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/.agents/skills/composio/SKILL.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/skills/elie222/rakazo/composio)<a href="https://agentmods.dev/skills/elie222/rakazo/composio"><img src="https://agentmods.dev/badge/skills/elie222/rakazo/composio/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/skills/elie222/rakazo/composio"><img src="https://agentmods.dev/badge/skills/elie222/rakazo/composio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.01103 |
| Opus 5.5 | $0.00034 | $0.00441 |
| Sonnet 5.5 | $0.00017 | $0.00221 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
composio 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 2mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composio
Use this skill as a router. Identify the product and the job, load only the relevant guidance, consult canonical documentation for volatile details, and then answer or do the work the user requested.
1. Choose the product
Do not blend the products. They use different credentials and setup paths.
| Composio For You | Composio Platform | |
|---|---|---|
| Use when | Someone wants their own agent to use their own apps | A developer is building a product whose users connect accounts |
| Primary surface | MCP or the Composio CLI | SDK sessions inside an application |
| Credential | ck_... consumer key when the client requires a header |
COMPOSIO_API_KEY project key |
| Dashboard | dashboard.composio.dev → For You |
dashboard.composio.dev → Platform |
Ask one short question only when context does not establish the product:
Is this for your own agent and accounts, or for a product where your users connect their accounts?
Treat a named personal AI client with no product code as For You. Treat an application codebase, SDK, user or tenant identity, backend, or product agent as Platform.
2. Choose the job
Identify the requested outcome before taking action:
- Explain or discover: answer a question, compare approaches, or find the current API.
- Set up: establish credentials, an MCP client, the CLI, or an SDK for the first time.
- Build or change: integrate Composio into an existing agent or application.
- Operate: find, connect, and run tools for a real task.
- Debug or migrate: diagnose a failure, update an older integration, or move from legacy direct execution or Tool Router.
Do not turn an explanation, documentation lookup, or narrow bug fix into onboarding.
3. Load only the relevant guidance
- For You: read Composio For You.
- Platform: read Composio Platform.
- Provider, connection, or execution failure: also read Errors and provider gotchas.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 78 lines · 84 tokens per session scan A 48d1fa49983d
composio is a skill published in the GitHub repository elie222/rakazo (6,155 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 1,103 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
data-dashboards
Build a fast, good-looking page: a data dashboard, or any page made with showhtml (a landing page, a pricing page, a tool), in this chat or at a public link with publishpage. Use when the person asks for a dashboard, charts or KPIs on a page, a page or mock-up to look at, or a data page to share or keep up to date.
create-verification-skill
Create one skill that teaches a bot how to launch, drive, and verify a specific app or project. Use only when the user explicitly asks for a verification skill.
phone-harness
Control, inspect, test, or automate a physical Android phone connected to OpenMausBot over authorized USB debugging. Use for explicit Android, USB phone, ADB, mobile-app, tapping, typing, swiping, scrolling, screenshot, or phone-screen requests.
dynamic-workflows
Use when writing, debugging, or resubmitting a dynamic-workflow script for the CreateWorkflow tool: choosing subagent topology, typing subagent results, fanning out over files or git, gating loops on world.run commands, testing pieces with EvalWorkflowSnippet, planner-reviewer loops, confirming findings before…
visualize
Create visualizations and interactive tools directly in conversation. Proactively use to show how something works; explore 'what happens when', 'what changes', or 'help me understand'; compare or inspect; create simulations, maps, charts, graphs, and mockups. Use standard tools for static scientific figures.
x-research
Research and synthesize substantial live X evidence across one or multiple topics, labeled query angles, Top and Latest, relevant timelines, and post context. Use for open-ended research, comparisons, trend discovery, emerging accounts, current events, or technical discussion on X.