Borrowing it
Nothing to install: this file belongs to brandon-fryslie/room-eq-wizard-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/brandon-fryslie/room-eq-wizard-mcp/master/.claude/skills/tune-system/SKILL.mdgit clone --depth 1 https://github.com/brandon-fryslie/room-eq-wizard-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/skills/brandon-fryslie/room-eq-wizard-mcp/tune-system)<a href="https://agentmods.dev/skills/brandon-fryslie/room-eq-wizard-mcp/tune-system"><img src="https://agentmods.dev/badge/skills/brandon-fryslie/room-eq-wizard-mcp/tune-system/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/skills/brandon-fryslie/room-eq-wizard-mcp/tune-system"><img src="https://agentmods.dev/badge/skills/brandon-fryslie/room-eq-wizard-mcp/tune-system.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 | $0.00084 | $0.02378 |
| Opus 5.5 | $0.00034 | $0.00951 |
| Sonnet 5.5 | $0.00017 | $0.00476 |
| Haiku 4.5 | $0.00008 | $0.00238 |
Grade A, and why
tune-system 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tuning Brandon's system
You are resuming an ongoing calibration of a real, working hi-fi. Everything here was verified live on 2026-09-09. Read values back after every write; twice in that session a remembered interface turned out wrong and the repo rule — never script against an interface you haven't run — earned its keep.
The rig
- REW 5.40 Beta 132 (API 0.9.6, Pro licensed) runs on studious.local (Mac
Studio), at
/Applications/REW-540-api/REW.app. Do NOT touch the user's 5.31 install at/Applications/REW. Relaunch:ssh studious.local open -a /Applications/REW-540-api/REW.app --args -api - This laptop reaches the API through an SSH tunnel; the MCP server needs no config:
ssh -f -N -o ExitOnForwardFailure=yes -o ServerAliveInterval=30 -L 127.0.0.1:4735:127.0.0.1:4735 studious.localIf tools report REW unreachable, the tunnel died — re-run that command. Never set REW_API_URL to the LAN address: the REW API has zero auth and exposes filesystem paths. Tunnel or nothing. - Signal chain (playback = measurement): REW → BlackHole 2ch → HQPlayer 5
Desktop (input: BlackHole via coreaudio; upsamples to DSD256; EQ goes in its
convolution engine) → xCORE USB Audio 2.0 Output → Evolution Acoustics MM2
(full-range). HQPlayer config:
~/.hqplayer/settings.xmlon studious. - Mic: UMIK-1 serial 7135194, 90° cal file
/Users/bmf/Documents/REW/cal/7135194_90deg.txt, input channel 2, mic at LP pointed at ceiling. There are two UMIK-1s and USB serials read identically — the other (7109804) belongs to the SHD; software cannot tell them apart. - REW enumerates audio devices at startup. A device powered on after launch is invisible until REW restarts.
- Reference level: 81.8 dBA at LP is the user's stated maximum. Room noise floor 43.0 dBA. Generator level −12 dBFS.
Standing rules (the user's, not defaults)
- ALWAYS sweep L and R separately. Select the channel, read it back, sweep,
then switch and repeat:
POST /audio/java/output-channel {"channel":"L"|"R"}— verify with GET before each sweep. Never sweep both channels together; per-channel asymmetry is the entire point of this work, and a combined sweep hides it silently. - Save after every session:
save_all_measurementsto/Users/bmf/Documents/REW/measurements/<date>_LP_L-R*.mdat(paths are on studious). Quitting REW discards unsaved measurements — one was lost that way. Save before you report a session done, not after. - The couch in front of the right speaker cannot move. It absorbs right-channel HF (sharp onset ~3 kHz); the fix is EQ, and the user was blunt — do not suggest moving it again.
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 Changed · +22 lines 5974387e7db4
- 1mo ago First seen · 126 lines · 84 tokens per session scan A 0924baf601c5
tune-system is a skill published in the GitHub repository brandon-fryslie/room-eq-wizard-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 2,378 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 2026-09-18.
Other skills, from other repositories
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
ruview-applications
Run RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-keypoint pose estimation (WiFlow), sleep monitoring & apnea screening, environment mapping, Mass Casualty Assessment (MAT), and the 3D point-cloud fusion demo. Use when someone wants to actually do something…
lab-hardware-cad
Designs custom laboratory hardware as parametric build123d models and exports fabrication artifacts as STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a…
pylabrobot
Develops and reviews PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Supports PyLabRobot protocols and API questions; keep physical execution behind an explicit operator safety gate.
pybamm
Simulates lithium-ion battery charge, discharge and rest experiments with PyBaMM, records parameter-set provenance, checks mesh and solver sensitivity, and compares predicted voltage curves with measured cycling data. Use for SPM or DFN electrochemical battery modeling, C-rate protocols, voltage cutoffs, parameter…
calibrate-room
Run the ADR-151 per-room calibration pipeline — baseline → enroll → extract → train → a bank of small specialists (presence/posture/breathing/heartbeat/restlessness/anomaly).