Review a design artifact (spec, plan, PR packet) with fresh, memoryless subagents. Invoke when the user asks — "goldfish this", "fresh eyes", "tear this apart" — or after suggesting it for a spec that has grown load-bearing and the user agrees.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Intent: an artifact written in a context-rich session always reads complete to that session. The test is whether a reader with zero session context can act on it.
A goldfish is a fresh subagent given only the artifact plus what any fresh context can legitimately reach: the repo, the wiki, linked sources. Session context is out of bounds — don't paste in your intent or the answer you hope for.
Facets — a menu, not a mandate; pick by stakes. Run the deleter before critic and readiness: optimizing a thing that shouldn't exist is the classic mistake.
Sandbox (non-negotiable): reviewers never mutate a checkout they don't own. Read-only subagents by default; a reviewer that must build or run gets its own disposable worktree.
Exit: findings filtered by you — a finding survives if acting on it would change what gets built or what risk is visible. Weigh findings toward the next action and the direction's validity; defects in far-future steps are usually premature — the user works iteratively, and those steps will be re-planned before they're reached. Done when a fresh reader can act on the artifact without rediscovering intent. If substantive findings persist after a couple of rounds, the artifact needs rethinking, not more polish.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Records hypotheses, evidence and decisions when proposing, running or evaluating forecast experiments, including backtests and feature or model comparisons. Excludes routine tests and unchanged forecast operation.
The English summary is being prepared. Showing the original description.
Diagnose GitHub CLI hiccups caused by Codex sandbox constraints; not a general GitHub workflow.
The English summary is being prepared. Showing the original description.
Interrogate the user before implementing a non-trivial or ambiguous ask, converging on shared intent. Use when the user says "grill me", when an ask admits multiple interpretations, or before any sizable piece of work whose intent isn't fully clear.
The English summary is being prepared. Showing the original description.
Launches and supervises long-running commands — solves, workflows, downloads, builds — detached with a log, PID and exit sentinel, then tells stuck from slow and kills verifiably. Use before running anything that may exceed a minute, for nohup or background launches, and when a run hangs, shows no output, or timed out.
The English summary is being prepared. Showing the original description.
Build and maintain a persistent, LLM-maintained markdown wiki following Andrej Karpathy's LLM Wiki pattern — the agent incrementally compiles raw sources into an interlinked knowledge base instead of re-deriving answers from scratch. Use this whenever the user wants to ingest a source (an article, paper, transcript, chapter, meeting notes), file knowledge or conversation findings into the wiki, query the accumulated knowledge base, lint or health-check the wiki, or mentions "the wiki", "knowledge base", "ingest this", "file this", "what do we know about X", or accumulating notes on a topic over time — even if they don't say "LLM Wiki" explicitly.
The English summary is being prepared. Showing the original description.
Guides writing and editing Mermaid diagrams in GitHub-rendered Markdown so they remain readable across themes and preserve placeholder labels.
The English summary is being prepared. Showing the original description.