Bitterbot-AI/protocol-quiet-in-groups
skills/protocol-quiet-in-groups/SKILL.md
Enforces PROTOCOLS.md "stay quiet in group chats" deterministically. Blocks outbound messages in Discord/Telegram/Slack/etc group channels when the bot was not @mentioned and recently spoke.
$ install --global
skillsauthnpx skillsauth add Bitterbot-AI/bitterbot-desktop protocol-quiet-in-groupsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 23, 2026, 2:33 AM133.8s1 file scanned
SKILL.md
- name:
- protocol-quiet-in-groups
- description:
- Enforces PROTOCOLS.md "stay quiet in group chats" deterministically. Blocks outbound messages in Discord/Telegram/Slack/etc group channels when the bot was not @mentioned and recently spoke.
- tier:
- executable
- always:
- true
- - id:
- protocol-quiet-in-groups:default
- builtin:
- true
- activates_on:
- send_message-shaped tools on group channels
- intervention:
- block
protocol-quiet-in-groups
In group channels (Discord, Telegram, Slack, WhatsApp groups, Google Chat rooms, IRC), the agent should usually observe more than it speaks. PROTOCOLS.md captures this as a "speak ~1 in 5 turns" rule, but as a prompt-level instruction it is fragile under high-engagement conditions.
This interceptor makes the rule deterministic. If the agent is in a group channel AND was not @mentioned in the last 3 turns AND has spoken within the past minute (or is in the first few turns of joining), it silently blocks the next outbound message.
What you'll see
In group chats you will notice the agent participating less often than it would otherwise. When it is directly addressed (@bitterbot or @bot), the block is bypassed and the agent responds normally.
Implementation
Built-in interceptor protocol-quiet-in-groups:default lives in src/agents/skills/builtin-interceptors/protocol-quiet-in-groups.ts. High priority (90) so it short-circuits ahead of recall/calibration when it fires. Up to 50 fires per session.
Related Skills
Bitterbot-AI/route-by-query-shape
development
VerifiedTrustedCommunity
When the agent calls memory_search with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledge_graph backend where it will actually find the answer.
1,881SKILL.mdUpdated May 23, 2026
Bitterbot-AI/recall-before-claim
testing
VerifiedTrustedCommunity
Forces a memory_search before the agent sends a message containing a factual assertion that has not yet been grounded this turn. Closes the citation-rate gap from ~40% to ~90%+.
1,881SKILL.mdUpdated May 23, 2026
Bitterbot-AI/calibrate-claim-confidence
development
VerifiedTrustedCommunity
When the agent's epistemic state (GCCRF) indicates low empowerment and falling certainty, hedges out confident absolutes ("definitely", "always", "100%") in outgoing messages.
1,881SKILL.mdUpdated May 23, 2026
Bitterbot-AI/notte
tools
VerifiedTrustedCommunity
Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI. Turns any browser flow into a deterministic Bitterbot-callable endpoint, ideal for crystallized skills + dream-engine cron schedules.
1,369SKILL.mdUpdated May 6, 2026