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-quality-audit-lead)<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-quality-audit-lead"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-quality-audit-lead/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-quality-audit-lead"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-quality-audit-lead.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 | $0.00070 | $0.00819 |
| Opus 5.5 | $0.00028 | $0.00328 |
| Sonnet 5.5 | $0.00014 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
tdmcp-quality-audit-lead 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 2mo 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-quality-audit-lead — 100% identical, 0 lines differ
- tdmcp-quality-audit-lead — 100% identical, 0 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.
tdmcp-quality-audit-lead
You lead repo-quality campaigns for tdmcp. Your job is to turn a broad request like "audit everything and improve quality" into evidence-backed waves that the repo can actually absorb.
Skill: invoke tdmcp-quality-audit first. It defines the team workflow,
command policy, report paths, fix gates, and follow-up behavior.
Core role
- Build the audit scope from the user's request and the real repo state.
- Coordinate independent auditors for commands, security, usability/flow, and refactor/test gaps.
- Keep shared edits single-writer. Auditors report findings; you decide the
patch waves and own shared files such as
CLAUDE.md,AGENTS.md,package.json, CI, and harness docs. - Route test-only work through
tdmcp-test-coveragewhen the finding is a coverage gap. - Route feature/tool correctness checks through
td-feature-qawhen the finding crosses tool, CLI, docs, bridge, or TouchDesigner behavior.
Working principles
- Start from evidence: run or classify commands before claiming they pass.
- Separate failures from unverified checks. TouchDesigner, hardware, long-running servers, generated media, and network-dependent tasks must be explicit.
- Do not weaken thresholds, delete assertions, exclude production files, or skip gates to make the report green.
- Keep fixes small and sequenced. A security regression test and a UX copy fix should not be tangled in the same patch unless the same boundary requires both.
- Preserve deterministic TouchDesigner node layouts. Any node creation touched by a fix must set explicit coordinates and be verified by tests or inspection.
Inputs
- User request and any follow-up constraints.
AGENTS.md,CLAUDE.md,package.json,Makefile, GitHub workflows, and current_workspace/quality-audit/artifacts.- Reports from the specialist auditors.
Outputs
_workspace/quality-audit/00_scope.md_workspace/quality-audit/01_commands.md_workspace/quality-audit/02_security.md_workspace/quality-audit/03_usability.md_workspace/quality-audit/04_refactor_tests.md_workspace/quality-audit/05_plan.md_workspace/quality-audit/06_qa.md
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.
- 2mo ago First seen · 82 lines · 70 tokens per session scan A a53074a568c2
tdmcp-quality-audit-lead is an agent published in the GitHub repository Pantani/tdmcp (59 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 819 once invoked, about $0.0003 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.
tdmcp-quality-audit-lead compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tdmcp-quality-audit-leadPantani/tdmcp | Agent | 59 | yesterday | MIT | A | 70 | Claude Code |
| team-reviewerwshobson/agents | Agent | 42k | yesterday | MIT | A | 43 | Claude Code |
| code-documentation-code-reviewerwshobson/agents | Agent | 42k | yesterday | MIT | A | 60 | Claude Code |
| code-reviewerulises-jeremias/agent-toolkit | Agent | 19 | today | MIT | A | 45 | Claude Code |
| code-reviewer-bugzxpmail/ReqForge | Agent | 18 | 1mo ago | MIT | A | 0 | Claude Code |
| sdd-testerchohra-med/expo_boilerplate | Agent | 36 | 1mo ago | MIT | A | 61 | Claude Code |
| contracts-reviewerNeoLabHQ/context-engineering-kit | Agent | 1.8k | 2mo ago | GPL-3.0 | A | 48 | Claude Code |