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 filestack/filestack-claude-plugin --skill filestack-workflow-designgit clone --depth 1 https://github.com/filestack/filestack-claude-pluginWrote 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/filestack/filestack-claude-plugin/filestack-workflow-design)<a href="https://agentmods.dev/skills/filestack/filestack-claude-plugin/filestack-workflow-design"><img src="https://agentmods.dev/badge/skills/filestack/filestack-claude-plugin/filestack-workflow-design/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/filestack/filestack-claude-plugin/filestack-workflow-design"><img src="https://agentmods.dev/badge/skills/filestack/filestack-claude-plugin/filestack-workflow-design.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 | $0.00110 | $0.01628 |
| Opus 5 | $0.00055 | $0.00814 |
| Sonnet 5 | $0.00022 | $0.00326 |
| Haiku 4.5 | $0.00011 | $0.00163 |
Grade A, and why
filestack-workflow-design 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 12d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filestack Workflows
Workflows are Filestack's primary asynchronous processing story — multi-step pipelines that run on every file upload (or on demand) and emit fs.workflow webhook events when complete.
Use this skill when the user wants to:
- Run a series of operations on each upload (resize → SFW check → store)
- Branch processing based on file type, MIME, intelligence result
- Use virus detection, video intelligence, or document workflows (these are workflow-only — not available as direct CDN tasks)
- Trigger an existing workflow from code
When to choose a Workflow vs direct tasks
Use direct CDN tasks (filestack_transform_url, filestack_transform_apply, filestack_analyze) when:
- The operation is synchronous and returns a transformed file or JSON
- One or two transforms in a chain
- The result is fetched on demand (CDN-cached)
Use a Workflow when:
- ≥3 steps with conditional branches
- Background processing — caller doesn't wait
- One of these workflow-only tasks is needed:
virus_detectionvideo_sfw,video_tagging(video intelligence)phishing_detection
- Multiple outputs need to be stored to different locations
- Caller wants webhook-driven completion via
fs.workflowevent
Designing a Workflow
Workflows are designed in the Filestack Developer Portal (https://dev.filestack.com/ → Workflows). They cannot be designed via API — only invoked via API once created.
A workflow has:
- Tasks: nodes that perform an action (transform, intelligence, store, webhook, etc.)
- Conditions: branches based on the previous task's output (e.g.
sfw == true) - A trigger: either explicit (via
filestack_run_workflowor pickerstoreTo.workflows), or implicit (on upload)
Walk the user through the Portal flow
- Sign in at https://dev.filestack.com/
- Open the target app → Workflows in left nav
- Click Create Workflow
- Drag tasks from the left panel onto the canvas. Tasks include:
- Transformation: resize, crop, output, watermark, etc.
- Intelligence: sfw, tags, caption, ocr, virus_detection, doc_detection, image_sentiment
- Storage: store (S3/GCS/Azure/Rackspace)
- Webhook: POST result to a customer URL
- Conditional: branch on previous task output
- Connect tasks with edges (right-handle → left-handle)
- Save — the workflow gets a UUID
- Copy the UUID into your application code or use it with
filestack_run_workflow
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.
- 12d ago First seen · 172 lines · 110 tokens per session scan A 3ff4fb7d4428
filestack-workflow-design is a skill published in the GitHub repository filestack/filestack-claude-plugin (3 stars, last pushed yesterday), licensed MIT. It adds 110 tokens to every session and 1,628 once invoked, about $0.0006 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…