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 |
|---|---|
| usage-logging Implements structured usage logging and audit trails for cost and session tracking | |
| utility Scores agent actions by expected gain, cost, uncertainty, and redundancy | |
| digital-garden-cultivator Manages digital garden notes, link structures, and health metrics | |
| knowledge-intake Processes external resources into stored knowledge with quality scoring and routing | |
| knowledge-locator Searches and navigates stored knowledge in memory palaces | |
| memory-palace-architect Designs memory palace structures with spatial layouts and domain organization | |
| palace-diagram Generates Mermaid and ASCII diagrams of palace structure, knowledge topology, and synapse connectivity | |
| review-chamber Captures and retrieves PR-review findings in memory palaces. Use after PR review to store architectural decisions, patterns, and standards for future reference | |
| session-palace-builder Builds session-scoped temporary memory palaces for extended conversations | |
| dora-metrics Computes DORA delivery-performance metrics from git and GitHub API | |
| github-initiative-pulse Generates markdown digests and CSV exports for GitHub initiative health | |
| release-health-gates Standardizes release approvals with GitHub-aware checklists and deployment gates. Use before releasing to production to verify all gates pass | |
| setup Provisions the oracle ML inference daemon with onnxruntime via uv | |
| python-async Async Python patterns via asyncio and aiohttp for I/O-bound concurrency | |
| python-packaging Python package creation and PyPI distribution via pyproject.toml and entry points | |
| python-performance Profiles Python code for performance bottlenecks and memory issues | |
| python-testing Python testing patterns with pytest, fixtures, TDD, mocking, async and integration tests | |
| api-review Evaluates API surface design, consistency, and exemplar alignment | |
| architecture-review Assesses architecture decisions, ADR compliance, and coupling | |
| blast-radius Analyzes code change impact with risk scoring and affected-node mapping. Use before merging to understand what a change touches and what lacks test coverage | |
| bug-review Hunts bugs with evidence trails | |
| code-refinement Improves code quality across duplication, efficiency, and architectural fit | |
| harden Applies NIST/CWE security hardening to Python and Rust code | |
| makefile-review Audits Makefiles for build correctness, portability, and recipe duplication | |
| math-review Verifies math-heavy code for algorithmic correctness and numerical stability | |
| performance-review Detects time and space complexity hotspots via AST scan | |
| rust-review Audits Rust code for unsafe blocks, ownership issues, and Cargo dependency risks | |
| safety-critical-patterns Applies NASA Power of 10 rules for safety-critical verifiable code | |
| shell-review Audits shell scripts for correctness, portability, and common pitfalls | |
| test-review Evaluates test suites for coverage gaps, TDD/BDD compliance, and anti-patterns | |
| tiered-audit Runs a three-tier codebase audit (git history, targeted scans, full review) with gating | |
| unified-review Orchestrates multi-domain review (code, arch, tests, security) in a single pass | |
| computer-control Automates desktop GUI workflows via computer use API with screenshot capture | |
| commit-messages Generates conventional commit messages from staged changes | |
| do-issue Implements GitHub or GitLab issues via parallel subagents with review gates between task batches | |
| doc-consolidation Merges ephemeral report and analysis artifacts into permanent documentation | |
| doc-updates Updates documentation after code changes with quality gates, slop detection, and accuracy checks | |
| file-analysis Maps file structure and module organization of a codebase. Use before architecture reviews, refactoring planning, or migration scope estimation | |
| git-workspace-review Verifies workspace state and staged changes as a read-only preflight. Use before commits or PRs to confirm staged set is clean and correct | |
| pr-prep Prepares pull requests by running quality gates, drafting descriptions, and validating tests | |
| pr-review Reviews pull requests with scope validation, requirements compliance, and line comments | |
| session-management Manages Claude Code sessions with naming, checkpointing, and resume strategies | |
| stack-create Initializes a stacked branch set from an ordered plan, one branch per slice with parent-child links | |
| stack-mode Detects shared stack membership and iterates a command across all PRs in base-to-tip order | |
| stack-push Pushes all branches in a stack and opens or updates one dependent PR per slice. Use after stack-create to publish the stack or after adding commits to a slice | |
| stack-rebase Cascades a rebase through an entire PR stack after a base PR merges or upstream changes | |
| test-updates Updates, generates, and validates tests using git-workspace context and TDD/BDD methodology | |
| tutorial-updates Generates or updates tutorials from VHS tapes and Playwright specs with dual-tone markdown and GIF recording | |
| update-readme Refreshes README structure and content using repo context and exemplar research | |
| version-updates Bumps versions, updates changelogs, and coordinates version changes across files for releases |
13,401–13,450 of 108,824