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.
npx agentmods add instructions/kellastico/aka/claude-mdgit clone --depth 1 https://github.com/Kellastico/AKAWhat 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 | $0.01101 | $0.01101 |
| Opus 5 | $0.00550 | $0.00550 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
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.
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_casein Rust, camelCase wrapper insrc/lib/tauri/commands.ts
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.
- 2d ago First seen · 111 lines · 1,101 tokens per session scan A 78986379f016
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.
Other instructions, from other repositories
cctop AGENTS.md
Instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
gemini-cli-desktop AGENTS.md
Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
examples CLAUDE.md
Claude Code instructions for rossoctl/examples, covering claude.md - agent examples, repository structure, key commands, code style and dco sign-off (mandatory).
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
claude-code-templates CLAUDE.md
Instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.