sno-ai/sno-station-skills / skills/T-delegation-and-work-orders/pl/skills/pl
pl
FlaggedMANUAL-ONLY — load solely when the human owner types `/pl`, uses `$pl`, or asks you to act as the Project Lead (PL). Supervise one project lane and its executor agents. A charter or dispatch means: you are an EXECUTOR, not the PL.
scripts/on-station-proof.t
View on GitHub#!/usr/bin/env bash
set -Eeuo pipefail
# The launcher needs systemd-run before it renders the card, so off Linux it stops at its
# dependency check.
if [[ "$(uname -s)" != Linux ]]; then
printf 'ok # SKIP (Linux only): absent fence is reported as absent in the generated Reach card\n'
exit 0
fi
script_dir="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
cos_claim=""
for d in "$script_dir/../../../../cos/skills/cos/scripts" "$script_dir/../../cos/scripts"; do
[[ -f "$d/cos-claim.sh" ]] && { cos_claim="$d/cos-claim.sh"; break; }
done
[[ -n "$cos_claim" ]] || { echo 'SKIP: cos skill not installed'; exit 0; }
root="$(mktemp -d)"
trap 'rm -r -- "$root"' EXIT
host="$(hostname)"
export HOME="$root/home" SNO_REACH_ROOT="$root/reach"
export PL_REGISTRY="$root/registry.tsv"
export SNO_PL_REGISTRY="$PL_REGISTRY"
mkdir -p "$HOME" "$root/repo/ai-doc" "$root/bin"
"$cos_claim" open repo >"$root/open.out"
printf 'mission: no-fence · operation: open · success-test: card rendered · evidence: card · owner: pending · parent: none · predecessor: none\n' >"$root/dispatch.md"
printf '#!/usr/bin/env bash\nexit 1\n' >"$root/bin/tmux"
printf '#!/usr/bin/env bash\nexit 0\n' >"$root/bin/codex"
chmod +x "$root/bin/tmux" "$root/bin/codex"
rc=0
PATH="$root/bin:$PATH" bash "$script_dir/spawn-exec.sh" \
--journey j-no-fence --repo "$root/repo" --budget-h 0.1 \
--dispatch "$root/dispatch.md" --class closure \
--callsign proof --addr "executor.no-fence@$host" \
--log "$root/executor.log" >"$root/spawn.out" 2>"$root/spawn.err" || rc=$?
[[ "$rc" == 1 ]]
sno reach lint "$root/executor.log.on-station.eml" >/dev/null
grep -Fxq 'X-Work: j-no-fence' "$root/executor.log.on-station.eml"
grep -Fq 'measured-at-spawn: fence-exists=no fence-bytes=0 fence-sha256=none' \
"$root/executor.log.on-station.eml"
grep -Fq 'observed-by-executor: sent separately' "$root/executor.log.on-station.eml"
printf 'ok - absent fence is reported as absent in the generated Reach card\n'
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: 323k | 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: 323k | 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: 323k | Updated | Claude CodeCodex | Verified | Install |