Skills for Real Engineers. Straight from my .agents directory.
gate-check
Agent skill fromundefined-ui/second-brain-os
Find the decisions in a pipeline that do not need the expensive model and propose the gate for each: a rule, a classic classifier, or a small model, with fail-closed routing. Use when the user asks to cut model costs or latency, says the big model handles everything, or wants a triage / routing / filter layer in front of an agent. Analysis plus an optional baseline scaffold. Do NOT use for auditing context layout (context-audit) or for building eval suites (evals-bootstrap).
How to install gate-check
npx skills add undefined-ui/second-brain-os# or add only this skill to Claude Code: copy the folder
plugins/agents-course/skills/gate-check/
# into
~/.claude/skills/gate-check/ (all projects)
.claude/skills/gate-check/ (one project)
1# Find the gates23Theory: [Cheap decisions](https://secondbrainos.dev/#/read/course-3-gate/cheap-decisions)4and [Gate practice](https://secondbrainos.dev/#/read/course-3-gate/gate-practice).5An agent does two kinds of work: it writes, which needs a big model, and it6decides — is this spam, which queue, does this need a person — which is a7bounded question the answer to which comes from a set you already know.8A gate is a cheap decision layer that sorts the stream so the expensive9model only sees the items that actually need judgement.1011## Workflow12131. **Map the decisions.** Read the pipeline's entry points and prompts and14 list every decision made before or during a model call: classification,15 routing, filtering, yes/no triage, priority, language, "is this even for16 us". Ignore the writing — only bounded decisions with a known label set.172. **Count what each costs today.** For each decision currently made by the18 big model: calls per day if known, tokens per call, and what a wrong19 answer costs. A decision worth one bit that burns a frontier call is the20 headline finding.213. **Propose the cheapest gate that can hold it**, in rising order of cost:22 - a **rule** — regex, allowlist, header check: free, instant, blind to23 anything unanticipated; always the first layer, never the last24 - a **classic classifier** — logistic regression or similar over simple25 features, trained on a few hundred labelled examples: milliseconds,26…
Excerpt shown under the repository's MIT license.
More skills in second-brain-os
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
