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 gaelic-ghost/socket --skill design-agent-eval-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-eval-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/design-agent-eval-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/design-agent-eval-workflow/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/gaelic-ghost/socket/design-agent-eval-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/design-agent-eval-workflow.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 | $0.00068 | $0.01267 |
| Opus 5.5 | $0.00027 | $0.00507 |
| Sonnet 5.5 | $0.00014 | $0.00253 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
design-agent-eval-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 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Agent Eval Workflow
Design evaluation workflows for agent, skill, prompt, and automation behavior.
This skill is a framework-neutral eval planning surface. It helps define what good behavior means, how to measure it repeatably, which tasks can safely run fully automatically, and where escalation remains necessary because safety cannot be engineered into the workflow with reasonable confidence.
Inputs
- Required: the agent, skill, prompt, automation, or workflow to evaluate
- Useful: target runtime, task examples, expected outputs, failure modes, write surface, external services touched, acceptable risk, and current validation commands
- Optional: preferred eval runner, existing case format, model/provider constraints, budget, cadence, and reporting destination
Workflow
- Restate the behavior under evaluation and the real decision the eval should support.
- Define the automation target:
full-auto: safe to run without human approval when it passes objective gatesauto-with-escalation: runs automatically but stops on bounded ambiguity, failed checks, secret exposure, destructive writes, or external side effectshuman-review: requires review because the task cannot yet be made safe enough through scope, validation, sandboxing, rollback, or orchestrationmanual-only-for-now: behavior is too underspecified or high-risk for a useful eval-backed automation claim
- Build the case set:
- happy path
- realistic messy input
- regression examples from past failures
- refusal or stop conditions
- tool, filesystem, network, or credential boundary cases
- full-auto eligibility cases when automation is the goal
- Choose graders:
- deterministic assertions for structure, file changes, commands, outputs, and policy boundaries
- snapshot review only when stable text shape matters
- model grading only for judgment that cannot be reduced to deterministic checks, with explicit rubrics and sampled audit review
- Set pass thresholds, stop conditions, and escalation rules.
- Choose the run surface:
- local script or
uv run pytestfor repo-local skill and prompt evals codex execor Codex GitHub Action for repeatable repo tasks- OpenAI Agents SDK tracing/evals when application code owns tools, handoffs, guardrails, and traces
- LangGraph evaluation or LangSmith-style tracing when a stateful graph owns transitions, persistence, resume behavior, or graph-level observability
- a stack-owned test runner when the workflow belongs to a narrower plugin
- local script or
- Produce a scaffold with cases, grader shape, thresholds, reporting, automation eligibility, and implementation handoff.
- Link official docs for every framework, runtime, or eval surface named.
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 · 121 lines · 68 tokens per session scan A 1f61f5add3fd
design-agent-eval-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,267 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
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…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.
turbo-pipeline
Use when the user wants a feature built end to end after answering one round of questions and then being left alone — "turbo", "ask me once, then just build it", "I'll answer up front, don't come back to me", "decide the rest yourself". Not for a run that wants a spec approval and no tests (superb:fast-pipeline), one…
pipeline-auto
Use when the user wants a substantial feature taken from idea through implementation in one run with as little interruption as possible ("just build it", "don't keep asking me"), or when controlling such a run and a worker question, quorum responses, the drift budget, a human decision, a review class or a completeness…
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
fast-pipeline
Use when the user wants a feature built quickly with low token cost and few interruptions, approves a spec once, and says no automated tests should be written because they will test it manually — "fast pipeline", "go fast, no tests, I'll test it myself", "don't keep asking me". Not for a run that should write or keep…