AKA CLAUDE.md

A repository-specific instruction file for AKA, a desktop app that lets users send coding tasks to different AI models and coding agents, then review the resulting changes.

In plain words
What is it for?
Use it when changing AKA's Tauri desktop shell, React interface, task workflow, model and agent selection, diff review, terminal, or state management.
Why use it?
It explains the project's local-first design, technology choices, and rule that users can choose their own model, provider, and agent.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/kellastico/aka/claude-md
Clone the repo
git clone --depth 1 https://github.com/Kellastico/AKA
Per session 1,101 This file is loaded in full into every session.
When invoked 1,101 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01101 $0.01101
Opus 5 $0.00550 $0.00550
Sonnet 5 $0.00220 $0.00220
Haiku 4.5 $0.00110 $0.00110

Measured 2d ago against content hash 78986379f016, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AKA CLAUDE.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 2d 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.

CLAUDE.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AKA — Root CLAUDE.md

What This Project Is

AKA is a local-first, task-driven desktop application for LLM-powered coding agents. Built with Tauri v2 (Rust backend) + React + TypeScript (frontend).

AKA is fully agnostic — users bring any LLM backend (Ollama, MLX, oMLX, LM Studio, any OpenAI-compatible endpoint) and any agent (Aider, OpenCode, Hermes, OpenClaw, LangChain, custom scripts). AKA orchestrates them; it never prescribes them.

The app is task-first: describe what you want built, pick your model + agent, launch, review the diff, approve or reject. Not a chat interface — a work dispatch tool.


Tech Stack

Layer Choice Reason
Shell Tauri v2 Cross-platform, Rust IPC, small binary
Frontend React 18 + TypeScript Ecosystem, component reuse
Bundler Vite Fast HMR, Tauri-compatible
State Zustand Lightweight, slices pattern
Editor/Diff Monaco Editor VS Code-grade, built-in diff API
Terminal Xterm.js ANSI support, real-feel streaming output
Styling Tailwind CSS v4 Utility-first, consistent tokens

Core Principle: Full Agnosticism

AKA never hardcodes a model, provider, or agent. Every integration is:

  • Configured by the user via the Provider Manager or Agent Runner
  • Stored as a user-defined record (name, command/URL, args)
  • Treated identically at runtime regardless of type

AKA's job is orchestration and UX — not opinion about which LLM or agent is best.


Project Conventions

Structure

  • Each feature lives under src/features/<NN-feature-name>/
  • Every feature has its own Context.md
  • Context.md = current state, decisions made, open questions

Naming

  • Components: PascalCase.tsx
  • Hooks: use-kebab-case.ts
  • Stores: use-feature-store.ts (Zustand)
  • Tauri commands: snake_case in Rust, camelCase wrapper in src/lib/tauri/commands.ts

Read the full file on GitHub · 111 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. 2d ago First seen · 111 lines · 1,101 tokens per session scan A 78986379f016

Subscribe to this mod's changes

AKA CLAUDE.md is an instructions file published in the GitHub repository Kellastico/AKA (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,101 tokens to every session, about $0.0055 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 2026-08-31.

Related

Other instructions, from other repositories