Rakazo is an open-source platform for running persistent AI teammates with their own conversations, memory, routines, and history. It is for people who want bots that can use browsers, terminals, files, computers, voice, peer delegation, and user-selected models through web, desktop, mobile, or local deployments.
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/elie222/rakazo/agents-mdgit clone --depth 1 https://github.com/elie222/rakazoWrote 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.
[](https://agentmods.dev/instructions/elie222/rakazo/agents-md)<a href="https://agentmods.dev/instructions/elie222/rakazo/agents-md"><img src="https://agentmods.dev/badge/instructions/elie222/rakazo/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01014 | $0.01014 |
| Opus 5 | $0.00507 | $0.00507 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
rakazo 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 today.
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 — 16 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
- This is a public repository: assume all tracked content and diffs are public. Never commit secrets,
.envfiles, private URLs, personal/customer data, or real production data; use fake placeholders. Reviewgit statusand the staged diff before committing, and never force-add ignored files. If private data appears, stop and alert the maintainer. - Rakazo is one product across web, Electron desktop, and Expo mobile; Electron hosts the web UI. Put shared behavior, contracts, API logic, and reusable UI in packages. Keep only genuinely native navigation, storage, permissions, and interactions platform-specific. Core workflows must cover every applicable surface or degrade safely for an explicit reason.
- No hosted vendor is required to run the core product. Keep LLMs, sandboxes, memory, voice, integrations, and future external services optional and behind provider-neutral interfaces. Vendor SDKs, configuration, and translation belong only in adapters and composition roots. New providers must reuse shared contracts and deterministic offline conformance tests.
- Keep UI and copy minimal. Show advanced capability progressively and only when it becomes relevant; do not add explainer text that repeats the interface. Frontends express intent and render state; the backend owns orchestration, authorization, validation, retries, recovery, and provider translation. Give controls concise accessible names when needed.
- Treat every visible word as UI. Start UX work by asking what can be removed, and prefer progressive disclosure over persistent explanation or status chrome. If a PR adds user-facing copy, its description must quote the copy, explain why it is necessary, and say why removing it or revealing it only when relevant would not work.
- Keep code simple: reuse existing primitives and one source of truth, remove duplication and unused flexibility, and avoid speculative abstractions. Add an interface when it protects a real external or platform boundary, not for its own sake.
- Treat auth, secret handling, sandbox boundaries, host commands, and integrations as security-sensitive. Keep tests deterministic and offline by default.
- The desktop Playwright suite (
pnpm --filter @rakazo/desktop test:e2e) opens real Electron windows and steals focus on macOS. Do not run it on a maintainer's machine as routine verification; run the unit tests locally and let CI's virtual-display job run the e2e on push. - After creating a pull request, stay with it until CI and automated review bots have finished. Poll checks, reviews, review threads, and PR comments at roughly 60-second intervals; passing checks alone do not mean the review is complete. Address every actionable issue, push the fixes, and repeat the review cycle until no actionable feedback remains. Do not merge while review bots are still pending or review issues remain unresolved.
- PR descriptions say why the change exists, what changed, and how it was tested. Write Why as the product reason (what was wrong and what this changes); never "Elie wants" or a third-person briefing of a named person; the maintainer is the author.
- Commit messages, PR descriptions, issues, and review replies are public too. Describe test results in words instead of pasting tool output, and never include anything that identifies a person, machine, or account: local paths, usernames, hostnames, signing identities, legal entity names, Apple Team IDs, API key IDs, issuer or tenant IDs, account emails, or the accounts, machines, and files that secret values came from. Naming the secrets a workflow reads is fine; use placeholders when a value must be shown.
- For UI changes, link the CI E2E screenshot that shows the change on the PR; add the web test that opens that screen if it is missing. For native-only mobile UI that CI cannot capture, say so in the PR instead of linking an unrelated web screenshot.
- UI system. Colors live in
@rakazo/ui-tokensas semantic tokens (background, card, muted, border, primary, destructive, ...) with one TypeScript source that generatestokens.css; never hardcode a product hex or use[var(--…)]arbitrary values. Web and Electron use shadcn/ui on Base UI, vendored intopackages/ui-webviapnpm exec shadcn addfrom the official registry only (third-party registries are a supply-chain risk); reuse those components before writing chrome by hand, and reuseapps/web/src/components/ai/for AI moments (loading, shimmer, success). The app is monochrome: primary is ink, status colors are destructive/success/warning, bots carry the only identity color. Mobile is native-first: Expo Router, Expo UI, native sheets, menus, alerts and pickers wherever one exists; custom surfaces (thread, composer, avatars, cards) use plain StyleSheet with the shared tokens throughapps/mobile/lib/appearance, and system chrome stays PlatformColor vialib/native. Mobile may diverge from web when the native pattern is better.
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.
- today Changed · +1 lines · +65 tokens per session 79de1c8cd6f2
- yesterday Changed · +3 lines · +317 tokens per session 9d4c3f07bd11
- 2d ago Changed · +1 lines · +56 tokens per session 8dcad91dff7f
- 5d ago First seen · 11 lines · 576 tokens per session scan A ddc6efa65d06
rakazo AGENTS.md is an instructions file published in the GitHub repository elie222/rakazo (1,925 stars, last pushed today), licensed Apache-2.0. It adds 1,014 tokens to every session, about $0.0051 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 2026-08-30.
Other instructions, from other repositories
polar CLAUDE.md
Claude Code instructions for jamaljsr/polar, covering claude.md, about polar, essential commands, development and testing individual files.
polar copilot-instructions.md
Copilot instructions for jamaljsr/polar, covering polar - ai coding assistant instructions, core architecture, network orchestration via docker compose, state management (easy-peasy + redux) and visual designer (react flow chart).
chat-on-steroids CLAUDE.md
Claude Code instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
pydantic-ai-backend CLAUDE.md
Claude Code instructions for vstorm-co/pydantic-ai-backend, covering claude.md, what this project is, commands, structure and core pattern.
vellium AGENTS.md
AGENTS.md instructions for tg-prplx/vellium, covering agents.md — vellium contributor and coding-agent guide, 1. product and runtime model, 2. start every task safely, 3. repository map and renderer: src/.
teak AGENTS.md
AGENTS.md instructions for praveenjuge/teak, covering teak agent guide, start here, architecture invariants, convex work and verification.