Borrowing it
Nothing to install: this file belongs to fomoPhil/uad-console-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/fomoPhil/uad-console-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/fomoPhil/uad-console-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/instructions/fomophil/uad-console-mcp/agents-md)<a href="https://agentmods.dev/instructions/fomophil/uad-console-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/fomophil/uad-console-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.04641 | $0.04641 |
| Opus 5 | $0.02320 | $0.02320 |
| Sonnet 5 | $0.00928 | $0.00928 |
| Haiku 4.5 | $0.00464 | $0.00464 |
Grade A, and why
uad-console-mcp AGENTS.md 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 7d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for an LLM driving uad-console-mcp. Human-facing docs: README.md,
docs/RECIPES.md, docs/PROTOCOL.md.
Orientation
- This server controls Universal Audio Apollo interfaces through the local UA Mixer Engine on
127.0.0.1:4710: channels, preamps, sends, monitor, talkback, clock, plugins, meters, snapshots. - Discovery first. Channel counts, indices, monitor output, send IDs and slot counts differ per model and are read from the engine, never assumed.
- Every write is read back. A write result is
{verified, before, after, warnings}plus the resolved{device, index, name}. - Refusals are information, not obstacles. Each one names the env var or confirm flag that would unblock it. Relay it; do not route around it.
- This is live audio hardware next to human ears. Loud is irreversible.
HARD RULES
- Never hardcode a channel index, monitor index or slot number. Call
uad_list_channelsfirst and use what it returns.ANALOG 1is input 0 on one model and absent on another. - Never raise monitor level without an explicit dB figure from the user. No "a bit louder",
no probing to check a fix.
uad_set_monitor(level_db=...)only with a number they said. - Never enable 48V without asking what microphone is connected. Ask, get an answer, then pass
confirm_condenser_mic=true. Never on a ribbon mic: phantom power destroys them permanently. If the answer is unknown or vague, leave 48V alone and say why. - Never change clock source or sample rate while meters show signal. Check
uad_peek_metersfirst, warn the user the chain will re-lock, then passconfirm=true. Both refuse above -60 dB. - Writes are verified. Treat
verified: falseas a failure, not as a retry cue. Read the property withuad_raw_get, report what the engine actually holds, and stop. Never loop. - Never probe by writing. The engine accepts writes to properties it marks read-only, so a test
write is a real change. Learn a property's type, range or enum with
uad_raw_get(path=...). - On
SafetyRefusal, relay the remedy to the user. Do not raise the ceiling, do not switch mode, do not retry with a different tool that reaches the same property. The rail is the point. - Call
uad_safe_statefirst when anything is unexpectedly loud. Diagnose afterwards. It needs no arguments and no confirmation. - Meter targets are names, and
targetsis optional.uad_peek_metersanduad_watch_metersboth taketargets,kind,device(watch alsoduration_s,threshold_db,interval_s). Omittargetsand they sweep every channel ofkind(default"input"). A numeric string is matched as a name first:"8"matchesANALOG 8,UG 8,VIRTUAL 8and errors as ambiguous. - A verified rename is usable immediately (the cached topology is updated in place), but if a
rename comes back
verified: falsethe old name is still the truth. Use the index until a freshuad_list_channelsproves otherwise. - With more than one device, always pass
device. An index that exists on several Apollos is ambiguous, by design. - Snapshot before experimenting, and show a
dry_run=truerestore before running it for real.
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.
- 7d ago First seen · 201 lines · 4,641 tokens per session scan A 7ae1e2be2e6f
uad-console-mcp AGENTS.md is an instructions file published in the GitHub repository fomoPhil/uad-console-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 4,641 tokens to every session, about $0.0232 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.