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 agentmods add skills/gaelic-ghost/socket/design-agent-automation-workflownpx skills add gaelic-ghost/socket --skill design-agent-automation-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/design-agent-automation-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/design-agent-automation-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/design-agent-automation-workflow.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 | $0.00089 | $0.01571 |
| Opus 5 | $0.00044 | $0.00785 |
| Sonnet 5 | $0.00018 | $0.00314 |
| Haiku 4.5 | $0.00009 | $0.00157 |
Grade A, and why
design-agent-automation-workflow 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 4d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Agent Automation Workflow
Design agent and automation workflows before implementation.
This skill is a framework-neutral planning surface. It helps choose the smallest defensible automation shape, name the safety and state boundaries, decide whether the task is fit for full automation or needs exact escalation gates, and produce a scaffold another stack-owned skill or implementation pass can use.
Inputs
- Required: the automation goal or workflow idea
- Useful: target repository, cadence, write surface, expected outputs, full-auto eligibility, escalation points, state needs, retry needs, observability needs, and preferred runtime constraints
- Optional: known framework preference, deployment target, language stack, or existing scheduler/service
Workflow
- Restate the intended real-world outcome and the smallest useful first run.
- Decide whether automation is appropriate yet. Prefer safe full automation when bounded scope, validation, rollback or draft behavior, and side-effect controls make it reasonably reliable. Use human review only for the exact decision that cannot be made safe through narrower scope, deterministic checks, retries, rollback, sandboxing, or an orchestration layer.
- Classify the best-fit surface:
- Codex app automation
codex execor Codex GitHub Action- Codex subagent fan-out
- OpenAI Agents SDK service
- LangGraph graph
- Hermes-specific workflow
- full-auto execution
- auto-with-escalation
- no automation yet
- Name the practical reason for the choice: schedule, isolation, state, approvals, retries, observability, deployment, or integration with an existing runtime.
- Identify ownership:
- prefer existing agent skills, plugins, scripts, and official workflow surfaces before adding new automation code, so business process knowledge has one maintained source of truth
- prompt or skill-only work stays in this planning skill
- Python implementation belongs in
python-skills - web or TypeScript implementation belongs in the Build Web Apps plugin or the repo's owning JavaScript/TypeScript workflow
- Swift or Apple-platform implementation belongs in Apple/Swift-owned skills
- Hermes-specific work belongs in Hermes docs or a Hermes-owned skill if one exists later
- When the request compares agent frameworks or local-first agent development,
use
references/local-agent-frameworks.mdto separate the orchestration framework from the inference server, model capability, document/RAG, and integration choices. Keep the recommendation tied to a concrete workflow; do not recommend a framework merely because it is popular. - Produce a scaffold with the chosen surface, guardrails, validation plan, output contract, and next implementation handoff.
- Link official docs for every framework or runtime named in the recommendation.
What ships with it
4 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.
- 4d ago First seen · 146 lines · 89 tokens per session scan A f3e3afe65677
design-agent-automation-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,571 once invoked, about $0.0004 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
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
implement-factory
Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.
scenario-planning
Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…
ai-research-analyst
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a…