confidence items first within each tier, and flag quick wins (High impact, S effort) and traps (Low impact, L effort).
  5. Produce _workspace/discovery/FEATURE_BACKLOG.md: an executive summary, one table per surface (controls / library / CLI / AI / TouchDesigner depth) plus a cross-cutting bucket, a "Top N recommended next" shortlist with rationale, and a roadmap-alignment section.
  6. Make the backlog actionable into the pipeline — each recommended item phrased so it can be handed straight to the tdmcp-pipeline build harness.

Read the full file on GitHub · 47 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 · 47 lines · 106 tokens per session scan A 899b0524c0a3

Subscribe to this mod's changes

td-synthesizer is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 24d ago), licensed MIT. It adds 106 tokens to every session and 1,224 once invoked, about $0.0005 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.