agent-skills vs agent-feed
AI coding workflows compared
agent-skills provides reusable skills for guiding AI agents from specifications through implementation, review, testing, and PR preparation. agent-feed installs a repository-owned workflow with shared instructions and checks; the main difference is that agent-skills centers on development skills and optional sprint automation, while agent-feed centers on consistent protocols across coding tools.

agent-skills: Structure AI-Assisted Development from Specs to PRs
A collection of reusable skills for AI coding agents, covering specification writing, implementation, review, testing, and autonomous sprint workflows. Useful for teams that want repeatable processes and clearer quality gates across agent sessions.

agent-feed: Govern AI Coding Workflows in Your Repository
Agent Feed installs a repository-owned workflow for AI coding tools, with shared instructions, task and review gates, checks, and tool adapters. It suits teams that want consistent, verifiable AI-assisted changes across Codex, Claude Code, and Cursor.
| agent-skills | agent-feed | |
|---|---|---|
| Language | Shell | Python |
| License | MIT | MIT |
| Stars | 2 | 4 |
| Forks | 0 | 0 |
| Last analyzed | Oct 3, 2026 | Oct 12, 2026 |
Key differences
- agent-skills is a collection of skills for agents that support the SKILL.md format; agent-feed is a Python CLI that installs and validates a repository workflow.
- agent-skills covers specification writing, task implementation, reviews, testing, and an optional autonomous sprint harness; agent-feed emphasizes task boundaries, decision checkpoints, verification, review, and session handoff.
- agent-feed provides adapters for Codex, Claude Code, and Cursor around a shared AGENTS.md protocol; agent-skills includes workflows for agent delegation and a Claude Code MCP-to-Codex configuration conversion skill.
- agent-skills is written in Shell, while agent-feed is written in Python and requires Python 3.11 or newer.
- Both projects use the MIT license. agent-skills has 2 stars and agent-feed has 4; agent-feed reports one contributor and no commits in its recent measured period.
Choose agent-skills if you…
- want reusable skills for moving from requirements and specifications to implementation, testing, and PR preparation.
- need an optional autonomous sprint workflow with planning, checkpoints, and PR creation.
- want to delegate implementation or request independent reviews from another agent.
Choose agent-feed if you…
- need one repository-owned workflow shared across Codex, Claude Code, and Cursor.
- want task scope, decision checkpoints, verification, review, and handoff practices encoded in repository instructions.
- need a Python CLI to install, check, and manage workflow assets and adapters.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.