Diffuse-Native-Apps: Instructions file for Codex

AGENTS.md

Diffuse-Native-Apps AGENTS.md is an instructions file for Codex, OpenCode from hoangsonww/Diffuse-Native-Apps. It costs 1,284 tokens per session, scanned A, original, MIT.

A repository instruction file for Diffuse-Native-Apps, a local-first app that keeps device history on the device. It explains the project layout, rules, documentation, testing, and release procedures.

In plain words
What is it for?
Use it when working on the project’s Swift, Kotlin, native apps, tests, documentation, or release tasks.
Why use it?
It gives an agent the project context needed before changing code. This reduces the risk of ignoring the repository’s architecture or safety rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is hoangsonww/Diffuse-Native-Apps's own configuration. It tells Codex and OpenCode how to work on Diffuse-Native-Apps 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 Diffuse-Native-Apps configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/Diffuse-Native-Apps. 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/hoangsonww/Diffuse-Native-Apps/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/Diffuse-Native-Apps

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 Diffuse-Native-Apps AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hoangsonww/diffuse-native-apps/agents-md/github.svg)](https://agentmods.dev/instructions/hoangsonww/diffuse-native-apps/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hoangsonww/diffuse-native-apps/agents-md"><img src="https://agentmods.dev/badge/instructions/hoangsonww/diffuse-native-apps/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 Diffuse-Native-Apps AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hoangsonww/diffuse-native-apps/agents-md"><img src="https://agentmods.dev/badge/instructions/hoangsonww/diffuse-native-apps/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,284 This file is loaded in full into every session.
When invoked 1,284 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 $0.01284 $0.01284
Opus 5.5 $0.00514 $0.00514
Sonnet 5.5 $0.00257 $0.00257
Haiku 4.5 $0.00128 $0.00128

Measured yesterday against content hash c0750f34c664, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Diffuse-Native-Apps 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 yesterday.

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 · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diffuse is a local-first device-history product. Five native apps (macOS, iOS, iPadOS, watchOS, Android) answer one question on the device that observed it. The four Apple apps share a capability-driven Swift engine. Android is a fully native Kotlin implementation. Snapshots never leave the device. There is no account, no cloud, and no telemetry. GitHub is the only backend.

Read this first

  1. Documentation/README.md then Documentation/Architecture.md
  2. Documentation/adr/
  3. Nested AGENTS.md in Packages/, Apps/, Tests/, Tools/ (closest file wins)

Adding a capability: Documentation/CapabilityGuide.md and .agents/skills/add-capability/SKILL.md. Writing tests: Documentation/Testing.md. CLI: Documentation/CLI.md. Scripts/CI: Documentation/Repository.md. Stack inventory: Documentation/TechStack.md. Build failures: Documentation/Troubleshooting.md. Tagging: Documentation/Releasing.md.

Layout

Packages/     domain engine (Swift)
Apps/         four native Apple apps + widgets/complications
Android/      native Kotlin app + domain engine
Tools/        diffuse-dev CLI
Tests/        Domain, Invariants, Integration, Support
Fixtures/     golden snapshots and expected diffs
.agents/      canonical skills (copied to .claude/skills/)
ARCHITECTURE.md  repository-wide Swift + Kotlin map
Apps → DiffuseUI → DiffuseCapabilities / DiffuseCore → DiffuseModels
                                                     → DiffuseDiff
                                                     → DiffuseStorage

Core packages have no UIKit/AppKit imports. They type-check against iOS and watchOS via ./Scripts/crosscheck.sh.

Hard rules

  • No third-party Swift packages.
  • No signing identities, team IDs, or provisioning profiles in this repo.
  • CI must stay able to produce unsigned artifacts.
  • Do not add CodeQL, Super-Linter, Scorecard, Semgrep, Trivy, Sonar, or other noisy static scanners.
  • Do not add Dependabot, Renovate, or any other dependency bot. Bumps are deliberate and human.
  • Do not weaken a golden fixture to make a test pass.
  • Swift 6, complete concurrency checking.
  • One concern per change.
  • Procedural workflows live in skills, not in this file.

Read the full file on GitHub · 110 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. yesterday First seen · 110 lines · 1,284 tokens per session scan A c0750f34c664

Subscribe to this mod's changes

Diffuse-Native-Apps AGENTS.md is an instructions file published in the GitHub repository hoangsonww/Diffuse-Native-Apps (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,284 tokens to every session, about $0.0051 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 2026-11-07.

Related

Diffuse-Native-Apps AGENTS.md compared with instructions from other repositories

Diffuse-Native-Apps AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Diffuse-Native-Apps AGENTS.mdhoangsonww/Diffuse-Native-AppsInstructions file111mo agoMITA1,284Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot