by bjarneo · Codex Skill · ★ 67
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
go install github.com/bjarneo/shoulder@latestTaken from the project's README on GitHub. Check the security audit before running it.
Flagged: sudo usage. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 67 |
| Forks | 4 |
| Language | Go |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 69/100 |
| Last Updated | 2026-10-29 |
| Created | 2026-10-27 |
| Platforms | claude-code, cli, codex, gemini, go |
| Est. Tokens | ~17k |
shoulder Watch over your agents' shoulder. See your coding agents work, live. shoulder follows Claude Code, Codex, Gemini CLI and opencode through your project. It shows the file that each agent reads or edits, the diff against your last commit, and the commands that it runs. To see the 47-second demo, open the website or download shoulder-demo.mp4.
Looking for a shoulder alternative? If you're comparing shoulder 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.
Process manager for AI agents (and humans)
A desktop app for coding with agents. Each thread is a real terminal running the agent you already use.
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Notion MCP server with token auth: connect Claude Code, Claude Desktop, Cursor, VS Code and Codex to Notion pa
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
One command to run the AI coding CLI you already pay for (Claude Code, Codex, Cursor, Gemini, Grok, aider) on
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: