Cognitive Stop
Termina i watcher cognitivi in background (inhibit, error, cleanup) lanciati da /cognitive-spawn. Invoca a fine sessione di lavoro intensiva, prima di un compact, o quando vuoi disattivare il monitoring. Triggers: "/cognitive-stop", "ferma watchers", "spegni monitoring cognitivo", "stop sentinels".
Install
$ agentstack add skill-tommasobbianchi-claude-cognitive-skills-cognitive-stop ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Cognitive-Stop
Spegne i daemon dei watcher cognitivi.
~/.claude/cognitive-watchers/spawn.sh stopTermina i PID registrati in ~/.claude-cognitive-alerts/.pids/, lascia intatti:
- alert già consegnati in
*.alert.delivered.(audit trail) - log dei daemon in
~/.claude-cognitive-alerts/.logs/ - il hook PostToolUse registrato in
~/.claude/settings.json(resta attivo, ma senza watcher non produce alert)
Per disinstallare completamente (rimuovere anche il hook), vedi il README del repo.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: tommasobbianchi
- Source: tommasobbianchi/claude-cognitive-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.