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/release-test-audit/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/release-test-audit)<a href="https://agentmods.dev/skills/8beeeaaat/touchdesigner-mcp/release-test-audit"><img src="https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/release-test-audit.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00133 | $0.01209 |
| Opus 5 | $0.00067 | $0.00605 |
| Sonnet 5 | $0.00027 | $0.00242 |
| Haiku 4.5 | $0.00013 | $0.00121 |
Grade A, and why
release-test-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release test audit
Answer one question for a release: is every API/MCP surface change in the
unreleased range covered by an integration test? This is a release-wide
completeness check — broader than the per-push integration-test-guard hook,
which only sees one push at a time and can be legitimately skipped commit by
commit. Across a full release those individual skips can add up to a real gap;
this audit catches that.
Scope boundary: this skill finds gaps. It does not teach how to write a
test — for suite choice, patterns, and run commands, hand off to the
integration-test-guard skill.
Step 1 — enumerate the release's surface changes
LAST_TAG=$(git describe --tags --abbrev=0)
git diff "$LAST_TAG"..HEAD --name-only
Keep only files under the API/MCP surface (same paths the guard watches):
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
Files outside this set (docs, deps, .claude/**, build config, pure types) need
no integration test — list them as N/A so the audit is explicit about what it
skipped.
Step 2 — map each change to the suite that must cover it
| A surface change in… | Expected suite | Live TD (9981)? |
|---|---|---|
tool response shape / formatting, registration, manifest (src/features/tools/**, src/server/**) |
tests/integration/mcpToolsResponse.test.ts |
No (mocked client) |
client ↔ WebServer behavior — create/update/delete/exec, TD-side Python (src/tdClient/**, td/modules/mcp/**, contract in src/api/**) |
tests/integration/touchDesignerClientAndWebServer.test.ts |
Yes |
HTTP transport — sessions, /mcp, /health (src/transport/**) |
tests/integration/httpTransport.test.ts |
No (starts HTTP server) |
A change spanning two rows needs coverage in each row's suite.
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.
- 8d ago First seen · 108 lines · 133 tokens per session scan A aec58baad8aa
release-test-audit is a skill published in the GitHub repository 8beeeaaat/touchdesigner-mcp (519 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 1,209 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
ship-workflow
Automated release pipeline: merges main, runs tests, pre-landing review, version bump, changelog, bisectable commits, and PR creation. Triggers on: "ship it", "release this", "prepare for release", "open a PR", "push and PR", "land this", "/ship-workflow".
polish-docs-meta
Finalize documentation and project metadata for a ship-ready release. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.
mathodology-dev-test-release
Use when checking skill metadata, references or repository boundaries, or preparing an explicitly requested skills release.
repo-harness-check
Verification entrypoint for repo-harness workflow readiness. Runs workflow gates, task sync, contract checks, inspector, and migration dry-run before merge or release.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.