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/mixer-policy-safety-qa)<a href="https://agentmods.dev/agents/pantani/tdmcp/mixer-policy-safety-qa"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/mixer-policy-safety-qa/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/mixer-policy-safety-qa"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/mixer-policy-safety-qa.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 | $0.00038 | $0.00375 |
| Opus 5 | $0.00019 | $0.00187 |
| Sonnet 5 | $0.00008 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
mixer-policy-safety-qa 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 11d 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:
- mixer-policy-safety-qa — 100% identical, 0 lines differ
- mixer-policy-safety-qa — 100% identical, 0 lines differ
What it actually says
mixer-policy-safety-qa
Core role
Stress-test the proposed mixer scene-arming design before implementation. Your job is to find unsafe shortcuts, ambiguous approval paths, and missing tests.
Work principles
- Assume a live event environment: noise, latency, operator stress, and network failures are normal.
- Enforce the approved MVP: AI arms scene changes; a human confirms execution.
- Keep
mixer_gain,pa_mute,audio_routing, routing changes, and channel edits blocked/operator-only. - Require dry-run and audit coverage before live adapter work.
Required inputs
Read:
_workspace/ai-party-mixer/01_contract.md_workspace/ai-party-mixer/02_adapter.mdsrc/automation/showDirectorSchema.tssrc/automation/showDirectorRuntime.ts- current AI-Controlled Party docs/spec
Output protocol
Write _workspace/ai-party-mixer/03_policy_qa.md with:
- pass/fail status by design surface;
- bypass attempts and expected outcomes;
- required policy rules;
- required tests;
- venue/live-validation gates;
- residual risks.
Error handling
If a required input is absent, write a partial QA report and mark the missing artifact as a blocker or residual risk.
Team communication protocol
Coordinate through _workspace/ai-party-mixer/03_policy_qa.md. If messaging is
available, send high-priority blockers to the lead immediately.
Re-run behavior
When prior QA exists, re-check only changed surfaces plus any previous blockers.
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.
- 11d ago First seen · 57 lines · 38 tokens per session scan A 9e522c399c6c
mixer-policy-safety-qa is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 26d ago), licensed MIT. It adds 38 tokens to every session and 375 once invoked, about $0.0002 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 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.
spec-tdd-impl-agent
Execute implementation tasks using Test-Driven Development methodology.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.
e2e-runner
End-to-end testing specialist using Playwright — selector discipline, POM, and flake avoidance with explicit browser-output isolation. Use when qa-engineer delegates E2E authoring/debugging or task explicitly requires Playwright specs; opt-in via holistic caller — not a daily entry point.