Ruflo is an execution and coordination layer for Claude Code and Codex that equips AI coding agents with tools, memory, control loops, sandboxes, and collaboration mechanisms. Developers use it to organize specialized agents into swarms, coordinate workflows, retain knowledge across sessions, and communicate across machines. The catalogue entries are Ruflo’s skills, commands, agents, hooks, and plugin components.
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 commands/ruvnet/ruflo/sandboxgit clone --depth 1 https://github.com/ruvnet/rufloWrote 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/ruvnet/ruflo/sandbox)<a href="https://agentmods.dev/commands/ruvnet/ruflo/sandbox"><img src="https://agentmods.dev/badge/commands/ruvnet/ruflo/sandbox.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 | $0.00015 | $0.00487 |
| Opus 5 | $0.00008 | $0.00244 |
| Sonnet 5 | $0.00003 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
flow-nexus-sandbox 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 yesterday.
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.
Copies of this mod
7 near-identical copies found in the catalogue:
- flow-nexus-sandbox — 100% identical, 83 lines differ
- flow-nexus-sandbox — 100% identical, 0 lines differ
- flow-nexus-sandbox — 100% identical, 0 lines differ
- flow-nexus-sandbox — 100% identical, 0 lines differ
- flow-nexus-sandbox — 100% identical, 0 lines differ
- flow-nexus-sandbox — 100% identical, 0 lines differ
- flow-nexus-sandbox — 100% identical, 0 lines differ
What it actually says
Flow Nexus Sandboxes
Deploy and manage isolated execution environments.
Create Sandbox
mcp__flow-nexus__sandbox_create({
template: "node", // node, python, react, nextjs, vanilla, base
name: "my-sandbox",
env_vars: {
API_KEY: "your_api_key",
NODE_ENV: "development"
},
timeout: 3600 // seconds
})
Execute Code
mcp__flow-nexus__sandbox_execute({
sandbox_id: "sandbox_id",
code: `
console.log('Hello from sandbox!');
const result = await fetch('https://api.example.com');
return result.json();
`,
language: "javascript",
capture_output: true
})
Manage Sandboxes
// List all sandboxes
mcp__flow-nexus__sandbox_list({ status: "running" })
// Get status
mcp__flow-nexus__sandbox_status({ sandbox_id: "id" })
// Upload file
mcp__flow-nexus__sandbox_upload({
sandbox_id: "id",
file_path: "/app/data.json",
content: JSON.stringify(data)
})
// Stop sandbox
mcp__flow-nexus__sandbox_stop({ sandbox_id: "id" })
// Delete sandbox
mcp__flow-nexus__sandbox_delete({ sandbox_id: "id" })
Templates
- node: Node.js environment
- python: Python 3.x environment
- react: React development setup
- nextjs: Next.js full-stack
- vanilla: Basic HTML/CSS/JS
- base: Minimal Linux environment
Common Patterns
// API development sandbox
mcp__flow-nexus__sandbox_create({
template: "node",
name: "api-dev",
install_packages: ["express", "cors", "dotenv"],
startup_script: "npm run dev"
})
// ML sandbox
mcp__flow-nexus__sandbox_create({
template: "python",
name: "ml-training",
install_packages: ["numpy", "pandas", "scikit-learn"]
})
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.
- yesterday First seen · 83 lines · 15 tokens per session scan A 6940ff3b42fa
flow-nexus-sandbox is a command published in the GitHub repository ruvnet/ruflo (70,498 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 487 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
launch
Preview the public launch — the file bundle, the secret/PII scan, and the release gates — in dry-run mode, cut a release by deriving its version and composing its changelog, and scaffold the changelog-driven release gate into a managed repo. The preview performs zero writes; ship writes the dated CHANGELOG heading and…
disembark
Pack a lifeboat from a repository into a destination directory — read-only over the source, behind a destination safety gate, secret-scanned before any write. Point it at any repo (including a dead or archived one) and write the lifeboat elsewhere.
capture
Capture issues to the structured per-repo ledger and query them, by invoking the abcd binary. Bare invocation is a read-only status render; list/promote/resolve/wontfix act on the ledger.
briefing
Structured pre-execution briefing session -- collects case context through specialist panel, builds execution plan, supports resume and depth control.
legal-goal
Define a checkable legal success condition for /legal-loop. Accepts a named profile (citations-clean, draft-passes-gate, adversarial-converge, nda-batch-clean, reg-watch, timeline-sourced) or free-text objective. Produces a persisted Goal Record — never starts work itself.
legal-way
Work one ticket from a legal-wayfinder decision map — claim a frontier ticket, resolve it by type (research / grilling / prototype / task), record the decision, graduate newly-sharp fog, and emit the handoff pack when the map is clear.