feat: Claude Code plugin packaging and multi-app setup docs#34
Merged
hybridindie merged 2 commits intomainfrom Mar 13, 2026
Merged
feat: Claude Code plugin packaging and multi-app setup docs#34hybridindie merged 2 commits intomainfrom
hybridindie merged 2 commits intomainfrom
Conversation
Package the MCP server as a Claude Code plugin with slash commands, contextual skills, and a security hook. Add configuration snippets for 8 client environments (Claude Code, Claude Desktop, VS Code, Cursor, Windsurf, Continue.dev, OpenCode, Open WebUI). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Packages this MCP server as a Claude Code plugin (slash commands + skills + hooks) and expands the README with multi-environment setup snippets so users can connect various AI clients to the ComfyUI MCP server.
Changes:
- Added Claude Code “skills” markdown files for
/comfy:*workflows (gen/status/models/history/progress/workflow) plus contextual workflow/troubleshooting knowledge. - Added a
PostToolUsehook configuration and a shell hook intended to surface security warnings. - Reworked README setup guidance with copy/paste configs for multiple clients and added a root
.mcp.jsonexample.
Reviewed changes
Copilot reviewed 13 out of 13 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
| skills/workflows/SKILL.md | Adds a workflow-building knowledge skill document. |
| skills/workflow/SKILL.md | Adds /comfy:workflow slash-command skill instructions. |
| skills/troubleshooting/SKILL.md | Adds troubleshooting knowledge skill document. |
| skills/status/SKILL.md | Adds /comfy:status skill instructions. |
| skills/progress/SKILL.md | Adds /comfy:progress skill instructions. |
| skills/models/SKILL.md | Adds /comfy:models skill instructions. |
| skills/history/SKILL.md | Adds /comfy:history skill instructions. |
| skills/gen/SKILL.md | Adds /comfy:gen skill instructions. |
| hooks/security-warning.sh | Implements a post-tool hook to emit a security warning message. |
| hooks/hooks.json | Registers the post-tool hook for specific MCP tool invocations. |
| README.md | Adds “Setup” section with client-specific configuration snippets and verification commands. |
| .mcp.json | Adds a project-local MCP server config example. |
| .claude-plugin/plugin.json | Adds Claude plugin metadata (name/description/version). |
You can also share your feedback on Copilot code review. Take the survey.
Comment on lines
+53
to
+60
| | Node | Purpose | Key Inputs | | ||
| |------|---------|------------| | ||
| | `CheckpointLoaderSimple` | Load a model checkpoint | `ckpt_name` | | ||
| | `CLIPTextEncode` | Encode text prompt | `text`, `clip` | | ||
| | `KSampler` | Run diffusion sampling | `model`, `positive`, `negative`, `latent_image`, `steps`, `cfg`, `seed` | | ||
| | `VAEDecode` | Decode latent to image | `samples`, `vae` | | ||
| | `VAEEncode` | Encode image to latent | `pixels`, `vae` | | ||
| | `SaveImage` | Save output image | `images`, `filename_prefix` | |
hooks/security-warning.sh
Outdated
| # Reads tool output JSON from stdin. Exits 0 always (non-blocking). | ||
|
|
||
| input=$(cat) | ||
| if echo "$input" | grep -qi "DANGEROUS"; then |
README.md
Outdated
| "-v", "~/.comfyui-mcp:/root/.comfyui-mcp:ro", | ||
| "ghcr.io/hybridindie/comfyui-mcp:latest" | ||
| ] | ||
| "args": ["run", "-i", "--rm", "-e", "COMFYUI_URL=http://host.docker.internal:8188", "ghcr.io/hybridindie/comfyui_mcp"], |
Comment on lines
+98
to
+100
| ```bash | ||
| claude plugin install github:hybridindie/comfyui_mcp | ||
| ``` |
- Fix security-warning.sh to match specific warning patterns instead of grepping for "DANGEROUS" which false-positives on JSON keys - Align all Docker image references to ghcr.io/hybridindie/comfyui_mcp:main (underscore, :main tag) matching the actual CI workflow output Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
.claude-plugin/plugin.json,.mcp.json) with plugin namecomfyfor/comfy:*slash commands/comfy:gen,/comfy:workflow,/comfy:status,/comfy:models,/comfy:history,/comfy:progress) and 2 contextual knowledge skills (workflow building guide, troubleshooting guide)PostToolUsesecurity hook that surfaces warnings when dangerous node patterns are detected afteraudit_dangerous_nodes,install_custom_node,update_custom_node,run_workflow, orgenerate_imageuvxand Docker variantsCloses #16
Test plan
claude --plugin-dir .from repo root — verify slash commands appear as/comfy:gen,/comfy:status, etc./comfy:gen "a sunset"— verify orchestration flow callslist_models→generate_image→get_image/comfy:status— verifyget_queueis called and output formatted🤖 Generated with Claude Code