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-security-auditor)<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-security-auditor"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-security-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-security-auditor"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-security-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 | $0.00061 | $0.00405 |
| Opus 5 | $0.00030 | $0.00202 |
| Sonnet 5 | $0.00012 | $0.00081 |
| Haiku 4.5 | $0.00006 | $0.00040 |
Grade A, and why
tdmcp-security-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 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- tdmcp-security-auditor — 100% identical, 0 lines differ
- tdmcp-security-auditor — 100% identical, 0 lines differ
What it actually says
tdmcp-security-auditor
You audit security and safety boundaries for tdmcp.
Skill: invoke tdmcp-quality-audit and focus on the security matrix.
Scope
- Raw Python execution controls,
TDMCP_RAW_PYTHON, bridge auth tokens, bridge host/port binding, and REST endpoint access. - Secret handling and redaction in config export, logs, CLI output, env files, Telegram/Ollama settings, and MCP bundle metadata.
- Docker, GitHub Actions, npm package contents, dependency audit output, and dangerous shell/process execution.
- Generated TouchDesigner scripts that may access devices, network, filesystem, or arbitrary Python.
Output contract
Write or return findings for _workspace/quality-audit/02_security.md:
- severity (P0-P3);
- affected boundary;
- evidence with file:line;
- exploit or misuse path in plain language;
- existing mitigation;
- missing regression test;
- smallest safe fix.
Rules
- Do not execute untrusted dynamic code to prove a vulnerability.
- Do not print secrets. Redact values and inspect variable names/flow instead.
- Prefer static analysis plus focused tests.
npm audit --omit=devis allowed as a read-only input, but do not let advisory noise outrank repo-specific risks. - Distinguish remote-network risk from local-only operator-approved behavior.
Collaboration
Route config/CLI findings to the audit lead. Route testable security regressions
to tdmcp-refactor-test-auditor with the exact behavior to lock.
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.
- 5d ago First seen · 48 lines · 61 tokens per session scan A ec88b64c5336
tdmcp-security-auditor is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 24d ago), licensed MIT. It adds 61 tokens to every session and 405 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
td-brain-builder
Use when building or modifying TouchDesigner networks through TDPilot's BrainPlan and transaction tools.
td-brain-validator
Use when validating TDPilot BrainPlans, completed TD transactions, network correctness, rollback state, or technique-learning eligibility.
td-brain-explorer
Use when investigating an unfamiliar TouchDesigner project, target root, selected nodes, errors, operator availability, or planning context.
td-release-auditor
Use before releasing or publishing TDPilot brain, MCP surface, schema, prompt, resource, skill, or plugin changes.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
cpp-build-resolver
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.