refactor: remove non-OpenCode AI tool support from aidevops#412
refactor: remove non-OpenCode AI tool support from aidevops#412marcusquinn merged 11 commits intomainfrom
Conversation
Remove Cursor, Continue, Cody config paths from inject_agents_reference and migration functions. Remove multi-tool claims from completion messages and setup output. Add deprecated paths for windsurf.md, configuration.md, status.md to cleanup function. Keep OpenCode and Claude Code (companion CLI).
Remove Cursor, Continue, Cody, Gemini, Windsurf, Qwen, Droid from status checks and uninstall cleanup. Keep OpenCode and Claude Code CLI.
Remove windsurf.md (Windsurf IDE integration), configuration.md (multi-tool AGENTS.md auto-reading config for Aider/OpenAI/AI Shell/ LiteLLM), and status.md (7-tool integration dashboard). These tools are no longer tested or supported by aidevops.
Replace catalogue of 10+ unsupported tools with focused documentation covering OpenCode (TUI, Desktop, Extension), claude-code CLI as companion, and OpenClaw. Add note about collaborator pointer files.
Remove 'Also Supported' section listing 17 AI tools. Remove Cursor MCP config example. Update MCP integrations intro. Replace multi-tool compatible tools lists with OpenCode focus. Keep collaborator pointer file mention and Agent Skills standard references.
Replace Claude Code recommendation with OpenCode (TUI, Desktop, Extension). Update runtime identity example. Update cross-tool reference to Claude marketplace plugin.
Remove windsurf, configuration, status entries. Add overview, openclaw.
Create .cursorrules, .windsurfrules, .clinerules, and .github/copilot-instructions.md with a one-liner pointing to AGENTS.md. Helps collaborators using other editors find project context without aidevops installing into or configuring those tools.
Remove explicit OpenCode/Claude Code branding from root AGENTS.md which is loaded at system prompt level. Use generic labels instead. Tool names in .agents/AGENTS.md (progressive context) are unaffected.
Update generate-skills.sh, build-agent.md, aidevops-plugin.md, deployment.md, augment-context-engine.md, context7.md to remove claims of supporting Cursor/Windsurf/etc. Keep MCP config reference sections in deployment docs (useful for MCP developers).
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. WalkthroughThis PR systematically refactors documentation and configuration to establish OpenCode as the primary AI assistant tool, repositioning Claude Code as a companion CLI tool. Multiple tool-specific documentation files are removed, and references across scripts and configuration are updated to reflect this new hierarchy. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~22 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Sat Feb 7 02:06:08 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
Summary of ChangesHello @marcusquinn, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request refactors the Highlights
Changelog
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This is a well-executed and thorough refactoring to focus the aidevops framework on OpenCode. The changes are consistent across documentation and scripts, and the removal of unsupported tool configurations is clean. I appreciate the clarity of the pull request description, which clearly outlines the motivation and scope of the changes. The addition of collaborator pointer files is a thoughtful touch to maintain compatibility for team members who might be using other tools.
I've added a couple of minor suggestions to improve the robustness of the scripts, but overall, this is a high-quality pull request that significantly improves the focus and maintainability of the project.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Fix all issues with AI agents
In @.agents/tools/context/context7.md:
- Line 74: The documentation is inconsistent: the prerequisite now recommends
"OpenCode" while setup sections still show "Claude Desktop", "Cursor IDE", and
"Augment Agent" and the "Quick Reference" points to the Claude Desktop config
path; decide whether this doc should be OpenCode-only or multi-tool and update
accordingly — if OpenCode-only, remove or archive the Claude Desktop, Cursor
IDE, and Augment Agent setup blocks and change the "Quick Reference" path (line
referenced as "Quick Reference") to the OpenCode config path and include any
OpenCode-specific steps; if multi-tool, add a clear top-level note stating
multi-tool support, update the prerequisite line to reflect all supported
assistants, and add a short index that points to each tool-specific setup
section (Claude Desktop, Cursor IDE, Augment Agent, OpenCode) so the intent is
explicit.
In `@aidevops.sh`:
- Around line 1098-1109: The loop that writes collaborator pointer files
(.cursorrules, etc.) always calls print_success even when nothing was created;
add a creation counter (e.g., created_count=0) before the for-loop, increment
created_count each time you write to pf_path (where pointer_files and
pointer_content are used), and after the loop call print_success only if
created_count > 0 (otherwise log a different informative message or do nothing).
Ensure mkdir -p and the echo branch is the place you increment so the logic
around pf_path and pointer_files remains unchanged.
In `@setup.sh`:
- Around line 2951-2956: The function setup_augment_context_engine currently
ends without an explicit return; update the function
(setup_augment_context_engine) to include an explicit return statement at the
end (e.g., return 0 or just return) to conform to the repo's shell script
standard and ensure a defined exit status when the function completes.
🧹 Nitpick comments (3)
.agents/tools/ai-assistants/overview.md (1)
21-25: Consider deferring detailed setup/config steps to AGENTS.md.
To preserve a single source of truth, keep Quick Reference high-level and point to AGENTS.md for authoritative setup details.✅ Suggested tweak
- - Config: `~/.config/opencode/opencode.json`, `~/.claude/` - - Setup: `aidevops update` deploys agents, configures OpenCode MCPs + - Config/Setup: See `~/Git/aidevops/AGENTS.md` (authoritative)Based on learnings: Maintain all AI assistant instructions, documentation, and operational guidance in AGENTS.md as the single source of truth.
README.md (2)
385-389: Consider clarifying "Collaborator compatibility" terminology.The term "Collaborator compatibility" (line 389) may not be immediately clear to new users. While the explanation mentions pointer files that reference AGENTS.md, consider adding a brief parenthetical or footnote explaining that this means "read-only reference files for team members using other editors" rather than full integration.
Current phrasing is technically accurate but could benefit from being more explicit about the distinction between:
- OpenCode (primary, fully configured)
- claude-code CLI (companion, called from OpenCode)
- Other tools (pointer files only, no installation/configuration)
📝 Suggested clarification
-**Collaborator compatibility:** Projects initialized with `aidevops init` include pointer files (`.cursorrules`, `.windsurfrules`, etc.) that reference `AGENTS.md`, helping collaborators using other editors find project context. aidevops does not install into or configure those tools. +**Collaborator compatibility:** Projects initialized with `aidevops init` include lightweight pointer files (`.cursorrules`, `.windsurfrules`, etc.) that reference `AGENTS.md`, helping collaborators using other editors (Cursor, Windsurf, etc.) find project context. These are reference-only files—aidevops does not install into or configure those tools.
1549-1558: Clarify "Claude Marketplace" refers to claude-code CLI.The section heading "### Claude Marketplace" (line 1549) could be more specific. This refers to the claude-code CLI plugin marketplace, not Anthropic's general Claude product marketplace. Consider updating the heading to avoid confusion.
🔍 Suggested heading clarification
-### **Claude Marketplace** +### **claude-code CLI Plugin Marketplace** -aidevops is available in the Claude marketplace: +aidevops is available as a claude-code CLI plugin:This makes it immediately clear this section is about the companion CLI tool, not the primary OpenCode tool or the web-based Claude interface.
- Add return 0 to setup_augment_context_engine function - Remove stale multi-tool comment in same function - Track pointer file creation count, only print success when files created - Add note to context7.md clarifying multi-tool config sections are MCP reference
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Sat Feb 7 02:12:55 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
|
- Remove dataforseo and outscraper from MCP table (replaced by curl subagents) - Update MCP count badge from 19 to 17 - Update script count to 172, subagent count to 765+ - Fix inconsistent script count (was 167 in one place, 146 in another) - Update supported AI assistants to reflect OpenCode-only support (PR #412) - Add three-tier agent lifecycle section (draft/custom/shared from PR #409) - Move outscraper to curl subagents section
* docs: update README with recent feature changes - Remove dataforseo and outscraper from MCP table (replaced by curl subagents) - Update MCP count badge from 19 to 17 - Update script count to 172, subagent count to 765+ - Fix inconsistent script count (was 167 in one place, 146 in another) - Update supported AI assistants to reflect OpenCode-only support (PR #412) - Add three-tier agent lifecycle section (draft/custom/shared from PR #409) - Move outscraper to curl subagents section * fix: align MCP table count with badge (19 available, add shadcn)
…(t147.7) Addressed 5 valid issues: - Remove trailing blank lines in content.md - Remove duplicate list item in aidevops-plugin.md - Remove dead setup_oh_my_opencode stub (no callers) - Add mkdir -p before touch in add_local_bin_to_path (fish dir) - Add fish config to alias duplicate detection in setup_aliases Already fixed (6 threads): augment return 0, context7 old refs, pointer file count, parse_args return, mutual exclusion guard, non-interactive check_requirements Dismissed (6 threads): Intel Homebrew path (code removed), Bun rc (code removed), lowercase-only y (intentional UX), dir check -e vs -f (unrealistic edge case), shorten warning (intentional verbosity), pr-loop dedup (maintainer dismissed)
…(t147.7) (#475) Addressed 5 valid issues: - Remove trailing blank lines in content.md - Remove duplicate list item in aidevops-plugin.md - Remove dead setup_oh_my_opencode stub (no callers) - Add mkdir -p before touch in add_local_bin_to_path (fish dir) - Add fish config to alias duplicate detection in setup_aliases Already fixed (6 threads): augment return 0, context7 old refs, pointer file count, parse_args return, mutual exclusion guard, non-interactive check_requirements Dismissed (6 threads): Intel Homebrew path (code removed), Bun rc (code removed), lowercase-only y (intentional UX), dir check -e vs -f (unrealistic edge case), shorten warning (intentional verbosity), pr-loop dedup (maintainer dismissed)
* fix: triage 17 PR review threads across PRs #418,#413,#412,#399,#394 (t147.7) Addressed 5 valid issues: - Remove trailing blank lines in content.md - Remove duplicate list item in aidevops-plugin.md - Remove dead setup_oh_my_opencode stub (no callers) - Add mkdir -p before touch in add_local_bin_to_path (fish dir) - Add fish config to alias duplicate detection in setup_aliases Already fixed (6 threads): augment return 0, context7 old refs, pointer file count, parse_args return, mutual exclusion guard, non-interactive check_requirements Dismissed (6 threads): Intel Homebrew path (code removed), Bun rc (code removed), lowercase-only y (intentional UX), dir check -e vs -f (unrealistic edge case), shorten warning (intentional verbosity), pr-loop dedup (maintainer dismissed) * chore: mark t147 complete - all 50 review threads resolved across 11 PRs (GH#438)
…de in context7.md Resolves GH#3468 — the Quick Reference section still pointed to the Claude Desktop config path after PR #412 switched the doc to be OpenCode-focused. Update to ~/.config/opencode/opencode.json to match the primary supported tool. The Claude Desktop section below remains as intentional MCP reference (consistent with deployment.md), guarded by the existing note.
…de in context7.md (#4555) Resolves GH#3468 — the Quick Reference section still pointed to the Claude Desktop config path after PR #412 switched the doc to be OpenCode-focused. Update to ~/.config/opencode/opencode.json to match the primary supported tool. The Claude Desktop section below remains as intentional MCP reference (consistent with deployment.md), guarded by the existing note.
1 participant
Summary
Changes
Removed (894 lines deleted)
windsurf.md- Windsurf IDE integration docconfiguration.md- Multi-tool AGENTS.md auto-reading config (Aider, OpenAI CLI, AI Shell, LiteLLM)status.md- 7-tool integration dashboardAdded
aidevops initnow generates collaborator pointer files (.cursorrules, .windsurfrules, .clinerules, .github/copilot-instructions.md) with one-liner pointing to AGENTS.mdKept (intentionally)
.cursorrulesformat support in skill import (describes file format, not tool support)Motivation
Only OpenCode (TUI, Desktop, Extension for Zed/VSCode/AntiGravity) is actively tested. Claiming support for 17+ tools creates user disappointment and support burden. This refactor removes the noise so we can focus on making the most of OpenCode's capabilities.
Summary by CodeRabbit
New Features
Documentation
Chores