by melagiri · Codex Skill · ★ 79
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npx @code-insights/cli
npm install -g @code-insights/cli
Taken from the project's README on GitHub.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
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 | 79 |
| Forks | 20 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66/100 |
| Open Issues | 11 |
| Last Updated | 2026-06-01 |
| Created | 2026-01-21 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~5503k |
Code Insights Turn your AI coding sessions into knowledge. Extract decisions, learnings, and prompt quality scores. Detect patterns. Get better at working with AI. Analyzes your sessions from Claude Code, Cursor, Codex CLI, Copilot CLI, and VS Code Copilot Chat to extract structured insights — decisions with trade-offs, learnings with root causes
These tools work well together with code-insights for enhanced workflows:
Looking for a code-insights alternative? If you're comparing code-insights 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.
Persistent memory for AI coding agents
MCP Fusion - The framework for AI-native MCP servers.
Notion MCP server with token auth: connect Claude Code, Claude Desktop, Cursor, VS Code and Codex to Notion pa
Local-first AI knowledge layer. Extract architecture, query from any AI tool via MCP. Private by architecture.
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Local citation-backed recall for Pi, OMP, Claude Code, Codex, and ChatGPT history.
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: