From CORAL
Launches, monitors, and manages CORAL agent experiments via CLI commands like start, status, log, and stop. Use when running or steering agent evaluations.
How this skill is triggered — by the user, by Claude, or both
Slash command
/coral:running-coral-experimentsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You drive a run with five verbs: **start → status → log/show → resume → stop**. Everything else is a flag on those or a deeper topic in the references. Prefer `coral <cmd> --help` over guessing flags.
You drive a run with five verbs: start → status → log/show → resume → stop. Everything else is a flag on those or a deeper topic in the references. Prefer coral <cmd> --help over guessing flags.
Prereq: a task (task.yaml + seed/ + grader package) that passes coral validate .. No task yet → that's the creating-a-coral-task skill. Each runtime CLI must be installed and authenticated → the setting-up-coral skill.
coral start -c task.yaml # auto-tmux session
coral start -c task.yaml agents.count=4 agents.model=opus # dotlist overrides (no quotes needed)
coral start -c task.yaml run.verbose=true run.ui=true # verbose logs + web dashboard
coral start -c task.yaml run.session=local # foreground, no tmux
key.subkey=value) beat task.yaml for this run only — the clean way to sweep count/model without editing the file.run.session: tmux (default, detachable) · local (foreground) · docker.results/<task-slug>/<timestamp>/; agents work in isolated git worktrees and the grader daemon scores their commits.coral status # agent health + leaderboard snapshot (the quick pulse)
coral runs # active runs across tasks; --all includes finished
coral ui --port 8420 # web dashboard: live leaderboard, logs, DAG
coral status answers "who's alive, how many evals, current best". If it looks healthy but scores never move, jump to budget classes + troubleshooting in references/scaling-and-ops.md.
coral log # top 20 real attempts by score
coral log -n 5 --recent # most recent instead of best
coral log --search "kernel" --agent agent-1
coral log --class grader_error # surface crashing graders (first stop when unhealthy)
coral show <hash> # one attempt: score, explanation, files changed
coral show <hash> --diff # full diff — see exactly what the leader did
<hash> comes from coral log/coral status. By default coral log hides tune and grader_error attempts; --all shows them, --class {real|tune|grader_error} filters to one. What the classes mean → references/scaling-and-ops.md.
coral resume # resume latest run, sessions restored
coral resume -i "Try greedy approaches first" # inject guidance agents read next loop
coral resume --from <hash> -i "Continue this fork" # reset an agent to an attempt, then steer
coral export <hash> -b winning-idea # export an attempt's commit as a git branch
resume -i is how you nudge a run without restarting from scratch (stop → resume with an instruction). --from forks a promising line that later regressed. You can also retune the reflection cadence — coral heartbeat set/remove/reset — to make agents reflect less, pivot sooner, etc. Both topics, with worked examples: references/steering.md.
coral stop # stop the current/latest run (picker if several)
coral stop --all # stop every active run
Stopping leaves all results, notes, and the leaderboard on disk — coral resume later, or just inspect with coral log/coral show.
coral validate . # grader scores the seed (once)
coral start -c task.yaml agents.count=2 # launch
coral status # ... check periodically
coral log -n 5 --recent # see what agents are trying
coral show <best-hash> --diff # inspect the leader
coral resume -i "Focus on the inner loop" # steer if they plateau
coral stop # done
Note: coral eval / diff / revert / checkout / wait are agent-side commands run inside a worktree during a run — agents already know them from the generated CORAL.md. As the operator you rarely touch them; you drive the verbs above. Full CLI reference: https://docs.coralxyz.com/cli/reference
npx claudepluginhub human-agent-society/coral --plugin coralOnboards users to CORAL, an infrastructure for autonomous coding agents that parallelize code optimization via a seed repo and grader. Covers installation, CLI setup, and workspace convention.
Runs the hive experiment loop for autonomous iteration on shared tasks in hive directories. Use to run experiments, submit results, or join agent swarms.
Guides the full ADK agent development lifecycle: scaffold, build, evaluate, deploy, publish, and observe using agents-cli on Google Cloud.