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 The-AI-Directory-Company/agents-and-skills --skill automation-workflow-designgit clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/automation-workflow-design)<a href="https://agentmods.dev/skills/the-ai-directory-company/agents-and-skills/automation-workflow-design"><img src="https://agentmods.dev/badge/skills/the-ai-directory-company/agents-and-skills/automation-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/the-ai-directory-company/agents-and-skills/automation-workflow-design"><img src="https://agentmods.dev/badge/skills/the-ai-directory-company/agents-and-skills/automation-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 | $0.00049 | $0.01483 |
| Opus 5.5 | $0.00020 | $0.00593 |
| Sonnet 5.5 | $0.00010 | $0.00297 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
automation-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 1mo 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automation Workflow Design
Before you start
Gather the following from the user:
- What is the trigger? (Webhook, schedule, database event, form submission, file upload)
- What is the desired outcome? (Record created, notification sent, file transformed, data synced)
- Which platform? (n8n, Make, Zapier, Power Automate, or platform-agnostic)
- What systems are involved? (APIs, databases, SaaS tools, file storage)
- What is the expected volume? (Runs per hour/day, payload sizes)
- What happens on failure? (Retry, alert, fallback, manual queue)
If the user says "automate this process," push back: "Which trigger starts it, what systems are involved, and what should happen when a step fails?"
Workflow mapping procedure
Step 1: Define the trigger
Identify the event that starts the workflow. Document:
- Trigger type: Webhook, polling, cron schedule, event subscription
- Payload shape: Fields available from the trigger (provide a sample JSON)
- Frequency: Expected invocations per time window
- Idempotency: Whether duplicate triggers are possible and how to handle them
Step 2: Map the action chain
For each step after the trigger, document in sequence:
Step [N]: [Action name]
Platform node: [Specific node/module name for the target platform]
Input: [Which fields from previous steps]
Transform: [Any data mapping or formatting]
Output: [Fields produced for downstream steps]
Error behavior: [Retry N times / skip / halt workflow]
Group related steps into logical stages: Intake, Processing, Output, Notification.
Step 3: Add conditional branches
For each decision point:
- State the condition as a boolean expression using available fields
- Document the true-path and false-path step sequences
- Identify whether branches rejoin or terminate independently
Step 4: Design error handling
For every step that calls an external service:
- Retry strategy: Count, backoff interval, max wait
- Timeout: Maximum seconds before treating as failure
- Dead letter handling: Where failed items go (error queue, log table, notification)
- Circuit breaker: If failure rate exceeds threshold, pause workflow and alert
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 156 lines · 49 tokens per session scan A 6f130eb6830a
automation-workflow-design is a skill published in the GitHub repository The-AI-Directory-Company/agents-and-skills (4 stars, last pushed 7mo ago), licensed MIT. It adds 49 tokens to every session and 1,483 once invoked, about $0.0002 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.
Other skills, from other repositories
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
low-code-platforms
Low-code and internal tool platforms including Retool, Supabase, Appsmith, Tooljet, n8n, and Zapier. Use when building admin panels, internal tools, workflow automations, or integrating low-code platforms with custom code.
one-on-one-prep
Deep-dive preparation for 1:1 meetings with direct reports. Surfaces recent work, wins, friction, wellbeing signals, and development goal progress, anchored in the org's performance framework, organizational values, and management best practices. Produces a prep sheet with suggested conversation topics, not a script.
priority-planner
Helps managers cut through noise and identify their highest-leverage actions for the day or week. Aggregates signals from calendar, triage, team context, and OKRs/goals. Presents a suggested focus list grouped by urgency, importance, and investment. The manager reviews and adjusts. Supports effective execution and…
meeting-prep
Comprehensive pre-meeting briefing that gathers all relevant context from Slack, email, Google Docs, Notion, and calendar. Produces a structured prep document so the manager walks into every meeting fully prepared. Supports thorough meeting preparation.
triage-messages
Batch-processes Slack messages and emails to surface what needs the manager's attention, categorised by urgency and type. Designed for batch-responder managers who do Slack sweeps rather than staying in reactive mode. Supports effective communication and responsiveness. Never drafts replies, only surfaces and…