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 agentmods add instructions/remsky/kokoro-fastapi/agents-mdgit clone --depth 1 https://github.com/remsky/Kokoro-FastAPIWrote 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/remsky/kokoro-fastapi/agents-md)<a href="https://agentmods.dev/instructions/remsky/kokoro-fastapi/agents-md"><img src="https://agentmods.dev/badge/instructions/remsky/kokoro-fastapi/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 | $0.00822 | $0.00822 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
Kokoro-FastAPI 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 4d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working on Kokoro-FastAPI. Agent-assisted contributions are welcome, with caveats: - All judgement and accountability falls to the named human contributor as the reviewer. - If the user doesn't demonstrate understanding a change, it's not ready to merge. - Code style here must still match house style. - To the above, explicitly: - wanton em-dash usage is not permitted. - expositionary and excessive commenting is not permitted. - when in doubt, do less. Comments are reserved for decision points, or unexpected gotchas, etc.
The general instructions must also still be followed, same as any contributor, and live in CONTRIBUTING.md.
Layout
api/src/routers/- HTTP endpoints.openai_compatible.pyis the main API surface.api/src/services/- TTS orchestration (tts_service.py), audio encoding and streaming (audio.py,streaming_audio_writer.py),text_processing/(normalization, phonemization).api/src/inference/- model backends (kokoro_v1.py), model and voice managers.api/src/core/-config.py(env-driven settings),paths.py,openai_mappings.json(OpenAI model/voice name mapping).web/- vanilla JS web player, served by the API. No framework, no build step.docker/{cpu,gpu,rocm}/- per-accelerator images and compose files.docker-bake.hcldefines the CI build targets.examples/- standalone samples with their own uv venv. Runuv runfrom insideexamples/, not the root env.
Commands
- Python tests:
uv run pytest(runsapi/tests/; integration tests are excluded by default, opt in with-m integration). - Format and lint:
ruff format .thenruff check . --fix. - Web unit tests:
npm run test:web. E2e:npm run test:e2e. New unit test files must be imported fromweb/tests/unit/index.test.mjs; it is a manual registry. - Container smoke test:
npm run cpu:up(orgpu:up,rocm:up).
Conventions
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.
- 4d ago First seen · 48 lines · 822 tokens per session scan A 1aa63ebd5910
Kokoro-FastAPI AGENTS.md is an instructions file published in the GitHub repository remsky/Kokoro-FastAPI (5,402 stars, last pushed today), licensed Apache-2.0. It adds 822 tokens to every session, about $0.0041 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 instructions, from other repositories
kokoro-tts-mcp CLAUDE.md
Instructions for scottschram/kokoro-tts-mcp, covering kokoro-tts-mcp, architecture, key constraints, design decisions and memory budget.
transformers copilot-instructions.md
Instructions for huggingface/transformers, covering copilot-instructions.md guide for hugging face transformers, core project structure, coding conventions for hugging face transformers, copying and inheritance and testing.
geolens CLAUDE.md
Claude Code instructions for geolens-io/geolens: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
diffusers AGENTS.md
AGENTS.md instructions for huggingface/diffusers, a project described as: 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
deckforge CLAUDE.md
Instructions for Whatsonyourmind/deckforge, covering deckforge, tech stack, project structure, key commands and local development.