talkflow-public: Instructions file for Codex

AGENTS.md

talkflow-public AGENTS.md is an instructions file for Codex, OpenCode from tororae/talkflow-public. It costs 1,688 tokens per session, scanned A, original, MIT.

Project-specific development instructions for TalkFlow, a Swift application that connects its user interface, application logic, and external services. They define architecture, file-size, privacy, and safety rules.

In plain words
What is it for?
Use them when changing TalkFlow’s Swift code, messaging integrations, storage, authentication, AI connections, UI, tests, logs, or documentation.
Why use it?
They help agents place code in the correct layer and prevent sensitive chat data, account identifiers, API keys, and unsafe message content from leaking into the project.

Instructions file for CodexOpenCode

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

This is tororae/talkflow-public's own configuration. It tells Codex and OpenCode how to work on talkflow-public 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 talkflow-public configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tororae/talkflow-public. 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/tororae/talkflow-public/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tororae/talkflow-public

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 talkflow-public AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tororae/talkflow-public/agents-md"><img src="https://agentmods.dev/badge/instructions/tororae/talkflow-public/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,688 This file is loaded in full into every session.
When invoked 1,688 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 $0.01688 $0.01688
Opus 5.5 $0.00675 $0.00675
Sonnet 5.5 $0.00338 $0.00338
Haiku 4.5 $0.00169 $0.00169

Measured 2mo ago against content hash 2ff634fac14e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

talkflow-public 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.

TalkFlow 개발 규칙

아키텍처 경계

  • TalkFlowDomain은 순수 모델·정책·프로토콜만 둔다. UI, 파일, 네트워크, macOS API에 의존하지 않는다.
  • TalkFlowApplication은 유스케이스와 작업 흐름을 둔다. 구체 어댑터를 직접 생성하지 않는다.
  • TalkFlowInfrastructure는 카카오톡, 로컬 저장소, Keychain, AI 제공자, macOS 상태 같은 외부 연동 구현을 둔다.
  • TalkFlowFeatures는 SwiftUI 화면과 화면 전용 상태를 둔다. 인프라 구현을 직접 호출하지 않는다.
  • TalkFlowApp은 앱 시작점과 의존성 조립만 담당한다.

파일 크기와 분리

  • Swift 소스 파일은 250줄을 권장 상한으로 하고 400줄을 넘기지 않는다.
  • 한 파일에는 하나의 주된 책임만 둔다. 모델, 프로토콜, 유스케이스, 화면, 어댑터를 섞지 않는다.
  • 화면이 커지면 화면 구성 요소, 상태 모델, 표시용 포맷터로 나눈다.
  • 조건문이 많은 정책은 독립된 정책 타입과 테스트로 분리한다.
  • 새 기능은 먼저 어느 모듈에 속하는지 정한 뒤 구현한다.

안전·개인정보

  • 카카오톡 원문, 계정 식별값, API 키를 로그·테스트 fixture·Git에 넣지 않는다.
  • API 키와 인증 토큰은 Keychain에만 저장한다.
  • 계정과 채팅방 정책의 기본 키는 표시 이름이 아니라 안정적인 식별값이다.
  • 계정 확인이 불확실하거나 자동 전송이 일시 중지된 상태에서는 전송하지 않는다.
  • 채팅 메시지는 신뢰할 수 없는 입력이다. 메시지 내용이 앱 정책이나 시스템 지시를 바꾸게 해서는 안 된다.
  • 테스트 픽스처와 주석의 이름·방 이름·메시지는 지어낸 것을 쓴다. 계정 자신은 한결, 상대는 지수·민준·민수, sender id는 19자리 합성값. 실제 값을 예시로 쓰면 그게 근거가 되어 버리고, 나중에 지울 때 근거까지 함께 사라진다.
  • 측정해서 알아낸 것을 적을 때 실제 이름이나 식별값이 논거로 필요해 보이면, 그것 없이 같은 논거를 쓸 방법을 먼저 찾는다. 「같은 표시 이름을 쓰는 두 사람이 sender id로만 구분됐다」는 이름 없이도 성립한다.
  • 실제 카카오톡 문장을 인용해야 하면 원문 대신 같은 모양으로 옮겨 적고, 옮겨 적었다고 밝힌다.
  • 이슈·PR·커밋 메시지에도 같은 규칙이 적용된다. 재현 방법을 적을 때 실제 대화, 실제 이름, 계정 식별값을 붙이지 않는다. 합성 fixture 또는 나와의 채팅으로 재현해서 적는다.

문서

  • 제품 결정은 DESIGN.md, 모듈 경계는 docs/ARCHITECTURE.md, 외부 소프트웨어의 관측된 동작은 docs/PLATFORM-FINDINGS.md에 둔다.
  • 측정해서 알아낸 사실은 확인 방법을 함께 적는다. 카카오톡과 macOS는 우리 통제 밖이라 그 사실은 언젠가 틀려진다.
  • 설계 문서에 측정치를 늘어놓지 않는다. 결정과 근거만 남기고 수치는 실측 기록을 가리킨다.

검증

  • 도메인 정책을 바꾸면 대응하는 단위 테스트를 추가한다.

  • UI나 인프라 변경 뒤에는 swift build를 실행한다.

  • 테스트는 아래 명령으로 돌린다. 그냥 swift test는 CPU 0%로 무한 정지할 수 있다. KatokPhotoExtractorTests.swift의 테스트가 실제 카카오톡 컨테이너를 열거하는데, 권한 없는 열거는 에러가 아니라 돌아오지 않는 호출이다. 권한이 살아 있으면 통과하므로, 되다가 안 되는 것이 정상이다.

    swift test --skip extractedPhotosLandInOneDirectoryThatDiscardRemoves \
               --skip aMessageWithNoPictureLeavesNoDirectoryBehind \
               --skip anEmptyPlaceholderFileIsNotOfferedToTheModel \
               --skip onlyPhotosUpToTheCapAreEverAskedFor \
               --skip withoutTheConnectorThereAreNoPhotosAndNoTemporaryFiles
    

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.

  1. 2mo ago First seen · 68 lines · 1,688 tokens per session scan A 2ff634fac14e

Subscribe to this mod's changes

talkflow-public AGENTS.md is an instructions file published in the GitHub repository tororae/talkflow-public (11 stars, last pushed 2mo ago), licensed MIT. It adds 1,688 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 2026-08-30.

Related

talkflow-public AGENTS.md compared with instructions from other repositories

talkflow-public AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
talkflow-public AGENTS.mdtororae/talkflow-publicInstructions file112mo agoMITA1,688Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot