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 Threat-Vector-Security/guardian-agent --skill automation-buildergit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWrote 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/threat-vector-security/guardian-agent/automation-builder)<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/automation-builder"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/automation-builder/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/threat-vector-security/guardian-agent/automation-builder"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/automation-builder.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 | $0.00788 |
| Opus 5.5 | $0.00000 | $0.00315 |
| Sonnet 5.5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
automation-builder 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automation Builder
Use this when the user wants a recurring check, scheduled task, monitoring workflow, or reusable playbook.
Workflow
- Clarify the purpose.
- What should the automation check or do?
- What target, tool arguments, and schedule are needed?
- What output should count as success, failure, or escalation?
- Check for an existing workflow or task first.
- Use
workflow_listandtask_listto avoid duplicates.
- Use
- Choose the simplest workflow shape.
- Single-tool workflow for one check or action.
- Sequential workflow when later steps depend on earlier output.
- Parallel workflow only when checks are independent.
- Instruction step only for summarization or prioritization, not for hidden tool execution.
- Scheduled assistant task when the assistant should wake up, inspect the environment with its normal skills/tools, and report back.
- Choose one shape unless the user explicitly wants both. Do not create both a scheduled playbook and a scheduled assistant task for the same job by default.
- Keep monitoring automations read-only by default.
- Prefer status, list, fetch, and diagnostic tools unless the user explicitly wants a mutating action.
- Create or update the playbook with
workflow_upsert. - If recurring execution is needed, add or update the schedule with
task_createortask_update.- For scheduled assistant turns, use
task_createwithtype: "agent",targetset to an agent id (ordefault),prompt, and a cron expression. - For a one-shot scheduled action, set
runOnce: trueso the task disables itself after the first execution. - Scheduled tasks are considered approved once created or updated, so the later cron execution should not pause for the same approval again.
- For scheduled assistant turns, use
- Verify before claiming success.
- Use
workflow_runwithdryRun: truewhen useful. - For scheduled automations, confirm both the workflow and the linked task exist.
- Use
Practical Rules
- One workflow should have one clear purpose.
- Prefer explicit tool args over vague instruction text.
- Use sequential mode by default unless parallelism clearly helps.
- Instruction steps are text-only. If the automation needs the assistant to choose tools or read skills at runtime, use an
agenttask instead of an instruction step. - Cron schedules are minute-granularity. If the user asks for sub-minute intervals, explain that limitation.
- When the automation is domain-specific, read the matching domain skill too, such as
cloud-operations,google-workspace,security-triage, orsecurity-response-automationfor alert-driven defensive workflows.
What ships with it
2 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 · 57 lines · 0 tokens per session scan A f76d967c98a6
automation-builder is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (13 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 788 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.
Other skills, from other repositories
intent-recognition
Load before you build any new kept workflow or Agent. It decides which one to build, or what to ask first. Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the…
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and workflowbuildercreatetasks silence rules. Load whenever any of these tags appear or after calling workflowbuildercreatetasks.
suggest-automations
Offer the three most common automations for a user as a single-choice card, from your own knowledge of their team and their apps, then build the one they choose once they confirm, or offer more. The system preloads it on onboarding threads, where the opening card already asked the user about themselves. Use it on…
workflow-builder
Load before calling workflowbuilderbuildworkflow. Use for single-workflow work: new one-off workflows, existing-workflow edits, verification repairs, and workflow-local data tables. For any other new workflow, load intent-recognition first when it is listed. Write or edit a workspace source file, run workflow-sdk…
nx-plugin-for-aws
Scaffold and build cloud-native applications on AWS using @aws/nx-plugin generators. Use when the user wants to create workspaces, generate projects, or scaffold infrastructure with the Nx Plugin for AWS.