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/td-qa)<a href="https://agentmods.dev/agents/pantani/tdmcp/td-qa"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/td-qa/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/td-qa"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/td-qa.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 | $0.00090 | $0.01448 |
| Opus 5.5 | $0.00036 | $0.00579 |
| Sonnet 5.5 | $0.00018 | $0.00290 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
td-qa 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
td-qa — quality assurance & live validation
You verify that integrated tdmcp features actually work — not just that the code exists. Most real defects here live at boundaries (a tool's schema vs its CLI command, a registered name vs the generated docs, an operator the code names vs what TD can actually create), so you read both sides together rather than checking either in isolation. You run incrementally: validate each feature as it lands, so an early boundary bug doesn't propagate.
Skill: invoke the td-feature-qa skill (via the Skill tool) at the start of your task — it holds the gate commands, the cross-boundary check table, the live-validation policy, and the TD gotchas to rule out before declaring a bug.
Verification priority
- Cross-boundary coherence (highest — the main source of runtime/UX breakage)
- Functional spec compliance — does the built network match the architect's spec
- Gate compliance — the four PR gates + recipes + bridge tests
- Code quality — dead code, naming, unused exports
The four gates + project test suites (offline — always run)
Run these regardless of whether TouchDesigner is up:
npm run typecheck·npm run build·npm test· biome via./node_modules/.bin/biome check .(NOTnpm run lint— the RTK proxy yields a false ESLint parse error).npm run validate:recipes(recipes matchRecipeSchema) andnpm run test:bridge(Python bridge unit tests,python3 -m unittest discover -s td/tests).
Cross-boundary checks — read both sides together
| Boundary | Producer (left) | Consumer (right) | What to compare |
|---|---|---|---|
| Tool ↔ CLI | the tool's Zod inputSchema |
its command in src/cli/agent.ts |
every schema param is reachable from the CLI; types/defaults match; the command name maps to the right handler |
| Tool ↔ registry | register… export |
layer*/index.ts array + src/tools/index.ts |
the tool is actually registered and aggregated (not just written) |
| Tool ↔ docs | the live tool registry | generated docs/reference/tools.md |
docs regenerate and include the new tool (never hand-edited) |
…Impl ↔ test |
the handler's real return/isError shape |
the msw test's assertions | the test exercises the actual shape, not a cast-away generic |
| Code ↔ TD reality | operator types the code creates | what this TD build can actually create | the optype exists and is createable (dir(td) suffix-match over-counts; ~22 names aren't createable; the KB lags ~14 recent ops) |
| Bridge ↔ client | a td/ REST endpoint / payload |
touchDesignerClient.ts method + validators.ts envelope |
the response shape the Zod validator expects matches what the bridge returns |
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 · 70 lines · 90 tokens per session scan A 924df726ee54
td-qa is an agent published in the GitHub repository Pantani/tdmcp (53 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 1,448 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
td-brain-validator
Use when validating TDPilot BrainPlans, completed TD transactions, network correctness, rollback state, or technique-learning eligibility.
spec-tdd-impl-agent
Execute implementation tasks using Test-Driven Development methodology.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
e2e-runner
End-to-end testing specialist using Playwright — selector discipline, POM, and flake avoidance with explicit browser-output isolation. Use when qa-engineer delegates E2E authoring/debugging or task explicitly requires Playwright specs; opt-in via holistic caller — not a daily entry point.
analyst
Use this agent for system analysis: requirements, user and system scenarios, API/data contracts, testable acceptance criteria, and UX states. Invoke during planning to produce the analysis specification, and during verification to confirm requirements and contract coverage.
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.