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.
curl -O https://raw.githubusercontent.com/avabbbb/Flovart/main/.agents/skills/flovart/commands/workflow.mdgit clone --depth 1 https://github.com/avabbbb/FlovartWrote 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/avabbbb/flovart/workflow)<a href="https://agentmods.dev/commands/avabbbb/flovart/workflow"><img src="https://agentmods.dev/badge/commands/avabbbb/flovart/workflow/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/commands/avabbbb/flovart/workflow"><img src="https://agentmods.dev/badge/commands/avabbbb/flovart/workflow.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00702 |
| Opus 5.5 | $0.00000 | $0.00281 |
| Sonnet 5.5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
workflow 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow commands
Workflow is the current automated generation workspace. Table has no registered CLI commands yet.
Normal Agent flow starts from readiness and inspect:
npm run flovart:cli -- ensure --json
npm run flovart:cli -- workflow.inspect --json
Use command.list / command.schema only when a compatibility command is unfamiliar or the Registry contract has changed.
Typical graph operations:
npm run flovart:cli -- workflow.project.list --json
npm run flovart:cli -- workflow.project.create --title "产品视频" --json
npm run flovart:cli -- workflow.project.use --project-id <project-id> --json
npm run flovart:cli -- workflow.inspect --json
npm run flovart:cli -- workflow.selection.get --json
npm run flovart:cli -- workflow.node.create --type text --title "创作 Brief" --x 80 --y 120 --json
npm run flovart:cli -- workflow.node.create-connected --from-node-id <text-id> --type config --title "图片生成" --x 520 --y 120 --json
npm run flovart:cli -- workflow.node.run --node-id <config-id> --json
npm run flovart:cli -- workflow.node.run --node-ids <shot-1>,<shot-2>,<shot-3> --json
npm run flovart:cli -- workflow.node.stop --node-id <config-id> --json
The stable Agent surface is workflow.inspect, workflow.selection.get, workflow.apply, and workflow.node.run (with workflow.node.stop for cancellation). Granular workflow.node.*, connection, selection, and viewport commands remain compatibility adapters and route through the same visible Workflow contract.
To run several independent nodes at once, pass nodeIds (CLI: --node-ids a,b,c) instead of nodeId; the two are mutually exclusive. The batch needs one confirmation, runs every node in parallel through the same executor, checks expectedRevision once at the start, and returns { projectId, runs: [{ nodeId, ok, runId?, artifact?, error? }], failed }. It errors only when every node fails; rerun only the failed nodes.
Node types are image, text, video, audio, and config. Read returned IDs directly, then use workflow.inspect to verify the redacted graph. Never use removed canvas.* or element.* commands.
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.
- 6d ago Changed · +3 lines 0abd6b715631
- 1mo ago Changed · +16 lines 0f89806d7b3d
- 1mo ago Changed b69bf572d614
- 2mo ago Changed · +3 lines 9f98100742d3
- 2mo ago First seen · 28 lines · 0 tokens per session scan A dad565577ac6
workflow is a command published in the GitHub repository avabbbb/Flovart (145 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 702 tokens. 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 2026-08-30.
workflow compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| workflowavabbbb/Flovart | Command | 145 | today | MIT | A | 0 | Claude Code |
| brand-setupindranilbanerjee/socialforge | Command | 42 | 8d ago | MIT | A | 25 | Claude Code |
| statusindranilbanerjee/socialforge | Command | 42 | 8d ago | MIT | A | 18 | Claude Code |
| check-approvalsindranilbanerjee/socialforge | Command | 42 | 8d ago | MIT | A | 16 | Claude Code |
| switch-brandindranilbanerjee/socialforge | Command | 42 | 8d ago | MIT | A | 17 | Claude Code |
| new-monthindranilbanerjee/socialforge | Command | 42 | 8d ago | MIT | A | 35 | Claude Code |
| reviewindranilbanerjee/socialforge | Command | 42 | 8d ago | MIT | A | 22 | Claude Code |