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 skills add ruvnet/ruflo --skill stream-chaingit 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/skills/ruvnet/ruflo/stream-chain)<a href="https://agentmods.dev/skills/ruvnet/ruflo/stream-chain"><img src="https://agentmods.dev/badge/skills/ruvnet/ruflo/stream-chain/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/ruvnet/ruflo/stream-chain"><img src="https://agentmods.dev/badge/skills/ruvnet/ruflo/stream-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 64 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
- high Prompt Injection · line 227 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
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 | $0.00018 | $0.02787 |
| Opus 5.5 | $0.00007 | $0.01115 |
| Sonnet 5.5 | $0.00004 | $0.00557 |
| Haiku 4.5 | $0.00002 | $0.00279 |
Grade A, and why
stream-chain 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 1mo 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.
This is a copy
100% identical to stream-chain — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 564 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stream-Chain Skill
Execute sophisticated multi-step workflows where each agent's output flows into the next, enabling complex data transformations and sequential processing pipelines.
Overview
Stream-Chain provides two powerful modes for orchestrating multi-agent workflows:
- Custom Chains (
run): Execute custom prompt sequences with full control - Predefined Pipelines (
pipeline): Use battle-tested workflows for common tasks
Each step in a chain receives the complete output from the previous step, enabling sophisticated multi-agent coordination through streaming data flow.
Quick Start
Run a Custom Chain
claude-flow stream-chain run \
"Analyze codebase structure" \
"Identify improvement areas" \
"Generate action plan"
Execute a Pipeline
claude-flow stream-chain pipeline analysis
Custom Chains (run)
Execute custom stream chains with your own prompts for maximum flexibility.
Syntax
claude-flow stream-chain run <prompt1> <prompt2> [...] [options]
Requirements:
- Minimum 2 prompts required
- Each prompt becomes a step in the chain
- Output flows sequentially through all steps
Options
| Option | Description | Default |
|---|---|---|
--verbose |
Show detailed execution information | false |
--timeout <seconds> |
Timeout per step | 30 |
--debug |
Enable debug mode with full logging | false |
How Context Flows
Each step receives the previous output as context:
Step 1: "Write a sorting function"
Output: [function implementation]
Step 2 receives:
"Previous step output:
[function implementation]
Next task: Add comprehensive tests"
Step 3 receives:
"Previous steps output:
[function + tests]
Next task: Optimize performance"
Examples
Basic Development Chain
claude-flow stream-chain run \
"Write a user authentication function" \
"Add input validation and error handling" \
"Create unit tests with edge cases"
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.
- 1mo ago First seen · 564 lines · 18 tokens per session scan A a31c8126310b
stream-chain is a skill published in the GitHub repository ruvnet/ruflo (76,506 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 2,787 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to stream-chain, differing in 10 lines, and is treated as a copy.
Other skills, from other repositories
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows. Use when piping output between agents/tools as streaming JSON or building a sequential transform pipeline.
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows.