Beacon Threat Intelligence
Know what you're installing before you trust it.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
| Name | Risk |
|---|---|
| mcp-code-execution Routes multi-tool workflows through MCP servers for large datasets and pipelines | |
| response-compression Compresses verbose responses by removing filler and framing to save 200-400 tokens | |
| smart-sourcing Selects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when deciding whether a claim needs verification | |
| token-conservation Enforces token quota management at session start with conservation and compression checks. Use at the start of every session or before large context loads | |
| install-watchdog Installs egregore watchdog daemon via launchd or systemd for autonomous relaunching | |
| quality-gate Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates | |
| summon Autonomous orchestrator for manifest work items through the development lifecycle | |
| uninstall-watchdog Removes the egregore watchdog daemon and its associated files | |
| challenge Presents adaptive codebase challenge questions with multiple-choice and trace exercises | |
| curate Adds developer-authored annotations to the gauntlet knowledge base | |
| extract Builds the gauntlet knowledge base from AST extraction and AI enrichment | |
| gauntlet-curate Audits the DSA problem bank for coverage gaps and proposes new YAML entries | |
| graph-build Builds or updates the code knowledge graph via tree-sitter AST and SQLite | |
| graph-search Searches the code knowledge graph by function, class, or type using FTS5 full-text search | |
| onboard Guides a new developer through five staged challenge sets covering architecture, domain, patterns, and hardening | |
| rule-catalog Browse hookify rule catalog | |
| writing-rules Creates behavioral rules in markdown to block dangerous commands or restrict AI behavior | |
| catchup Summarizes recent git changes for context recovery after session breaks | |
| diff-analysis Analyzes changesets with risk scoring, categorization by type and impact, and release note preparation | |
| feature-review Scores backlog items with RICE/WSJF/Kano and files GitHub issues for top candidates | |
| justify Audits changes for additive bias and Iron Law compliance | |
| karpathy-principles Pre-implementation gate covering think-first, simplicity, surgical edits, and verifiable goals | |
| latent-space-engineering Shapes agent behavior via instruction framing and style transfer | |
| proof-of-work Enforces validation and evidence before claiming work complete. Use before declaring implementation done, creating a PR, or submitting deliverables for review | |
| review-core Provides review-workflow scaffolding for context, evidence, and output. Use at the start of any detailed review to ensure consistent, comparable findings | |
| rigorous-reasoning Applies anti-sycophancy checklist to override agreement bias | |
| scope-guard Scores feature worthiness and enforces branch-size limits against overengineering | |
| structured-output Formats review deliverables with consistent structure for comparable findings | |
| vow-enforcement Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers | |
| workflow-monitor Detects workflow failures and inefficient patterns then files GitHub issues | |
| additive-bias-defense Inverts burden of proof for code additions | |
| authentication-patterns Provides auth patterns for API keys, OAuth, and token management | |
| content-sanitization Provides sanitization guidelines for external content in skills and hooks | |
| damage-control Recovers broken agent state via crash recovery, context overflow, and merge conflict protocols | |
| deferred-capture Defines the contract for deferred-item capture across plugins | |
| document-conversion Converts documents and URLs to markdown via tiered fallback (MCP markitdown, native tools, user notice) | |
| error-patterns Provides error classification, recovery, and graceful-degradation patterns | |
| evaluation-framework Provides weighted scoring, rubrics, and decision-threshold patterns | |
| git-platform Detects git forge (GitHub/GitLab/Bitbucket) and maps CLI commands cross-platform | |
| markdown-formatting Enforces markdown line-wrap and structure rules for clean git diffs | |
| progressive-loading Implements hub-and-spoke lazy loading to minimize token usage in large skills | |
| pytest-config Provides standardized pytest config, reusable fixtures, and CI integration patterns | |
| quota-management Tracks quotas, monitors thresholds, and degrades gracefully for rate-limited APIs | |
| risk-classification Classifies agent tasks into 4 risk tiers (GREEN/YELLOW/RED/CRITICAL) | |
| sem-integration Provides sem semantic-diff detection, install-on-first-use, and fallback patterns | |
| service-registry Registers external services with health checks, central config, and unified execution | |
| stewardship Applies stewardship virtues (Care, Curiosity, Humility, Diligence) to plugin work | |
| storage-templates Provides templates and lifecycle patterns for storage and documentation systems | |
| supply-chain-advisory Audits dependency supply chains for bad versions, lockfile drift, and artifact integrity | |
| testing-quality-standards Defines testing quality metrics, coverage thresholds, and anti-patterns |
13,351–13,400 of 108,824