{"name":"agent-feed: Govern AI Coding Workflows in Your Repository","description":"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.","github":"https://github.com/fqmyysjjd/agent-feed","url":"https://osrepos.com/repo/fqmyysjjd-agent-feed","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/fqmyysjjd-agent-feed","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/fqmyysjjd-agent-feed.md","json":"https://osrepos.com/repo/fqmyysjjd-agent-feed.json","topics":["python","ai-agents","developer-tools","workflow-automation","coding-agent","agent-skills","cursor-rules"],"keywords":["python","ai-agents","developer-tools","workflow-automation","coding-agent","agent-skills","cursor-rules"],"stars":null,"summary":"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.","content":"## Overview\n\nAgent Feed is a Python CLI that installs workflow instructions and supporting checks into a code repository. It addresses the fragmentation that occurs when AI coding guidance lives across chat history, tool-specific rules, and scattered project documents.\n\nThe installed protocol uses `AGENTS.md` as a shared entry point, with rules, skills, project knowledge, verification steps, and adapters for Codex, Claude Code, and Cursor. It is designed for teams that want AI-assisted changes to follow repository-defined scope, decision, review, and handoff practices.\n\n## Key Features\n\n- Initializes a repository with `AGENTS.md` and a structured `.agents/` workflow.\n- Provides thin adapters for Codex, Claude Code, and Cursor, keeping the shared protocol canonical.\n- Defines task boundaries, decision checkpoints, verification gates, review, and session handoff.\n- Checks protocol structure, references, scripts, skills, and client adapters.\n- Supports project-specific constraints and domain knowledge alongside reusable workflow rules.\n- Manages local and imported skills, with trust checks for external assets.\n- Includes status, upgrade, adapter sync, and configuration commands in its CLI.\n\n## Use Cases\n\n- A team using several AI coding tools wants repository instructions to stay consistent across clients.\n- Developers want small coding requests to remain scoped and architecture or contract decisions to receive human confirmation.\n- Teams need completion to include project-defined tests, documentation checks, or review rather than relying on chat claims.\n- A developer working across long AI sessions wants a concise handoff of active conclusions instead of replaying conversation history.\n- Maintainers want to add team-specific skills and constraints without replacing a shared workflow foundation.\n\n## Our Take\n\nAgent Feed offers a concrete, repository-centered way to govern AI coding, but its quiet recent activity and reliance on one contributor make ongoing maintenance worth checking before adoption.\n\n**Good fit if:**\n- You use Codex, Claude Code, or Cursor and want a common source of workflow guidance in the repository.\n- Your team values explicit scope, verification, review, and human decision gates for AI-generated changes.\n- You can run a Python 3.11+ CLI and are comfortable adopting an MIT-licensed project whose work is concentrated in one contributor.\n\n**Look elsewhere if:**\n- You need a hosted service or runtime platform rather than repository-installed workflow files and checks.\n- You need evidence of ongoing commits or issue and pull-request handling: the project is marked quiet, with no commits or closed issues or merged pull requests in the measured recent period.\n- Your workflow does not use the supported coding-agent adapters and a shared `AGENTS.md` protocol would add little value.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **Quiet**: no commits in the last 90 days |\n| Last commit | 2026-05-09 (5 months ago) |\n| Commits, last 90 days | 0 |\n| Releases, last 12 months | 9 (latest v1.1.6, 2026-05-08) |\n| Contributors | 1 |\n| Issues closed, last 90 days | 0 |\n| Pull requests merged, last 90 days | 0 |\n| Project age | 5 months |\n\nChecked on 2026-10-12 with the GitHub API.\n\n## Project Facts\n\n- Language: Python\n- License: MIT\n- Stars: 4\n- Forks: 0\n- Topics: agentic-development, agentic-development-environment, agentsmd, ai-coding, ai-coding-agents, ai-workflow, claude-code, claude-md\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Node.js >=16.0.0 (from package.json)\n- Python >=3.11 (from pyproject.toml)\n- A test suite and automated checks on GitHub Actions\n\n## Getting Started\n\nInstall with one of the supported package managers, then initialize and check the repository:\n\n```sh\nuv tool install agent-feed\nagent-feed init\nagent-feed check\n```\n\nSee the [README](https://github.com/fqmyysjjd/agent-feed) and [Usage Guide](https://github.com/fqmyysjjd/agent-feed/blob/main/docs/usage-guide.md) for setup options and customization.\n\n## License in Plain Words\n\n**MIT** (permissive).\n\n- Commercial use: yes\n- Modify and redistribute: yes\n- You must keep: the copyright and license notice\n- Share your changes: no\n\nA summary, not legal advice: the LICENSE file is what applies.\n\n## Alternatives\n\n- [compound-engineering-plugin](https://osrepos.com/repo/everyinc-compound-engineering-plugin): It packages reusable skills for planning through implementation and captured learnings, rather than installing a repository-owned workflow with shared checks and gates.\n- [agent-skills](https://osrepos.com/repo/addyosmani-agent-skills): It offers portable engineering workflows for planning, testing, review, and release, while agent-feed centers on a repository-owned setup with tool adapters.\n- [agent-skills](https://osrepos.com/repo/anyoneanderson-agent-skills): It provides reusable specification, review, testing, and sprint skills, rather than a repository-owned workflow with shared instructions and checks.\n- [agentic-engineering](https://osrepos.com/repo/affectionatec-agentic-engineering): It emphasizes documentation, session memory, and human-controlled merges, while agent-feed installs shared workflow gates and tool adapters in a repository.\n\n| Project | Language | License | Stars | Status |\n|---|---|---|---|---|\n| **agent-feed** | Python | MIT | 4 | Quiet |\n| [compound-engineering-plugin](https://osrepos.com/repo/everyinc-compound-engineering-plugin) | TypeScript | MIT | 25.4k | Active |\n| [agent-skills](https://osrepos.com/repo/addyosmani-agent-skills) | JavaScript | MIT | 101k | Active |\n| [agent-skills](https://osrepos.com/repo/anyoneanderson-agent-skills) | Shell | MIT | 2 | Active |\n| [agentic-engineering](https://osrepos.com/repo/affectionatec-agentic-engineering) | – | MIT | 5 | Quiet |\n\n## Considerations\n\n- The measured project status is quiet: there have been no commits in the recent measured period, despite releases during the past year. Release activity does not by itself establish current maintenance.\n- The project has one contributor, with nearly all contribution activity concentrated there. This creates a maintainer-continuity risk for a workflow teams may depend on.\n- The CLI requires Python 3.11 or newer. The npm package is a wrapper and also requires Python on the machine.\n- Agent Feed installs and validates instructions and workflow assets; it is not a replacement for the coding agents themselves or for project-specific test infrastructure.","metrics":{"detailViews":1,"githubClicks":1},"dates":{"published":null,"modified":"2026-10-12T11:00:35.000Z"}}