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.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 | $0.00000 | $0.00788 |
| Opus 5 | $0.00000 | $0.00394 |
| Sonnet 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 8d 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.
- 8d 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 yesterday), 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
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
intent-recognition
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 other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.
config-evals
Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…
one-off-operations
Handles one-off operations: the request is a concrete effect that happens once — export or copy data somewhere, a migration, a backfill, a cleanup — with no trigger, schedule, or reuse intent. The workflow is the vehicle, not the deliverable. Users rarely say "one-off"; infer it from the task's shape. Load before…
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.