메뉴
Launch a local live web dashboard to watch the current project's Leopold run — status, cost meters (context/subagents/forks), event feed, decisions, and a Stop button. Local-only (127.0.0.1), zero dependencies.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Phase 1 of Leopold. A structured debate that captures the mission and your decision-making, then writes the brief (MISSION, CHARTER, GUARDRAILS, PLAN) that the autonomous run executes.
Compile a Leopold brief into a dynamic workflow and run it. The plan lives in code instead of one growing context window, every item gets an independent adversarial review, and git stays locked — nothing is committed. The workflow is resumable and shows up in /workflows.
Control plane for the global prompt enhancer: status, on/off, preview a prompt against the gate, and the learn loop that mines your enhancement ledger into proposed prompt-profile rules. Never edits PROMPT-PROFILE.md itself — you review and apply.
The self-improving charter. Mines past Leopold decisions, session corrections, and git history for recurring judgment calls, skeptic-verifies each candidate, and proposes charter amendments. Never edits CHARTER.md itself — you review and apply.
Phase 2 of Leopold. Enters autonomous mode and conducts Claude Code through the plan, deciding from the charter instead of asking, with git locked. The Stop hook keeps it going until the plan is done or a stop condition fires.
Triage a backlog (GitHub issues, bug reports, any queue) as a dynamic workflow: quarantined classifiers over untrusted content, dedupe against what's tracked, severity-ranked report, fix plans for quick wins. Pair with /loop to run it continuously.
| name | leopold-watch |
| version | 0.1.0 |
| description | Launch a local live web dashboard to watch the current project's Leopold run — status, cost meters (context/subagents/forks), event feed, decisions, and a Stop button. Local-only (127.0.0.1), zero dependencies. |
| allowed-tools | ["Bash"] |
| triggers | ["leopold watch","watch the run","open the dashboard"] |
Start the local live dashboard for this project's Leopold run and give the user the URL.
It only reads .leopold/ (state, plan, decisions, events) and serves on loopback;
nothing leaves the machine. The one action it offers is a Stop button, which touches
.leopold/STOP — the same kill switch as /leopold-stop.
Run this (idempotent — if it is already up, just report the URL):
WATCH="$HOME/.claude/leopold/scripts/leopold-watch.py"; [ -f "$WATCH" ] || WATCH="scripts/leopold-watch.py"
PORT="${LEOPOLD_WATCH_PORT:-4179}"
if curl -sf "http://127.0.0.1:$PORT/api/state" >/dev/null 2>&1; then
echo "Dashboard already running -> http://127.0.0.1:$PORT"
else
nohup python3 "$WATCH" --project "$(pwd)" --port "$PORT" >/tmp/leopold-watch.log 2>&1 &
sleep 1
if curl -sf "http://127.0.0.1:$PORT/api/state" >/dev/null 2>&1; then
echo "Dashboard started -> http://127.0.0.1:$PORT (pid $!)"
else
echo "Failed to start; last log lines:"; tail -3 /tmp/leopold-watch.log
fi
fi
Then tell the user, briefly:
/leopold-run); otherwise it says
"no active run" and updates the moment one starts.pkill -f leopold-watch.py. It also runs via make watch
or, from the npm package, npx leopold-driver watch./leopold-run loop applies at
the next turn boundary (a workflow node's steer becomes a directive for the next
resume). Git stays locked throughout: steering never commits.Do not do anything else. Start it, report the URL, stop.