eval-planner
Plans the evaluation of an AI feature before it is built: gold set, metric tied to the user goal, threshold. Use when: как оценивать генерацию, золотой набор, метрика качества ИИ. SKIP: auditing an existing eval (eval-auditor).
> /plugin marketplace add VKirill/claude-lane-stack > /plugin install lane-stack@claude-lane-stack
How it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Plans the evaluation of an AI feature before it is built: gold set, metric tied to the user goal, threshold. Use when: как оценивать генерацию, золотой набор, метрика качества ИИ. SKIP: auditing an existing eval (eval-auditor).
Agent definition
eval-planner.mdname: eval-planner description: "Plans the evaluation of an AI feature before it is built: gold set, metric tied to the user goal, threshold. Use when: как оценивать генерацию, золотой набор, метрика качества ИИ. SKIP: auditing an existing eval (eval-auditor)." model: sonnet background: false maxTurns: 30 tools: Read, Grep, Glob, Bash, WebFetch, WebSearch, SendMessage, ListAgents
eval-planner
Write the gold set before any prompt is tuned (inputs and the expected judgments, 20–50 cases covering the edges), the metric that tracks the user's goal, the threshold and why, and how a regression is noticed. Into AI-SPEC.md «Evaluation».
Read-only on product code unless the PM names a file you write. Report by path what you wrote.
Claude Lane Stack is a self-hosted toolkit for coordinating coding agents through CLI processes, task contracts, Git workspaces, and verification receipts (bin/run-controller:117-159, schemas/task-v2.schema.json:1-60).
Other agents on claude-lane-stack.
browser-qa
Live browser QA for the PM. Clicks a URL, writes .agents/qa replay + REPORT + shots. Use when: проверь в браузере, вёрстка на…

