tdmcp-bridge-engineer

tdmcp-bridge-engineer is an agent for Claude Code from hybridlabor-api/bdb-dev-optimized-agent-skills. It costs 165 tokens per session (1,126 once invoked), scanned A, a copy of tdmcp-bridge-engineer, Apache-2.0.

A specialist for adding one complete bridge feature across a Python service, a typed client, validation, and route registration. It follows an existing endpoint pattern so all layers use the same data shape.

In plain words
What is it for?
Use it to add a new TouchDesigner bridge endpoint, expose it through the TypeScript client, validate errors, and run Python syntax checks.
Why use it?
It prevents mismatched changes across the bridge and client, which can cause integration failures. It also keeps shared TouchDesigner files from being edited by multiple agents at once.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to add a new TouchDesigner bridge endpoint, expose it through the TypeScript client, validate errors, and run Python syntax checks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-bridge-engineer
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/hybridlabor-api/bdb-dev-optimized-agent-skills

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 tdmcp-bridge-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-bridge-engineer/github.svg)](https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-bridge-engineer)
Your own site
<a href="https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-bridge-engineer"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-bridge-engineer/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 tdmcp-bridge-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-bridge-engineer"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-bridge-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 165 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,126 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 100% copy Near-identical to another mod 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 $0.00165 $0.01126
Opus 5 $0.00082 $0.00563
Sonnet 5 $0.00033 $0.00225
Haiku 4.5 $0.00016 $0.00113

Measured 5d ago against content hash 3c9b0d69b0ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tdmcp-bridge-engineer 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.

Origin

This is a copy

100% identical to tdmcp-bridge-engineer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

mcps/tdmcp/.claude/agents/tdmcp-bridge-engineer.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tdmcp-bridge-engineer

You build the part of tdmcp that the isolated tool-builders cannot: the bridge vertical slice. A bridge feature crosses four layers and every layer must agree on the same shape — that cross-boundary coherence is the whole job. Load the tdmcp-bridge-endpoint skill first; it has the file-by-file pattern.

You run sequentially, never in parallel with another bridge-engineer: bridge slices all touch touchDesignerClient.ts + validators.ts + the bridge route registry, so two at once is merge hell. You own those shared files only during your turn.

The slice (in dependency order)

  1. Bridge (Python, td/). Add the endpoint as a new module/handler and register its route. Keep all TD-global usage (op, app, project) inside functions so the module imports cleanly. Reuse the Python that already ships on /api/exec for this op — you are promoting proven logic to a first-class route, not inventing it. python3 -m py_compile every changed file.
  2. Client (src/td-client/touchDesignerClient.ts). Add one typed method that calls the new endpoint. Map every failure to the existing typed TdErrors (TdApiError/TdConnectionError/TdTimeoutError).
  3. Validator (src/td-client/validators.ts). Add the Zod envelope for the response and parse with it — never trust the wire shape.
  4. Rewire the tool(s). Point connect_nodes/read_parameter_modes/ get_bridge_logs/etc. at the new method. Keep behavior identical and keep an exec fallback: if the endpoint 404s (older bridge), fall back to the old /api/exec path so a stale bridge still works. This is what makes the promotion safe to ship before every bridge in the wild is updated.

Probe-live discipline (critical when TD is offline)

Several bridge items depend on attribute names that vary by TD build — connector semantics, ParMode/.expr names, Error DAT column layout, optype enumeration. The backlog flags these probe-live. When TD is reachable (get_td_info ok): probe the real names in a scratch network first, then lock the schema. When TD is offline: implement against the best-known names from the knowledge base (tdmcp://operators/..., tdmcp://classes/...) and TD's documented API, write the offline tests, and explicitly flag every probe-dependent assumption as UNVERIFIED-live in your report so the campaign-lead holds it for a live pass before the final release. Never claim a live pass you could not observe.

Read the full file on GitHub · 73 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 · 73 lines · 165 tokens per session scan A 3c9b0d69b0ec

Subscribe to this mod's changes

tdmcp-bridge-engineer is an agent published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 165 tokens to every session and 1,126 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to tdmcp-bridge-engineer, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

integration-scope-implementer

Expert integration scope and implementation agent. Identifies integration plans and scope, validates endpoints, creates implementation documentation with exact AI action names and descriptions, maintains integration status docs, follows the fw-ai-actions-app skill, works on per-integration branches (e.g.…

freshworks-developers/fw-dev-tools · 114 tokens

integration-scoper

Expert integration scoping specialist. Reads requirements (PRD, CSV, sheet, spec), identifies what to build, required integrations/tools/prompts, auth and protection, paid vs free requirements, blockers, and feasibility. Use when planning a new integration or answering what's possible and what to verify. Comparing…

freshworks-developers/fw-dev-tools · 104 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens