What is Patter AGENTS.md?

Instructions for agents contributing to Patter, open-source telephony infrastructure that connects AI agents to phone calls. The project provides matching Python and TypeScript software libraries and requires specific practices for features, compatibility, and release notes.

Use it when adding features, fixing bugs, changing APIs, updating both SDKs, writing changelog entries, or preparing a pull request for Patter.

It prevents one language library from gaining behavior that the other lacks. It also helps keep new settings compatible with existing users and records user-visible changes.

How PatterAI/Patter configures Codex and OpenCode

About the project

Patter is an open-source SDK that lets developers build voice AI agents connected to telephone networks, handling the agent loop, language model, speech recognition, speech synthesis, real-time voice, audio processing, and carrier connection. Developers use it from Python or TypeScript and can choose providers for each part of the call. The catalogue instruction relates to operating and building with Patter.

PatterAI/Patter · 1,083 stars · on GitHub · getpatter.com

Reuse

Borrowing it

Nothing to install: this file belongs to PatterAI/Patter. 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/PatterAI/Patter/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/PatterAI/Patter

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/patterai/patter/agents-md/github.svg)](https://agentmods.dev/instructions/patterai/patter/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/patterai/patter/agents-md"><img src="https://agentmods.dev/badge/instructions/patterai/patter/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/patterai/patter/agents-md"><img src="https://agentmods.dev/badge/instructions/patterai/patter/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 855 This file is loaded in full into every session.

When invoked 855 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.

Model	Per session	Once invoked
Fable 5.1	$0.00855	$0.00855
Opus 5.5	$0.00342	$0.00342
Sonnet 5.5	$0.00171	$0.00171
Haiku 4.5	$0.00085	$0.00085

Measured 2mo ago against content hash eda2ef9a8c85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Patter 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 2mo 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Claude Code, Cursor, Codex, OpenClaw, …) working in this repository. Humans: see CONTRIBUTING.md — this file is the same contract in agent-readable form. Read this before opening a PR.

Patter is open-source telephony infrastructure that connects AI agents to phone calls. It ships two SDKs with full parity: Python (pip install getpatter, libraries/python/) and TypeScript (npm install getpatter, libraries/typescript/).

Non-negotiables (CI and reviewers block on these)

Feature parity. Every user-visible feature lands in BOTH SDKs in the same PR, with the same API shape and defaults. Names map snake_case (Python) ↔ camelCase (TypeScript); everything else (field order, default values, error classes) matches. No Python-only or TS-only public surface.
CHANGELOG.md in the same PR. Append an entry under ## Unreleased (### Added / ### Changed / ### Fixed / ### Deprecated / ### Removed / ### Security) for any user-visible change. Exempt: pure refactors, test-only, docs-only — note that in the PR description.
Opt-in, backward-compatible. New config fields are optional with safe defaults. Never change an existing default or require a new credential.
Authentic tests. Tests exercise real code paths. Mock ONLY the paid/external boundary (provider/carrier WebSocket, carrier HTTP) — tag Python mocks @pytest.mark.mocked, name TS mocks *.mocked.test.ts.
No secrets / PII. No real API keys, phone numbers, emails, or customer SIDs in code, tests, docs, or notebooks. Use env vars + placeholders.
No external license headers or "ported from " provenance comments in source files. Naming a provider/carrier you integrate (Twilio, Telnyx, Plivo, OpenAI, ElevenLabs, Deepgram, …) is expected and fine; copying a competitor SDK's lineage/headers is not.
Async everywhere. All I/O is async (Python asyncio, TS Promises). Logger: Python logging.getLogger("getpatter"), TS getLogger() — never print() / bare console.* in library code.

Read the full file on GitHub · 68 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.

2mo ago First seen · 68 lines · 855 tokens per session scan A eda2ef9a8c85

Subscribe to this mod's changes

Patter AGENTS.md is an instructions file published in the GitHub repository PatterAI/Patter (1,083 stars, last pushed 2d ago), licensed MIT. It adds 855 tokens to every session, about $0.0034 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 2026-08-30.

Python open-source openai sdk speech-to-text telnyx

Patter AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Patter AGENTS.mdPatterAI/Patter	Instructions file	1.1k	2d ago	MIT	A	855	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Patter: Instructions file for Codex