FishMCP: Instructions file for Claude Code

CLAUDE.md

FishMCP CLAUDE.md is an instructions file for Claude Code from AceDataCloud/FishMCP. It costs 540 tokens per session, scanned A, original, MIT.

Project instructions for FishMCP, an MCP server that turns text into speech through the Fish Audio service. Text-to-speech means creating spoken audio from written text.

In plain words
What is it for?
Use them when developing, testing, or operating FishMCP, including selecting models, generating audio, checking task status, and reading usage guidance.
Why use it?
They document the project structure and the sequence for choosing a voice, submitting text, waiting for processing, and retrieving the audio.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is AceDataCloud/FishMCP's own configuration. It tells Claude Code how to work on FishMCP 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 FishMCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AceDataCloud/FishMCP. 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/AceDataCloud/FishMCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AceDataCloud/FishMCP

Made for: Claude Code.

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 FishMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/acedatacloud/fishmcp/claude-md.svg)](https://agentmods.dev/instructions/acedatacloud/fishmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/acedatacloud/fishmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/acedatacloud/fishmcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 540 This file is loaded in full into every session.
When invoked 540 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 $0.00540 $0.00540
Opus 5 $0.00270 $0.00270
Sonnet 5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 6d ago against content hash 3abc91854e4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

FishMCP CLAUDE.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 6d 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.

CLAUDE.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FishMCP

MCP (Model Context Protocol) server for the AceDataCloud Fish Audio API — text-to-speech with voice conditioning powered by Fish Audio models.

Project Structure

core/
  config.py     — Settings dataclass (API token, base URL, timeouts)
  server.py     — FastMCP server singleton + optional OAuth provider
  client.py     — FishClient: async httpx wrapper for /fish/* endpoints
  types.py      — Literal types (FishModel, etc.)
  exceptions.py — Error classes (FishAuthError, FishAPIError, FishTimeoutError)
  oauth.py      — Generic AceDataCloud OAuth 2.1 provider (PKCE)
tools/
  audio_tools.py — fish_generate_audio (submit a TTS task)
  task_tools.py  — fish_get_task, fish_get_tasks_batch
  info_tools.py  — fish_list_models, fish_get_model, fish_get_usage_guide
prompts/
  __init__.py    — fish_guide, fish_workflow_examples
tests/
  test_smoke.py  — Smoke tests (settings, server import, tool registration)

TTS workflow

  1. Pick a voice model (fish_list_modelsfish_get_model).
  2. Submit text (fish_generate_audio(text=..., model="s2-pro", reference_id=...)).
  3. Poll status until terminal (fish_get_task(task_id=...)).
  4. Read the final audio_url from the task payload and play / download it.

Sync from Docs

When invoked by the sync workflow, the Docs repo is checked out at _docs/. Your job:

  1. Source of truth_docs/openapi/fish.json is the OpenAPI spec for the Fish Audio API.
  2. Compare models — The Literal types in core/types.py must match the spec's voice model enum. Add/remove as needed.
  3. Compare parameters — Each @mcp.tool() function's parameters should match the corresponding OpenAPI endpoint.
  4. Update defaults — If a new model becomes the recommended default, update the default in core/types.py.
  5. Update README — Keep the model table and feature list current.
  6. Add tests — For new tools or parameters, add test cases in tests/.
  7. PR title — Use format: sync: <description> [auto-sync]

Read the full file on GitHub · 52 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. 6d ago First seen · 52 lines · 540 tokens per session scan A 3abc91854e4c

Subscribe to this mod's changes

FishMCP CLAUDE.md is an instructions file published in the GitHub repository AceDataCloud/FishMCP (1 stars, last pushed today), licensed MIT. It adds 540 tokens to every session, about $0.0027 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.

Related

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.

openai/codex · 5,182 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 7,296 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 · 4,469 tokens

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.

github/spec-kit · 7,104 tokens