by JunsW · Codex Skill · ★ 120
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Repo-native shared memory for AI coding agents.
| Stars | 120 |
| Forks | 1 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 56.2817423335396/100 |
| Last Updated | 2026-07-16 |
| Created | 2026-07-06 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~3k |
These tools work well together with feature-track for enhanced workflows:
Looking for a feature-track alternative? If you're comparing feature-track 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.
Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKI
Open-source, Git-native memory for AI coding agents — deterministic local recall for Claude Code, Codex, Curso
Git-native memory for coding agents. Repo memory before the diff.
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
Run Claude Code/Codex within AgentFS, orchestrated by LlamaIndex Workflows
Explore other popular codex skill tools:
feature-track is Repo-native shared memory for AI coding agents.. It is categorized as a Codex Skill with 120 GitHub stars.
feature-track is primarily written in Python. It covers topics such as agent-context, ai, ai-agent-memory.
You can find installation instructions and usage details in the feature-track GitHub repository at github.com/JunsW/feature-track. The project has 120 stars and 1 forks, indicating an active community.
feature-track is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to feature-track on Agent Skills Hub include ok-skills, ownmem, mainline. 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: