wolffish-app: Instructions file for Codex

AGENTS.md

wolffish-app AGENTS.md is an instructions file for Codex, OpenCode from thewolffish/wolffish-app. It costs 1,642 tokens per session, scanned C, original, MIT.

Repository instructions for Wolffish, a personal desktop AI application built with Electron, React, and TypeScript. They describe its processes, folders, local data, and development conventions.

In plain words
What is it for?
Use them when changing Wolffish's interface, Electron processes, local AI integration, configuration, storage, or project structure.
Why use it?
They clarify where code belongs and how the desktop application's main process, user interface, and communication bridge must interact.

Instructions file for CodexOpenCode

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

This is thewolffish/wolffish-app's own configuration. It tells Codex and OpenCode how to work on wolffish-app 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 wolffish-app configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thewolffish/wolffish-app. 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/thewolffish/wolffish-app/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/thewolffish/wolffish-app

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 wolffish-app AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thewolffish/wolffish-app/agents-md.svg)](https://agentmods.dev/instructions/thewolffish/wolffish-app/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/thewolffish/wolffish-app/agents-md"><img src="https://agentmods.dev/badge/instructions/thewolffish/wolffish-app/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,642 This file is loaded in full into every session.
When invoked 1,642 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
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 $0.01642 $0.01642
Opus 5 $0.00821 $0.00821
Sonnet 5 $0.00328 $0.00328
Haiku 4.5 $0.00164 $0.00164

Measured 6d ago against content hash 0144f95f6d4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

wolffish-app AGENTS.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Hard rule: **uninstall must be `rm -rf ~/.wolffish/`**. Every byte the app writes goes there:
AGENTS.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wolffish — Agent Guide

Personal AI desktop app. Electron + React + TypeScript. The runtime is modeled as a 15-module brain — see ARCH.md for the full mapping.

Stack

  • Electron via electron-vite. Three processes: main (Node), preload (bridge), renderer (React).
  • Tailwind v4, i18next (en / ar), Ollama for local inference.
  • IPC is the only main↔renderer channel. Never import main code from the renderer or vice versa — go through preload.

Project layout

src/
├── main/            Electron main process (Node)
│   ├── index.ts     entry — IPC handlers live here
│   ├── ollama/      Ollama HTTP client + install detection
│   ├── workspace/   ~/.wolffish init, config, purge
│   ├── lockfile/    single-instance guard
│   ├── system/      OS info (platform, RAM, disk)
│   └── runtime/     the brain — one folder per region
│       ├── thalamus/, prefrontal/, hippocampus/, ...
│       └── providers/  LLM provider adapters (anthropic/, openai/, local/)
├── preload/         contextBridge — types in index.d.ts
├── renderer/src/
│   ├── App.tsx, main.tsx, env.d.ts, assets/
│   ├── components/  common/ (composed) and core/ (primitives)
│   ├── pages/       one folder per screen
│   ├── providers/   React context providers
│   ├── hooks/       custom hooks
│   └── lib/         i18n, utils
└── defaults/workspace/  bundled into the app, copied to ~/.wolffish on first launch

resources/   fonts/, icons/, images/  (use @resources alias)
scripts/     build helpers (one folder each)

Folder convention — one thing per folder

Every module lives in its own kebab-case folder, and the file inside matches the folder name:

components/core/copy-button/CopyButton.tsx
hooks/use-online/useOnline.ts
pages/model-picker/ModelPicker.tsx
main/runtime/hippocampus/hippocampus.ts

When a file has both a component and a hook (Fast Refresh requires single-purpose files), split them:

providers/flow/FlowProvider.tsx   ← component only
providers/flow/useFlow.ts         ← context + hook + types

Read the full file on GitHub · 114 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 · 114 lines · 1,642 tokens per session scan C 0144f95f6d4a

Subscribe to this mod's changes

wolffish-app AGENTS.md is an instructions file published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed yesterday), licensed MIT. It adds 1,642 tokens to every session, about $0.0082 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

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

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

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