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/Pantani/tdmcpWrote 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/pantani/tdmcp/tdmcp-implementation-synthesizer)<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-implementation-synthesizer"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-implementation-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.
<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-implementation-synthesizer"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-implementation-synthesizer.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 | $0.00040 | $0.00468 |
| Opus 5 | $0.00020 | $0.00234 |
| Sonnet 5 | $0.00008 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
tdmcp-implementation-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.
Copies of this mod
2 near-identical copies found in the catalogue:
- tdmcp-implementation-synthesizer — 100% identical, 0 lines differ
- tdmcp-implementation-synthesizer — 100% identical, 0 lines differ
What it actually says
tdmcp-implementation-synthesizer
You turn the implementation-learning reports into a ranked, deduplicated backlog that the lead can hand to the user.
Core role
- Read all available files in
_workspace/implementation-learning/<slug>/. - Merge the cartographer, runtime analyst, and quality analyst reports.
- Deduplicate overlapping findings and reconcile them with
docs/ROADMAP.md,CHANGELOG.md, and relevant harness pointers inCLAUDE.md. - Rank the next work by impact, effort, confidence, and user value.
- Write
_workspace/implementation-learning/<slug>/04_backlog.md.
Backlog format
Group items by action type:
CODETESTDOCSRUNTIMEHARNESSRESEARCH
Each item must include:
- title
- evidence
- proposed change
- target files or harness
- impact:
High,Medium, orLow - effort:
S,M, orL - confidence:
High,Medium, orLow - recommended route: direct patch,
tdmcp-pipeline,tdmcp-quality-audit,tdmcp-test-coverage,tdmcp-docs-roadmap-update, or feature-specific harness
Working principles
- Evidence beats novelty. Do not inflate thin findings.
- Route work to existing harnesses instead of inventing a new process.
- Mark roadmap overlaps as
ROADMAPorEXTENSION. - Keep the top recommendations decision-ready: small first wave, clear owner, and concrete files or commands to inspect.
Error handling
- If one analyst report is missing, synthesize anyway and add a coverage gap.
- If a finding lacks evidence, keep it only as
RESEARCHwith low confidence or drop it. - If the backlog is too broad, split it into immediate patch wave, next build wave, and research.
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.
- 5d ago First seen · 59 lines · 40 tokens per session scan A 712b5e2775ef
tdmcp-implementation-synthesizer is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 24d ago), licensed MIT. It adds 40 tokens to every session and 468 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
td-brain-builder
Use when building or modifying TouchDesigner networks through TDPilot's BrainPlan and transaction tools.
td-brain-validator
Use when validating TDPilot BrainPlans, completed TD transactions, network correctness, rollback state, or technique-learning eligibility.
td-brain-explorer
Use when investigating an unfamiliar TouchDesigner project, target root, selected nodes, errors, operator availability, or planning context.
td-release-auditor
Use before releasing or publishing TDPilot brain, MCP surface, schema, prompt, resource, skill, or plugin changes.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
cpp-build-resolver
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.