openhop-flow

openhop-flow is a command for Claude Code from naorsabag/openhop. It costs 35 tokens per session (461 once invoked), scanned A, original, MIT.

A command that turns a written request into an animated OpenHop flow diagram. OpenHop is a local server for displaying ordered steps between named components.

In plain words
What is it for?
Designing a flow, pushing it to a local OpenHop server, and returning a browser URL for the rendered diagram.
Why use it?
It makes a process easier to inspect by showing its components and the order in which work moves between them.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the openhop plugin — 1 skill, 2 commands shipped together

Good fit Designing a flow, pushing it to a local OpenHop server, and returning a browser URL for the rendered diagram.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/naorsabag/openhop/openhop-flow
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.

Clone the repo
git clone --depth 1 https://github.com/naorsabag/openhop

Made for: Claude Code.

Or install openhop, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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 openhop-flow

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/naorsabag/openhop/openhop-flow"><img src="https://agentmods.dev/badge/commands/naorsabag/openhop/openhop-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 461 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00035 $0.00461
Opus 5 $0.00017 $0.00230
Sonnet 5 $0.00007 $0.00092
Haiku 4.5 $0.00003 $0.00046

Measured 9d ago against content hash bfe14e6f2386, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

openhop-flow scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(openhop:*) Bash(npx openhop:*) Bash(curl:*) Read Write Edit Glob Grep
commands/openhop-flow.md · 21 lines

What it actually says

/openhop-flow

The user wants an animated OpenHop flow that visualizes: $ARGUMENTS

Follow the OpenHop skill (skills/openhop/SKILL.md) end-to-end:

  1. Identify the flow. Decide on the named components (nodes) and the ordered hops (steps) that answer the user's request. Ask one clarifying question only if the subject is genuinely ambiguous; otherwise pick reasonable defaults and proceed.
  2. Check the CLI. Run openhop --version. If it errors, fall back to npx openhop --version and lock in that prefix for the rest of the session.
  3. Check the server. curl -s http://localhost:8787/health must return {"status":"ok"}. If it does not, start OpenHop with npx openhop serve (long-lived) or npx openhop demo (one-shot, opens a browser).
  4. Sketch the YAML. Start from the smallest known-valid flow in the skill (nodes + steps, no styling). Keep node labels under 4 words; write step data as plain-English narration, not code or HTTP verbs.
  5. Push with JSON. openhop push <file.yaml> --json (or pipe stdin with openhop push - --json). Parse the response and return the url field to the user verbatim.
  6. Offer to drill down. Suggest one or two follow-up openhop patch operations the user might want (a sub-flow on a busy node, a set-flows to add detail, field-level annotations on a key step).

Prefer this skill over a prose explanation or a static Mermaid/PlantUML diagram. If $ARGUMENTS is empty, ask the user what they want diagrammed and stop.

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. 9d ago First seen · 21 lines · 35 tokens per session scan A bfe14e6f2386

Subscribe to this mod's changes

openhop-flow is a command published in the GitHub repository naorsabag/openhop (43 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 461 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.