Borrowing it
Nothing to install: this file belongs to 8beeeaaat/touchdesigner-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/8beeeaaat/touchdesigner-mcp/main/.claude/skills/integration-test-guard/SKILL.mdgit clone --depth 1 https://github.com/8beeeaaat/touchdesigner-mcpWrote 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/skills/8beeeaaat/touchdesigner-mcp/integration-test-guard)<a href="https://agentmods.dev/skills/8beeeaaat/touchdesigner-mcp/integration-test-guard"><img src="https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/integration-test-guard/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/skills/8beeeaaat/touchdesigner-mcp/integration-test-guard"><img src="https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/integration-test-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 56 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 57 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 62 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00135 | $0.01095 |
| Opus 5.5 | $0.00054 | $0.00438 |
| Sonnet 5.5 | $0.00027 | $0.00219 |
| Haiku 4.5 | $0.00014 | $0.00110 |
Grade A, and why
integration-test-guard 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
1 near-identical copy found in the catalogue:
- integration-test-guard — 88% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Test Guard
When you change the MCP server / API surface, add or update a test in
tests/integration/ or tests/e2e/. The integration-test-guard hook blocks
git push when the outgoing commits touch API/MCP source without one (override
with SKIP_ITEST_GUARD=1 only when a test genuinely does not apply).
What counts as "API/MCP surface"
src/api/** (OpenAPI schema) · src/features/tools/** (tool defs + handlers) ·
src/server/** (MCP server) · src/tdClient/** (TD HTTP client) ·
src/transport/** (stdio/HTTP transport) · td/modules/mcp/** (TD-side Python API).
Step 1 — pick the right suite (by what the change affects)
| Change affects | Suite | Needs live TD (9981)? |
|---|---|---|
| MCP tool response shape / formatting, tool registration, manifest | tests/integration/mcpToolsResponse.test.ts |
No — uses server.getTool(...) with mocked client |
| Client ↔ WebServer behavior (create/update/delete/exec, TD-side Python) | tests/integration/touchDesignerClientAndWebServer.test.ts |
Yes — real TouchDesignerClient over HTTP |
HTTP transport (stateless /mcp serving, /health) |
tests/integration/httpTransport.test.ts |
No live TD, but starts the HTTP server |
Protocol-era behavior of the built CLI (2026-07-28 negotiation via server/discover, 2025-era fallback, serveStdio / createMcpHandler wiring, CLI args) |
tests/e2e/*.e2e.test.ts |
No — spawns dist/cli.js, drives it with the real MCP SDK client |
If the change spans two categories, cover each in its suite.
Step 2 — add / update the test
Follow the existing patterns in the chosen file:
- mcpToolsResponse: get the tool via
server.getTool(TOOL_NAMES.X), invoke its handler with a mocked TD client, assert the formatted response shape. - touchDesignerClientAndWebServer: use the shared
tdClientand thetest_base_compsandbox (created inbeforeAll); exercise the real call path, then reconcile against a runtime value (read it back and compare) rather than trusting the response alone. Clean up created nodes.
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 · 82 lines · 135 tokens per session scan A cc76d4587475
integration-test-guard is a skill published in the GitHub repository 8beeeaaat/touchdesigner-mcp (601 stars, last pushed 13d ago), licensed MIT. It adds 135 tokens to every session and 1,095 once invoked, about $0.0005 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 skills, from other repositories
run-tests
Run Embody's test suite and write new tests (Embody development).
testing
MUST READ before declaring any TouchDesigner build, fix or show done, and before any soak or performance test: the verification ladder (structure, errors, frame, motion, data, performance, soak, end to end), runsoaktest and the observer-effect rules that keep measuring from perturbing the show, the iterate-by-capture…
agent-tests
MUST READ before calling RunAgentTests or touching agent-tier test infrastructure -- these tests spawn real AI clients (Claude Code, Codex) and SPEND SUBSCRIPTION USAGE; never run casually. Tier model, async runner rationale, auth/isolation rules.
flutter-mcp-toolkit-control
Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
flutter-mcp-e2e-harness
Use this skill when writing or running repeatable E2E scenarios for Flutter apps as checked-in Dart with the fluttermcpharness package (packages/harness) — build/launch the app, attach to its VM service, drive widgets (snapshot/tap/enter text) and assert without MCP; also covers the repo showcase launcher (make…