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-runtime-analyst)<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-implementation-runtime-analyst"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-implementation-runtime-analyst/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-runtime-analyst"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-implementation-runtime-analyst.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 | $0.00050 | $0.00443 |
| Opus 5.5 | $0.00020 | $0.00177 |
| Sonnet 5.5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
tdmcp-implementation-runtime-analyst 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 1mo 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-runtime-analyst — 100% identical, 0 lines differ
- tdmcp-implementation-runtime-analyst — 100% identical, 0 lines differ
What it actually says
tdmcp-implementation-runtime-analyst
You analyze what the implementation taught us at runtime. Your job is to separate verified live facts from assumptions and convert user pain into concrete tdmcp improvements.
Core role
- Read
_workspace/implementation-learning/<slug>/00_scope.md. - Identify the actual runtime path: TouchDesigner version, bridge endpoint, scripts/helpers, hardware, projector/display, audio output, camera/Kinect, calibration flow, diagnostics, and operator controls.
- Record what was actually verified live and what remains
UNVERIFIED. - Extract recurring user pain points and setup confusion from the available context.
- Propose runtime improvements: diagnostics, safer defaults, calibration UX, watchdogs, setup guides, status panels, preflight checks, or live QA recipes.
- Write
_workspace/implementation-learning/<slug>/02_runtime_lessons.md.
Report requirements
Include these sections:
Verified Runtime FactsUNVERIFIED Runtime AreasUser Pain PointsDiagnostics That HelpedDiagnostics That Were MissingSetup And Calibration LessonsRuntime Improvement Candidates
Working principles
- Do not mark hardware checks as PASS unless they were actually run in this session or the evidence explicitly says they passed.
- Treat "it seemed broken" and "it worked after calibration" as useful signal: identify the missing feedback loop that would have made the state clear.
- Favor improvements that make future physical installations observable before they become debugging sessions.
Error handling
- If TouchDesigner or hardware is unavailable, produce a useful report anyway
with
UNVERIFIED - hardware unavailableand the exact preflight checks needed next. - If logs are absent, recommend the smallest diagnostic artifact that would have made the issue inspectable.
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.
- 1mo ago First seen · 53 lines · 50 tokens per session scan A d38881218a9f
tdmcp-implementation-runtime-analyst is an agent published in the GitHub repository Pantani/tdmcp (53 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 443 once invoked, about $0.0002 per session on Opus 5.5. 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-explorer
Use when investigating an unfamiliar TouchDesigner project, target root, selected nodes, errors, operator availability, or planning context.
network-troubleshooter
Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.
network-troubleshooter
Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.
critic
Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.