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.
npx skills add rosasynthesiz/flstudio-mcp --skill flstudio-productiongit clone --depth 1 https://github.com/rosasynthesiz/flstudio-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/rosasynthesiz/flstudio-mcp/flstudio-production)<a href="https://agentmods.dev/skills/rosasynthesiz/flstudio-mcp/flstudio-production"><img src="https://agentmods.dev/badge/skills/rosasynthesiz/flstudio-mcp/flstudio-production/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/rosasynthesiz/flstudio-mcp/flstudio-production"><img src="https://agentmods.dev/badge/skills/rosasynthesiz/flstudio-mcp/flstudio-production.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 | $0.00113 | $0.00552 |
| Opus 5 | $0.00056 | $0.00276 |
| Sonnet 5 | $0.00023 | $0.00110 |
| Haiku 4.5 | $0.00011 | $0.00055 |
Grade A, and why
flstudio-production 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.
What it actually says
FL Studio production skill
This is the orchestration layer. Deep content lives in references/.
Before you act
- Call
fl_pingonce at the start of every session. Ifalive: false, stop and tell the user to open FL Studio and select FLStudioMCP as a controller type. Do not retry blindly. - Read
references/limits.mdso you don't promise things the FL API can't deliver (no plugin loading, no new-pattern creation, etc). - If the user is going to write Piano Roll notes, FL Studio must be the focused window. Warn them once at the start.
Tool selection
| User intent | Tools |
|---|---|
| Tempo, play, stop | fl_set_tempo, fl_play, fl_stop, fl_toggle_play |
| Where are we in the song | fl_get_song_position |
| Drum patterns | fl_channel_set_grid_bit (Phase 1) — NOT the Piano Roll |
| Mixer levels | fl_mixer_set_volume, _set_pan (Phase 2) |
| Melody in a raga | fl_preset_write_raga_melody (Phase 6) which calls Piano Roll under the hood |
| Kuthu beat | fl_preset_write_kuthu_pattern (Phase 6) |
When something fails
FLNotRunning→ bridge is healthy, FL is not. Ask user to open FL.FLTimeout→ controller is loaded but stalled. Ask user to re-select FLStudioMCP in MIDI Settings.FLCommandFailedwithcode=client→ bad input. Show the user what was wrong and ask for a correction.
References
references/limits.md— FL API constraints.references/ragas.md— How the Carnatic raga preset pack is organised.references/kuthu.md— Kuthu / gaana rhythm vocabulary.
(These references are written as Phase 6 ships.)
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 · 46 lines · 113 tokens per session scan A b0e818f88f7e
flstudio-production is a skill published in the GitHub repository rosasynthesiz/flstudio-mcp (37 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 552 once invoked, about $0.0006 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 skills, from other repositories
seedance-audio
This skill should be used when the user asks for Seedance 2.0 audio, dialogue, lip-sync, music, sound effects, ambience, beat-sync, audio-reference mapping, desync troubleshooting, or sound-driven visual timing.
listen
Nested swiss-knife reference for local audio analysis — transcribe speech with Whisper, or extract musical features (tempo, key, dynamics, spectral profile) with librosa. Both run on the user's machine with no API key. Read this when the human asks you to transcribe a voice note, extract lyrics from singing, critique…
metasounds
Create and modify MetaSound Source assets — add/connect nodes, wire pins, set input defaults, and play procedurally (MetaSoundService). Use when the user asks to create a MetaSound, build or edit a MetaSound graph, add operator/input/output nodes, or generate procedural audio.
videoagent-audio-studio
Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.
transcribe-tool
Audio transcription tool. Converts audio files to text with Whisper and optional LLM post-processing. Use when: transcribing meetings, podcasts, or extracting text from recorded audio files.