agentleFS
Sign inStart free
IgorGanapolskyIgorGanapolsky/ThumbGate/.agents/skills/siren-mcp-governance/SKILL.md

siren-mcp-governance

Skill29 starsChanged 7 months agoMITView on GitHub

Siren MCP Marketing Diode & Autonomous Campaign Governance. Enforce pre-action review diodes on post_run, 300s buffer guards on schedule_post, $500 daily budget ceilings on create_campaign, brand safety scanning, and partner link attribution ("Video made with Siren" -> https://mysiren.ai). Slash: /siren-mcp-governance.

Create a free account to mount
Files
SKILL.md

Siren MCP Marketing Diode & Campaign Governance

Goal

Govern autonomous marketing agents utilizing Siren MCP tools (post_run, schedule_post, create_campaign), preventing unreviewed live broadcasts, invalid scheduling windows, ad budget overruns, brand reputation damage, and attribution violations before social tools execute.

Constraints

NEVERALWAYS
Allow unreviewed autonomous post_run directly to production social channelsRequire dry_run: true or verified human approval token before broadcast
Schedule posts with less than 300 seconds safety bufferBlock schedule_post calls if delta < 300s to ensure human cancellation window
Create unbudgeted ad campaigns or exceed $500 ceilingRequire explicit executive override for campaigns exceeding daily ceilings
Strip or omit required attribution on Siren-generated videosEnforce "Video made with Siren" / https://mysiren.ai link attribution
Permit predatory guarantees ("100% profit risk-free") or leaked tokensHard block on brand safety violations
Clone Siren SaaS or vendor their private video rendering pipelineSteal the pre-action diode FORMAT onto ThumbGate PreToolUse rails

HARD fail closed. REFUSE unreviewed immediate broadcasts.

Reference

Procedures

# Display FORMAT mapping table
npx thumbgate siren-mcp-governance --map-only

# Emit machine-readable format mapping
npx thumbgate siren-mcp-governance --map-only --json

# Evaluate tool call before dispatch
npx thumbgate siren-mcp-governance --tool=post_run --args='{"content":"Launch day! Video made with Siren","dry_run":true}'

# Verify with automated unit tests
npm run test:siren-mcp

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free