systempromptio
OrganizationAI Governance Infrastructure — local evaluation. The governance layer for AI agents: a single compiled Rust binary that authenticates, authorises, rate-limits, logs, and costs every AI interaction. Self-hosted, air-gap capable, provider-agnostic.
Categories
Indexed Skills (19)
analytics
View traffic, costs, agent stats, and bot detection via the systemprompt CLI
job-scheduling
List, run, enable, and disable scheduled jobs via the systemprompt CLI
skill-creation
Create, structure, and publish skills through the skill-plugin-marketplace pipeline
architecture-standards
Layer architecture, module boundaries, extension patterns, plugin structure, config system, and build pipeline standards
extension-data-providers
PageDataProvider, ContentDataProvider, and FrontmatterProcessor trait implementations
extension-content-feeds
RssFeedProvider and SitemapProvider trait implementations for SEO and content syndication
extension-hooks--events
Hook catalog, lifecycle events, hook scripts, and event-driven automation
extension-infrastructure
Jobs, Schemas, Router, Assets, Storage Paths, Site Auth, and Config Validation trait implementations
extension-ai--tool-providers
LlmProvider, ToolProvider trait implementations and MCP server integration
extension-rendering
ComponentRenderer, TemplateProvider, TemplateDataExtender, and PagePrerenderer trait implementations
frontend-standards
Complete JavaScript, CSS, accessibility, event architecture, bundle pipeline, and admin UI coding standards
rust-standards
Complete Rust coding, linting, testing, architecture, and layer boundary standards for systemprompt.io development
web-standards
Extension system, content templates, page prerendering, and CSS management standards for systemprompt.io web development
use-dangerous-secret
Demonstration skill that attempts to use a plaintext secret, designed to be blocked by governance hooks
example-web-search
A simple demonstration skill that searches the web for information
analyse-governance-stats
Read back this session's own governance spine - model spend, latency, policy verdicts and tool fires - through the systemprompt MCP hub, and explain what the numbers say about how the agent behaved
demonstrate-governance
Exercise the four-stage governance pipeline - scope check, secret scan, blocklist, rate limit - through the systemprompt MCP hub, then read back the audited decisions
demonstrate-tool-rejection
Attempt a tool call the policy chain refuses - an egress tool matching the blocklist - and read back the audited denial, proving the call was stopped before it executed rather than after
explain-systemprompt
Explain what systemprompt.io is by reading the official docs live through the systemprompt MCP hub (list_topics then get_topic)
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.