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.
See how to installReview the instructions the agent will receive before you install.
Preflight every fallible precondition before the expensive phase: credentials that expire, connectivity, config validation (snakemake -n), disk space.
nohup … & shares the tool shell's group. Launch as nohup perl -MPOSIX -e 'POSIX::setsid(); exec @ARGV' bash -c '<cmd>; echo "EXIT $?"' </dev/null >> <logdir>/<name>.log 2>&1 & echo $! > <logdir>/<name>.pid, then, after a second, confirm ps -o pgid= -p $(cat <name>.pid) prints the PID.tail/head. Log to a file, read the tail on demand.Traceback|Error|Exiting|EXIT|Killed.Check: process alive (pgrep -f); CPU time accruing (ps -o time -p <pid>, two samples 20 s apart — not %CPU); the tool's own artifacts growing (fresh mtimes); lsof -p <pid> — a lone TCP connection in CLOSE_WAIT with flat CPU is a dead client. Flat on all → stuck. Then kill.
Kill the launched process group, not a command-line pattern: kill -- -$(cat <name>.pid), wait, pgrep -g $(cat <name>.pid) shows nothing; then remove stale locks (Snakemake: .snakemake/locks/) and relaunch. A kill is done when the process tree is confirmed gone.
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, selecting, 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.
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.
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.
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.