agentmods.dev

Flovart: Skill for Claude Code

.agents/skills/open-flovart/SKILL.md

open-flovart is a skill for Claude Code, Codex from avabbbb/Flovart. It costs 34 tokens per session (349 once invoked), scanned A, original, MIT.

A workflow for opening Flovart and preparing the current visual workflow for control by command-line or coding-agent tools.

In plain words
What is it for?
Use it when an agent needs to operate a visible Flovart workflow.
Why use it?
It connects the current workflow so the agent can inspect it, apply changes, or run individual workflow nodes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex; mentions OpenCode.

This is avabbbb/Flovart's own configuration. It tells Claude Code and Codex how to work on Flovart itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Flovart configures →

not rated 145repo +2 changed today A scan 34 tokens original MIT
View source ↗ avabbbb/Flovart avabbbb.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to avabbbb/Flovart. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/avabbbb/Flovart/main/.agents/skills/open-flovart/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/avabbbb/Flovart

Made for: Claude Code, Codex.

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 open-flovart

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/avabbbb/flovart/open-flovart"><img src="https://agentmods.dev/badge/skills/avabbbb/flovart/open-flovart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 349 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.
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 $0.00034 $0.00349
Opus 5.5 $0.00014 $0.00140
Sonnet 5.5 $0.00007 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured today against content hash dfdafe52aaae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

open-flovart 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 today.

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.

.agents/skills/open-flovart/SKILL.md · 29 lines

What it actually says

Open Flovart

This is the entry point only. All Workflow work follows the flovart Skill; read it before the first write.

  1. Run flovart ensure --json (in this source checkout, when the packaged command is not installed: npm run flovart:cli -- ensure --json). Never fall back to npx flovart-cli.
  2. Continue only when it returns ok: true and state: "ready". Otherwise tell the user the public state and error action it returned and stop. Do not guess a port, read local config, or open a URL by hand.
  3. Confirm you are on the user's canvas: flovart status --json, then flovart workflow.inspect --agent-identity <host> --json with your host's identity (codex, claude-code, opencode, workbuddy). Use the same identity on every later write; without it writes fail with AGENT_HOST_REQUIRED.
  4. Continue with "Prepare for this job" in the flovart Skill.

Never open the WebUI in your own or a headless browser, read Agent configuration or private Runtime files, call a Provider directly, write browser storage, or configure an MCP server yourself. The optional MCP projection is described in the flovart Skill's references/hosts.md.

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. today Changed · -24 lines · +1 tokens per session dfdafe52aaae
  2. 1mo ago Changed · -40 lines · -23 tokens per session scan B → A 7db395f45d98
  3. 2mo ago Changed · +23 lines d1742a9d411a
  4. 2mo ago First seen · 70 lines · 56 tokens per session scan B c9053b93268f

Subscribe to this mod's changes

open-flovart is a skill published in the GitHub repository avabbbb/Flovart (145 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 349 once invoked, about $0.0001 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 2026-09-03.

Building agentsagentic-aiai-agentai-imageai-videoaigcbyok
Related

open-flovart compared with skills from other repositories

open-flovart next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
open-flovartavabbbb/FlovartSkill145todayMITA34Claude Code, Codex
create-shortDojoCodingLabs/remotion-superpowersSkill1578d agoMITA58Claude Code
generate-clipDojoCodingLabs/remotion-superpowersSkill1578d agoMITA32Claude Code
transcribeDojoCodingLabs/remotion-superpowersSkill1578d agoMITA75Claude Code
add-captionsDojoCodingLabs/remotion-superpowersSkill1578d agoMITA89Claude Code
add-musicDojoCodingLabs/remotion-superpowersSkill1578d agoMITA54Claude Code
generate-imageDojoCodingLabs/remotion-superpowersSkill1578d agoMITA39Claude Code