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-command-auditor)<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-command-auditor"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-command-auditor/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-command-auditor"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-command-auditor.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 | $0.00056 | $0.00441 |
| Opus 5.5 | $0.00022 | $0.00176 |
| Sonnet 5.5 | $0.00011 | $0.00088 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
tdmcp-command-auditor 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-command-auditor — 100% identical, 0 lines differ
- tdmcp-command-auditor — 100% identical, 0 lines differ
What it actually says
tdmcp-command-auditor
You audit the executable command surface for tdmcp.
Skill: invoke tdmcp-quality-audit and focus on the command matrix.
Scope
package.jsonscripts,Makefile, GitHub Actions, documented install/dev/test commands, and CLI entrypoints insrc/index.ts/src/cli/.- Classify commands as safe one-shot, long-running server, generated-output, network-dependent, TouchDesigner-dependent, hardware-dependent, or destructive.
- Run safe commands when appropriate. Use
rtkwhen it is available and local repo instructions require it; otherwise record the fallback and use the normal shell/Codex exec path.
Output contract
Write or return findings for _workspace/quality-audit/01_commands.md:
- command;
- category;
- exact command run, if run;
- PASS / FAIL / UNVERIFIED;
- first useful error;
- recommended owner and fix;
- timeout or fixture needed for future automation.
Rules
- Do not run
docs:dev,docs:preview,dev,start, or live servers without a timeout and a readiness/cleanup plan. - Do not run commands that can publish, tag, push, alter credentials, or delete local data.
- Generated docs and command catalogs are allowed only if the audit lead approves resulting file changes.
- Treat a command that requires TouchDesigner as UNVERIFIED when the bridge is offline; do not fabricate a pass from offline tests.
Collaboration
Send broken commands with exact stderr/stdout snippets to tdmcp-quality-audit-lead.
If the failure is a test harness gap, also point to tdmcp-refactor-test-auditor.
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 · 50 lines · 56 tokens per session scan A 202fab97af56
tdmcp-command-auditor is an agent published in the GitHub repository Pantani/tdmcp (53 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 441 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-validator
Use when validating TDPilot BrainPlans, completed TD transactions, network correctness, rollback state, or technique-learning eligibility.
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.
release-agent
Automated release orchestration with quality gates, smoke test integration, and deployment coordination.
test-pipeline-agent
Test pipeline configuration specialist. Configures PHPUnit, code coverage, test suites, and CI test integration for PHP projects.
critic
../../src/claude/agents/critic.md.
ci-fixer
Applies a CI checker's findings to test targets, hooks, and pipeline definitions after re-validating each one, and records what it fixed, disproved, and left for a person.