agents-course Plugin
Tools from the agents course: audit your context, write done as a script, bootstrap your eval suite, and a loop critic agent.
So installierst du das agents-course Plugin
Führe beide Befehle in Claude Code aus. Der erste fügt den Marketplace einmalig hinzu; der zweite installiert das Plugin.
/plugin marketplace add undefined-ui/second-brain-os
/plugin install agents-course@second-brain-osWas ist in agents-course enthalten
6 Teile wurden aus den eigenen Dateien des Plugins gelesen.
Agents 1
Aufrufen als @agent-agents-course:name- @agent-agents-course:loop-critic
>-
Skills 5
Claude lädt es, wenn die Aufgabe passt- context-audit
Audit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to audit, review or fix their agent's context, prompt caching, token spend per turn, or CLAUDE.md / AGENTS.md layout. Read-only: reports findings and a fix list, changes nothing. Do NOT use for writing evals (evals-bootstrap) or for loop design (goal-test).
- evals-bootstrap
Scaffold a first eval suite for an agent: mine real failures into cases, write behavioural checks over traces, and generate the runner. Use when the user wants evals, regression tests for an agent, a golden set, or asks how to know a prompt/model change did not break things. Do NOT use for a single task's done-check (goal-test) or for auditing context (context-audit).
- gate-check
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).
- goal-test
Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent. Use when the user wants to run an agent in a loop, asks how to know when an agent task is finished, or says a goal like "improve X" needs to become checkable. Do NOT use for building eval suites over many cases — that is evals-bootstrap.
- harness-audit
Audit an agent's harness against the four rings: containment, guides, sensors, permissions. Use when the user asks whether their agent setup is safe, wants a review of sandboxing / permissions / hooks / AGENTS.md guardrails, or asks what a bad session could break. Read-only: reports the blast radius and a hardening list, changes nothing. Do NOT use for context layout (context-audit) or cost routing (gate-check).
Verwendung von agents-course in Claude Code
Frage nach einem Agent per Name:
@agent-agents-course:loop-criticSkills benötigen keinen Command. Claude liest sie, wenn deine Anfrage dem entspricht, was sie beschreiben.
Aktualisieren, deaktivieren oder entfernen
- Plugin aktualisieren (shell)
- claude plugin update agents-course@second-brain-os
- marketplace aktualisieren
- /plugin marketplace update second-brain-os
- Vorerst deaktivieren
- /plugin disable agents-course@second-brain-os
- Entfernen
- /plugin uninstall agents-course@second-brain-os
Skills in agents-course
- context-auditundefined-ui/second-brain-os
Audit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to audit, review or fix their agent's context, prompt caching, token spend per turn, or CLAUDE.md / AGENTS.md layout. Read-only: reports findings and a fix list, changes nothing. Do NOT use for writing evals (evals-bootstrap) or for loop design (goal-test).
1576Stars - evals-bootstrapundefined-ui/second-brain-os
Scaffold a first eval suite for an agent: mine real failures into cases, write behavioural checks over traces, and generate the runner. Use when the user wants evals, regression tests for an agent, a golden set, or asks how to know a prompt/model change did not break things. Do NOT use for a single task's done-check (goal-test) or for auditing context (context-audit).
1576Stars - gate-checkundefined-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).
1576Stars - goal-testundefined-ui/second-brain-os
Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent. Use when the user wants to run an agent in a loop, asks how to know when an agent task is finished, or says a goal like "improve X" needs to become checkable. Do NOT use for building eval suites over many cases — that is evals-bootstrap.
1576Stars - harness-auditundefined-ui/second-brain-os
Audit an agent's harness against the four rings: containment, guides, sensors, permissions. Use when the user asks whether their agent setup is safe, wants a review of sandboxing / permissions / hooks / AGENTS.md guardrails, or asks what a bad session could break. Read-only: reports the blast radius and a hardening list, changes nothing. Do NOT use for context layout (context-audit) or cost routing (gate-check).
1576Stars
Fragen zum agents-course Plugin
Wie installiere ich das agents-course Plugin?
Führe in Claude Code /plugin marketplace add undefined-ui/second-brain-os aus, dann /plugin install agents-course@second-brain-os.
Was enthält das agents-course Plugin?
agents-course bündelt 1 Agent, 5 Skills.
Welche Agents sind bei agents-course dabei?
loop-critic. Rufe einen mit @agent-agents-course:loop-critic auf.
Wie aktualisiere oder entferne ich das agents-course Plugin?
Aktualisiere es mit claude plugin update agents-course@second-brain-os in deiner shell oder über den Installed-Tab von /plugin. Entferne es mit /plugin uninstall agents-course@second-brain-os.
Unter welcher Lizenz steht das agents-course Plugin?
MIT, wie im Manifest des Plugins angegeben.