flow-nodes

flow-nodes is a skill for Claude Code from Cognigy/cognigy-plugin. It costs 68 tokens per session (6,834 once invoked), scanned A, original, MIT.

A guide for adding logic nodes to Cognigy conversation flows and rendering those flows as diagrams. Nodes are building blocks that perform steps inside an agent tool, such as handling an operation or condition.

In plain words
What is it for?
Use it to create tool branches, add custom logic, configure voice-session settings, or visualize a flow. It explains the tool-first process and the rules for where nodes may be placed.
Why use it?
It prevents placing logic where it can cause conversation loops or interfere with the agent's orchestration. It also defines the required order and placement of supported nodes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cognigy plugin — 16 skills, 2 agents shipped together

Good fit Use it to create tool branches, add custom logic, configure voice-session settings, or visualize a flow. It explains the tool-first process and the rules for where nodes may be placed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cognigy/cognigy-plugin/flow-nodes
Install

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.

Any agent
npx skills add Cognigy/cognigy-plugin --skill flow-nodes
Clone the repo
git clone --depth 1 https://github.com/Cognigy/cognigy-plugin

Made for: Claude Code.

Or install cognigy, the plugin that ships this one along with the rest of its 16 skills, 2 agents.

Wrote 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.

agentmods badge for flow-nodes

README.md
[![agentmods](https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/flow-nodes/github.svg)](https://agentmods.dev/skills/cognigy/cognigy-plugin/flow-nodes)
Your own site
<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/flow-nodes"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/flow-nodes/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.

agentmods 80×15 button for flow-nodes

Your own site · 80×15
<a href="https://agentmods.dev/skills/cognigy/cognigy-plugin/flow-nodes"><img src="https://agentmods.dev/badge/skills/cognigy/cognigy-plugin/flow-nodes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,834 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

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 →

  • medium Data Exfiltration · line 286
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 304
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.06834
Opus 5.5 $0.00027 $0.02734
Sonnet 5.5 $0.00014 $0.01367
Haiku 4.5 $0.00007 $0.00683

Measured 14d ago against content hash f49aee61638e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flow-nodes 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 14d 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.

plugin/skills/flow-nodes/SKILL.md · 582 lines

How it starts

The opening of the file, as written. The whole thing — 582 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flow Node Reference

Use manage_flow_nodes to add logic nodes inside tool branches only. Nodes are helpers for tools — they must ALWAYS be created under a tool, never as standalone pre-agent nodes.

CRITICAL: NEVER add nodes before the AI Agent Job node. Pre-agent nodes cause conversation loops and break the agent's ability to orchestrate. ALL logic — including authentication, data collection, greetings, and conditional behavior — must be implemented as agent tools.

Voice exception — Set Session Config: The one node that should run before the AI Agent node is a setSessionConfig (Set Session Config) node, and only in voice flows. It applies per-session speech settings (barge-in, ASR, STT/TTS, input timeouts) and must be the first node. The audit_voice_agent tool checks for this and can create it by prepending before the AI Agent node. Do not add any other pre-agent nodes.

LLM Prompt exception: llmPrompt (llmPromptV2) is a top-level raw LLM node for flows with no AI Agent node. Create it only when the user asks for an LLM Prompt node by name; otherwise use the AI Agent default. Reading or updating existing llmPromptV2 nodes is fine. See the LLM Prompt section.

Quick Start (tool-first workflow)

1. Create a tool — create_tool { aiAgentId, toolType: 'tool', name: 'Process Order', config: { toolId: 'process_order', description: 'Process a customer order' } } → returns toolNodeId
2. Get the flowId — from create_ai_agent response, or list_resources { resourceType: 'flow', projectId }
3. Add a node inside the tool — manage_flow_nodes { operation: 'create', flowId, parentNodeId: '<toolNodeId>', mode: 'appendChild', nodeType: 'code', label: 'Validate Order', config: { code: '...' } }
4. Add more nodes — manage_flow_nodes { operation: 'create', flowId, parentNodeId: '<previousNodeId>', mode: 'append', nodeType: 'say', label: 'Confirm', config: { text: 'Order processed!' } }
5. List all nodes — manage_flow_nodes { operation: 'list', flowId } (id, type, label, parentId, isDisabled when true — no config)
   Read one node with its config before editing — manage_flow_nodes { operation: 'get', flowId, nodeId: '<id>' }
6. Update a node — manage_flow_nodes { operation: 'update', flowId, nodeId: '<id>', config: { text: 'Updated!' } }
7. Delete a node — manage_flow_nodes { operation: 'delete', flowId, nodeId: '<id>' }

Read the full file on GitHub · 582 lines

Changes

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.

  1. 14d ago Changed · +2 lines · +16 tokens per session f49aee61638e
  2. 25d ago Changed · +53 lines 54cb1b308339
  3. 1mo ago Changed · +70 lines e5b7daa3b774
  4. 2mo ago First seen · 457 lines · 52 tokens per session scan A 39f9480638b4

Subscribe to this mod's changes

flow-nodes is a skill published in the GitHub repository Cognigy/cognigy-plugin (18 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 6,834 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 2026-08-31.

Related

flow-nodes compared with skills from other repositories

flow-nodes next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
flow-nodesCognigy/cognigy-pluginSkill18yesterdayMITA68Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code