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.
Borrowing it
Nothing to install: this file belongs to elie222/rakazo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/elie222/rakazo/main/.github/prompts/weekly-dependencies.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/commands/elie222/rakazo/weekly-dependencies)<a href="https://agentmods.dev/commands/elie222/rakazo/weekly-dependencies"><img src="https://agentmods.dev/badge/commands/elie222/rakazo/weekly-dependencies/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.
<a href="https://agentmods.dev/commands/elie222/rakazo/weekly-dependencies"><img src="https://agentmods.dev/badge/commands/elie222/rakazo/weekly-dependencies.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00403 |
| Opus 5.5 | $0.00000 | $0.00161 |
| Sonnet 5.5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
weekly-dependencies 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 3d 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.
What it actually says
Update Rakazo's dependencies in one small, reviewable batch. Follow AGENTS.md.
Use npm-check-updates to inspect the workspaces, review relevant release notes, and apply worthwhile patch releases. You own the investigation, edits, lockfile, compatibility fixes, and validation; no dependency list is prescribed.
Preserve intentional compatibility constraints: TypeScript 6 in Expo/Astro, Expo's supported React/native versions, and patched Electron Builder. Leave the pi model-catalog packages to the existing model-catalog-bump workflow. Defer major/minor migrations and anything that needs a newer supported Node baseline. If an update breaks compatibility, omit it rather than weakening checks.
Prepend the directory containing $VALIDATION_NODE to PATH for package commands
so validation covers CI's Node baseline. Keep package caches inside the ignored
.cache/ directory if the sandbox needs a writable cache.
Install dependencies, generate the database client, and run workspace typechecks,
affected offline unit tests, and production builds. Use fake build credentials as
in CI. Run Linux host-script checks; leave desktop Electron E2E to CI and report
that limit. Check supported Node versions and run
focused tests for any fixes. Keep fixes strictly related to the updates. Do not
change workflows, agent instructions, secrets, or unrelated code. Do not run
live-provider tests.
If no worthwhile updates remain, leave the checkout unchanged. Otherwise leave the complete changes uncommitted. Do not push, open a PR, or merge; the workflow publishes the diff separately. Only leave a patch when its required local checks pass. If validation cannot pass, revert the proposed changes and explain why.
Your final message becomes the public PR description. Use concise Why, Changes, and Validation sections, including deferred updates and any validation limits. Follow AGENTS.md's public-content rules; never include credentials, local paths, account details, or business metrics. Do not claim checks ran unless they did.
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.
- 3d ago First seen · 33 lines · 0 tokens per session scan A 8bb54516f0c9
weekly-dependencies is a command published in the GitHub repository elie222/rakazo (6,155 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 403 tokens. 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 2026-10-26.
Other commands, from other repositories
test
Generates comprehensive test suite with ROI-based prioritization.
session
Complete guide to managing pair programming sessions.
test-tdd
Run when user calls /test-tdd. Scans modified files, locates their corresponding unit/integration test suites, and runs them.
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
lg:node
Create, modify, and manage nodes in LangGraph graphs including LLM nodes, tool nodes, human-in-the-loop, subgraphs, and conditional nodes.
story-and-test
For the component(s) in scope.