Heyvhuang/copybook-skills / standalone/coordinator/skills/coordinator
coordinator
FlaggedCoordinate an ongoing software delivery run when the user assigns this session the coordinator role or asks it to manage worker handoffs, gates, release approvals and progress. Use when starting, supervising or resuming that run, including a run with one active lane. Lanes run as Herdr workers (parallel-goal-fleet) on Claude or Codex, from whichever harness coordinates; T3 Code child tasks are the fallback. Do not start a coordinator run for discussion, a read-only review of the workflow, a standalone quick second opinion or an ordinary single-session edit.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.8 KB |
| references/example-run.md | markdown | 3.4 KB |
| references/herdr.md | markdown | 7.7 KB |
| references/lessons.md | markdown | 6.9 KB |
| references/models.md | markdown | 4.9 KB |
| references/pipeline.md | markdown | 6.1 KB |
| references/situations.md | markdown | 3.4 KB |
| references/t3.md | markdown | 4.9 KB |
| scripts/gemini.mjsexecutable | script | 2.3 KB |
| scripts/heavy.shexecutable | script | 829 B |
| scripts/status.shexecutable | script | 2.0 KB |
| scripts/watch-ready.shexecutable | script | 2.0 KB |
| templates/lane-brief.md | markdown | 1.5 KB |
| templates/release-packet.md | markdown | 1.4 KB |
| templates/run-record.md | markdown | 1.2 KB |
| templates/ship.md | markdown | 1.1 KB |
scripts/status.sh
View on GitHub#!/bin/bash
# status.sh: a live progress board for a coordinator run. Read-only; redraws every 20 s until you press Ctrl-C.
# Usage: status.sh <run-dir> <herdr-session> [repo-path]
# Shows the repo's remote main (when a repo path is given), each Herdr worker's state, the READY lines in the
# run's hand-overs and reviews, the lines under "## Done" in gate/queue.md, and the run record's last six log lines.
# Open it in a terminal tab the user can see. It reads files and asks git and Herdr; it changes nothing.
RUN=${1:?usage: status.sh <run-dir> <herdr-session> [repo-path]}
SESSION=${2:?usage: status.sh <run-dir> <herdr-session> [repo-path]}
REPO=$3
while :; do
clear 2>/dev/null || printf '\033[2J\033[H'
echo "$(basename "$RUN") · $SESSION $(date '+%H:%M:%S') (refreshes every 20 s, Ctrl-C to stop)"
if [ -n "$REPO" ]; then
echo "Remote main: $(git -C "$REPO" ls-remote origin refs/heads/main 2>/dev/null | cut -c1-9)"
fi
echo
echo "== Workers =="
# Drop HERDR_SESSION, as parallel-goal-fleet's references/herdr.md does, so the board reads the run's session
# even when it runs inside another Herdr pane.
env -u HERDR_SESSION herdr --session "$SESSION" agent list 2>/dev/null | python3 -c '
import json, sys
try:
agents = json.load(sys.stdin).get("result", {}).get("agents", [])
except Exception:
agents = []
for a in agents:
print(" %-14s %-8s %s" % (a.get("name", "?"), a.get("agent_status", "?"), a.get("pane_id", "")))
if not agents:
print(" (the Herdr session is not running, or has no workers)")
'
echo
echo "== Handed back =="
grep -h -E '^[-*>` ]*[A-Z0-9-]+-READY( |$)' "$RUN"/handover-*.md "$RUN"/review-*.md 2>/dev/null | sed -E 's/^[-*>` ]*/ /' | sort -u
if [ -f "$RUN/gate/queue.md" ]; then
echo
echo "== Gate =="
awk '/^## /{d=($0 ~ /^## Done[[:space:]]*$/); next} d && NF' "$RUN/gate/queue.md" | sed 's/^/ /'
fi
echo
echo "== Run record, last 6 lines =="
grep '^- ' "$RUN/STATE.md" 2>/dev/null | tail -6 | cut -c1-160 | sed 's/^/ /'
sleep 20
done
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |