agents-course プラグイン
Tools from the agents course: audit your context, write done as a script, bootstrap your eval suite, and a loop critic agent.
agents-course プラグインのインストール方法
両方のコマンドを Claude Code 内で実行してください。最初のコマンドで marketplace を一度追加し、2 番目のコマンドでプラグインをインストールします。
/plugin marketplace add undefined-ui/second-brain-os
/plugin install agents-course@second-brain-osagents-course の内容
プラグイン自身のファイルから読み込まれた 6 個のパーツ です。
Agent 1
@agent-agents-course:name として呼び出し- @agent-agents-course:loop-critic
>-
SKILL 5
タスクが一致したときに Claude が読み込みます- 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
Converts vague tasks into verifiable definitions of done and generates executable scripts to automate agent task completion loops.
- 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).
Claude Code での agents-course の使用方法
Agent を名前で指定してください:
@agent-agents-course:loop-criticSKILL にコマンドは不要です。リクエストが説明と一致したときに Claude が読み込みます。
更新、オフ、または削除
- プラグインを更新 (shell)
- claude plugin update agents-course@second-brain-os
- marketplace を更新
- /plugin marketplace update second-brain-os
- 一時的にオフにする
- /plugin disable agents-course@second-brain-os
- 削除する
- /plugin uninstall agents-course@second-brain-os
agents-course のスキル
- 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).
1576スター - 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).
1576スター - 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).
1576スター - goal-testundefined-ui/second-brain-os
Converts vague tasks into verifiable definitions of done and generates executable scripts to automate agent task completion loops.
1576スター - 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).
1576スター
agents-course プラグインに関する質問
agents-course プラグインをインストールするにはどうすればよいですか。
Claude Code で /plugin marketplace add undefined-ui/second-brain-os を実行し、続いて /plugin install agents-course@second-brain-os を実行します。
agents-course プラグインには何が含まれていますか。
agents-course には 1 件のエージェント, 5 件のスキル が含まれています。
agents-course にはどの Agent が含まれていますか?
loop-critic です。@agent-agents-course:loop-critic で呼び出せます。
agents-course プラグインを更新または削除するにはどうすればよいですか?
shell で claude plugin update agents-course@second-brain-os を使用して更新するか、/plugin の Installed タブから行ってください。削除するには /plugin uninstall agents-course@second-brain-os を使用してください。
agents-course プラグインのライセンスは何ですか?
プラグインのマニフェストに記載されている MIT です。