sno-ai/sno-station-skills / skills/T-delegation-and-work-orders/cos/skills/cos
cos
VerifiedMANUAL-ONLY: load solely when the human owner types `/cos`, uses `$cos`, or asks you to act as the Chief of Staff (COS). The COS is the one agent the owner talks to; it coordinates the owner and the per-project Project Leads (PLs). A task card, charter, or dispatch makes you an executor, not COS.
| File | Kind | Size |
|---|---|---|
| LEARNING.md | markdown | 6.1 KB |
| SKILL.md | skill md | 76.0 KB |
| references/card-template.md | markdown | 10.9 KB |
| references/digest-template.md | markdown | 4.9 KB |
| references/owner-profile.md | markdown | 5.3 KB |
| references/pocket-card.md | markdown | 1.6 KB |
| scripts/cos-claim.shexecutable | script | 31.4 KB |
| scripts/cos-claim.texecutable | script | 13.4 KB |
| scripts/cos-roster.shexecutable | script | 40.5 KB |
| scripts/cos-roster.texecutable | script | 7.6 KB |
| scripts/cos-screen.shexecutable | script | 4.8 KB |
| scripts/cos-screen.texecutable | script | 2.5 KB |
| scripts/cos-since.shexecutable | script | 3.6 KB |
| scripts/exec-sentinel.shexecutable | script | 6.1 KB |
| scripts/exec-sentinel.t | other | 2.4 KB |
| scripts/exec-tree-check.shexecutable | script | 2.6 KB |
| scripts/selftest/run-selftest.shexecutable | script | 204 B |
| scripts/selftest/text-check.py | script | 1.0 KB |
scripts/cos-screen.t
View on GitHub#!/usr/bin/env bash
# Real tmux on a private server; `sno` (seat list) and `orca` (the desktop app's CLI)
# are the only fakes, because both are external programs a test cannot start.
set -Eeuo pipefail
script_dir="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
screen="${COS_SCREEN_UNDER_TEST:-$script_dir/cos-screen.sh}"
root="$(mktemp -d)"
trap 'env -u TMUX TMUX_TMPDIR="$root/tmux" tmux kill-server >/dev/null 2>&1 || true; rm -r -- "$root"' EXIT
mkdir -p "$root/bin" "$root/tmux"
export TMUX_TMPDIR="$root/tmux" SNO_PL_REGISTRY="$root/registry.tsv" PATH="$root/bin:$PATH"
unset TMUX
cat >"$root/bin/sno" <<'EOF'
#!/usr/bin/env bash
printf '%s\n' \
'{"address":"pl.tmuxrepo@h","channel":"tmux","handle":"tmux-abc123:cosscreen","state":"live"}' \
'{"address":"pl.orcarepo@h","channel":"orca","handle":"term_fake","state":"live"}'
EOF
# Stream mode (no --screen) returns repaint fragments, as the real Orca does.
cat >"$root/bin/orca" <<'EOF'
#!/usr/bin/env bash
[[ "$*" == *"--screen"* ]] || { echo '{"ok":true,"result":{"terminal":{"tail":["cclclecleaclear"]}}}'; exit 0; }
[[ "$*" == *"term_fake"* ]] || { echo '{"ok":false,"error":{"code":"terminal_handle_stale"}}'; exit 1; }
echo '{"ok":true,"result":{"terminal":{"tail":["PL is waiting on review","",""]}}}'
EOF
chmod +x "$root/bin/sno" "$root/bin/orca"
printf 'home_repo\tlane\treach_address\theartbeat_name\truntime\towning_cos\tstate\tnote\n' >"$SNO_PL_REGISTRY"
printf 'orcarepo\tall\tpl.orcarepo@h\tx\tcodex\tcos/x\tRUN\t-\n' >>"$SNO_PL_REGISTRY"
tmux new-session -d -s cosscreen "printf 'TMUX-SCREEN-MARKER\n'; sleep 60"
for _ in 1 2 3 4 5 6 7 8 9 10; do
tmux capture-pane -p -t =cosscreen: | grep -q TMUX-SCREEN-MARKER && break
sleep 0.3
done
printf 'TAP version 13\n'
out="$(bash "$screen" pl.tmuxrepo@h)"
if grep -q 'TMUX-SCREEN-MARKER' <<<"$out"; then
printf 'ok 1 - tmux seat prints the live pane\n'
else
printf 'not ok 1 - tmux seat prints the live pane\n# %s\n' "$out"; exit 1
fi
out="$(bash "$screen" orcarepo)"
if grep -q 'PL is waiting on review' <<<"$out" && ! grep -q cclclecleaclear <<<"$out"; then
printf 'ok 2 - repo name resolves to the Orca seat and reads the rendered screen\n'
else
printf 'not ok 2 - Orca screen read\n# %s\n' "$out"; exit 1
fi
rc=0
out="$(bash "$screen" no-such-repo)" || rc=$?
if [[ "$rc" == 3 ]] && grep -q '^NO WINDOW' <<<"$out"; then
printf 'ok 3 - no window is reported as NO WINDOW with exit 3\n'
else
printf 'not ok 3 - no window (rc=%s)\n# %s\n' "$rc" "$out"; exit 1
fi
printf '1..3\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: 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 |