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 arjunprabhulal/devops-skills --skill workflow-automationgit clone --depth 1 https://github.com/arjunprabhulal/devops-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/arjunprabhulal/devops-skills/workflow-automation)<a href="https://agentmods.dev/skills/arjunprabhulal/devops-skills/workflow-automation"><img src="https://agentmods.dev/badge/skills/arjunprabhulal/devops-skills/workflow-automation.svg" alt="Measured on agentmods" 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 | $0.00116 | $0.01316 |
| Opus 5 | $0.00058 | $0.00658 |
| Sonnet 5 | $0.00023 | $0.00263 |
| Haiku 4.5 | $0.00012 | $0.00132 |
Grade A, and why
workflow-automation 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Automation
An operational workflow is rarely one action — it's a chain: detect a condition, decide, act, verify, notify. Most automation failures happen not because a single step was wrong, but because the chain assumed the happy path and had no plan for a step failing halfway through, running twice, or firing on a burst of duplicate events.
Treat a workflow as a state machine you can inspect mid-flight, not a script that either finishes or silently dies. The workflow's job is to reach a known-good end state, not to execute a fixed sequence of commands.
1. Trigger on events, not on polling when you can help it
Polling wastes cycles and adds latency proportional to the poll interval; it also invites a race where two pollers both see the same unhandled condition. An event-driven trigger — a webhook, a queue message, a Kubernetes watch — reacts immediately and, if built on an at-least-once delivery system, gives you an explicit signal to deduplicate against instead of an implicit one you have to infer from timing.
- Prefer push over pull — a webhook or queue beats a cron job polling an API for changes.
- Carry a unique event ID through the whole chain so downstream steps can deduplicate.
- Treat "at least once" delivery as the default assumption, not an edge case to handle later.
Done when: the workflow's trigger is the event itself, not a poll loop guessing at freshness.
2. Make every step idempotent before you make it automatic
An automated step will eventually run twice — a retried webhook, a redelivered queue message, an operator re-running by hand after an ambiguous failure. If "create the resource" isn't safe to run twice, the second run either errors confusingly or creates a duplicate. Idempotency turns retries from a hazard into a free safety net.
- Key every action on a stable identifier (an ID, a desired-state hash) so re-running converges instead of duplicating.
- Check current state before acting — "ensure X exists" instead of "create X."
- Make the check and the act atomic where the underlying system allows it, so two concurrent runs don't both pass the check and both act.
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 First seen · 104 lines · 116 tokens per session scan A f7fcd506226f
workflow-automation is a skill published in the GitHub repository arjunprabhulal/devops-skills (3 stars, last pushed 12d ago), licensed MIT. It adds 116 tokens to every session and 1,316 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
google-mobile-ads-android-migrate-to-next-gen
Migrates Android applications from the old, legacy Google Mobile Ads (GMA) SDK (com.google.android.gms:play-services-ads) to the new GMA Next-Gen SDK (com.google.android.libraries.ads.mobile.sdk:ads-mobile-sdk). Provides comprehensive mapping tables for imports, classes, and method signatures to help determine…
agent-platform-inference
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-deploy
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a…
agent-platform-eval-flywheel
Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on…