sonilo-mcp: Instructions file for Codex

AGENTS.md

sonilo-mcp AGENTS.md is an instructions file for Codex, OpenCode from sonilo-ai/sonilo-mcp. It costs 1,695 tokens per session, scanned A, original, MIT.

Repository instructions for working on sonilo-mcp, a local server that connects coding agents to Sonilo's public services for music, sound effects, video analysis, audio processing, dubbing, and proofreading. They describe the project layout, credentials, tests, commands, and release files.

In plain words
What is it for?
Use them when developing, testing, or releasing the sonilo-mcp Python package and its connection to the MCP Registry.
Why use it?
They give an agent the project facts and boundaries needed to change the repository without confusing the local server with Sonilo's separate hosted service. They also identify how tests avoid using the real network.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is sonilo-ai/sonilo-mcp's own configuration. It tells Codex and OpenCode how to work on sonilo-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sonilo-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sonilo-ai/sonilo-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.

Copy the file
curl -O https://raw.githubusercontent.com/sonilo-ai/sonilo-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/sonilo-ai/sonilo-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for sonilo-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sonilo-ai/sonilo-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/sonilo-ai/sonilo-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sonilo-ai/sonilo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sonilo-ai/sonilo-mcp/agents-md/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.

agentmods 80×15 button for sonilo-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sonilo-ai/sonilo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sonilo-ai/sonilo-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,695 This file is loaded in full into every session.
When invoked 1,695 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01695 $0.01695
Opus 5.5 $0.00678 $0.00678
Sonnet 5.5 $0.00339 $0.00339
Haiku 4.5 $0.00169 $0.00169

Measured 5d ago against content hash 68a2866bf1ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sonilo-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 5d 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.

AGENTS.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Notes for coding agents working on sonilo-mcp, and for agents connecting to it.

What this repo is

A local stdio MCP server (Python, FastMCP) that wraps Sonilo's public API: music, sound effects, combined music + SFX, video analysis, audio ducking, dubbing and proofreading. It uploads local files, waits on async tasks and saves results to disk. Published to PyPI as sonilo-mcp and to the MCP Registry as io.github.sonilo-ai/sonilo-mcp.

There is also a hosted, OAuth-authenticated server at https://api.sonilo.com/mcp. It is not built from this repo.

Layout

src/sonilo_mcp/api.py          every tool, HTTP calls, polling, downloads, path confinement; entry point `main`
src/sonilo_mcp/credentials.py  reads the `sonilo login` credential file
tests/test_api.py              tool tests (respx mocks the API; no network)
tests/test_credentials.py
tests/conftest.py              clears SONILO_* env vars and points HOME at a tmp dir
pyproject.toml                 package metadata and the real version
server.json                    MCP Registry manifest; release CI rewrites its version
uv.lock                        pins mcp to 1.x (2.x removed mcp.server.fastmcp)

setup.py is legacy and its version is not used. pyproject.toml is the source of truth.

Commands

uv sync --extra dev --frozen   # install, honouring uv.lock
uv run pytest -v               # what CI runs
uv run sonilo-mcp              # start the server on stdio

Use uv sync --frozen, not a plain pip install: an unpinned resolve can pull mcp 2.x and every import fails. There is no PR CI in this repo; tests run in .github/workflows/release.yml before publishing, so run them locally.

Releasing

  1. Bump version in pyproject.toml; put the version in the commit title, e.g. proofread: ... (0.26.0).
  2. Push a vX.Y.Z tag that matches it. The release workflow tests, publishes to PyPI (trusted publishing), waits until PyPI serves the version, then syncs server.json and publishes to the MCP Registry.

Read the full file on GitHub · 124 lines

Changes

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.

  1. 5d ago First seen · 124 lines · 1,695 tokens per session scan A 68a2866bf1ba

Subscribe to this mod's changes

sonilo-mcp AGENTS.md is an instructions file published in the GitHub repository sonilo-ai/sonilo-mcp (53 stars, last pushed 6d ago), licensed MIT. It adds 1,695 tokens to every session, about $0.0068 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 2026-10-14.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,649 tokens

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.

vercel/next.js · 7,257 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,159 tokens