Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by shepard-system · Codex Skill · ★ 70
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is shepard-obs-stack safe to install? View the security audit →
shepard-obs-stack The Eye — self-hosted observability for AI coding assistants. You use Claude Code, Codex, or Gemini CLI every day. You have no idea how much they cost, which tools they call, or whether they're actually helping. This fixes that. More screenshots Tools — 5K calls across all three CLIs, top tools ranked, failing tools by error count: Operations — live event rate, breakdown by source and event type: Claude Code Deep Dive — per-model cost, token breakd
| Stars | 70 |
| Forks | 6 |
| Language | Shell |
| Category | Codex Skill |
| Quality Score | 65.9735221760898/100 |
| Last Updated | 2026-03-24 |
| Created | 2026-02-23 |
| Platforms | claude-code, cli, codex, gemini |
| Est. Tokens | ~77k |
These tools work well together with shepard-obs-stack for enhanced workflows:
Looking for a shepard-obs-stack alternative? If you're comparing shepard-obs-stack with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Unified local observability for AI coding assistants
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality ga
Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, C
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Explore other popular codex skill tools:
shepard-obs-stack is Self-hosted observability for AI coding agents. Clone. Configure. See.. It is categorized as a Codex Skill with 70 GitHub stars.
shepard-obs-stack is primarily written in Shell. It covers topics such as ai-agents, claude-code, codex.
You can find installation instructions and usage details in the shepard-obs-stack GitHub repository at github.com/shepard-system/shepard-obs-stack. The project has 70 stars and 6 forks, indicating an active community.
The top alternatives to shepard-obs-stack on Agent Skills Hub include ai-observer, agent-skills, agent-designer. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: