Frad’s Claude Code Plugins
Install focused Claude Code workflows for engineering, research, content production, and productivity.
- Source repo
- FradSer/dotclaude
- Stars
- ★ 596
- Last updated
- 15d ago
- License
- MIT
- Primary language
- JavaScript
- FA score
- 45/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specificClaude Code
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A developer using Claude Code who wants conventional, atomic commits backed by repository health checks.
- Not a fit if
- Teams that do not use Claude Code
- Users seeking a standalone app or self-hosted service
- Users who need every feature to work without external keys or tools
- Website
- dotclaude.frad.me ↗ set on GitHub
- Maintenance
- Commits in the last 30 dayslast commit 2026-11-06latest release v1.13.0 (2026-06-22)
- Source review
- 45/100 · Major gaps
What does this agent do, and when should you use it?
dotclaude is a collection of Claude Code plugins spanning Git and GitHub automation, refactoring, BDD, SwiftUI review, security checks, research, content production, and hardware design. Its deployable units are separate plugins installed with claude plugin install <name>@frad-dotclaude, not a single application or background service. Plugins expose agents, skills, and slash commands, with documented entry points such as /git-agent:commit, /github:review-pr, /memory:consolidate, and /pi:delegate. Outputs vary by plugin and include atomic commits, PR review findings, research articles, patent applications, videos, images, PCB fabrication files, and STL, DXF, or PNG assets. The primary runtime boundary is Claude Code, while selected plugins call external CLIs, search services, model endpoints, or remote agents and may require their own credentials.
A user selects a plugin, installs it, and invokes its skills, agents, or slash commands from Claude Code. git handles conventional commits, repository management, and GitFlow branches; git-agent uses @git-agent to inspect gitignore completeness, commit-scope freshness, TruffleHog secret leaks, and co-change index health. github adds quality gates, TDD workflows, validation, and persistent CI and reviewer-comment monitoring through /github:review-pr, while refactor and swiftui address cross-file refactoring and SwiftUI Clean Architecture review. Research and content plugins run autoresearch iteration loops, STORM-style retrieval and article generation, image generation, Remotion or HyperFrames video work, and marketing or office-document workflows. Other plugins operate through Gemini Managed Agents, pi, the Feishu/Lark CLI, KiCad 9.0, OpenSCAD, DeepWiki, Context7, Exa, Git clone, and web search to produce task-specific results and artifacts.
- A developer using Claude Code who wants conventional, atomic commits backed by repository health checks.
- A GitHub project team that needs ongoing PR CI monitoring and triage of reviewer comments.
- An engineering team practicing BDD or TDD that wants checklists, validation, and workflow orchestration inside Claude Code.
- An iOS or macOS developer reviewing SwiftUI code against Clean Architecture and documented best practices.
- A researcher or technical writer running a resumable, multi-perspective retrieval, outlining, and long-form writing process.
- A hardware designer using KiCad 9.0 or OpenSCAD CLI to produce fabrication files, validation reports, or 3D models.
Key setup facts
Pulled from the install and usage notes below. The project README has the current values.
- Environment variables
GEMINI_API_KEY
How do you install or deploy this agent?
Claude Code v0.6+ is required. The source provides direct installation commands for individual plugins but does not document the command for initially adding the frad-dotclaude marketplace; that exact prerequisite is therefore missing for an unconfigured environment. Install the plugin you need, for example:
claude plugin install git@frad-dotclaudeInstall the GitHub workflow plugin:
claude plugin install github@frad-dotclaudeInstall the repository scanning and atomic-commit plugin:
claude plugin install git-agent@frad-dotclaudeIndividual plugins can impose additional requirements. antigravity, for example, explicitly requires GEMINI_API_KEY and uv, while the hardware workflows invoke KiCad 9.0 or the OpenSCAD CLI.
How do you use this agent?
After installation, invoke the selected plugin’s agent, skill, or slash command in a Claude Code session opened for the target workspace. These are documented starting points, although the source does not provide argument examples for them:
@git-agentThis runs the full Git health scan. Atomic commits, related-file queries, and workspace initialization use:
/git-agent:commit
/git-agent:related
/git-agent:initMonitor GitHub PR checks and reviewer comments with:
/github:review-prConsolidate memory manually or delegate a task to pi with:
/memory:consolidate
/pi:delegateBefore using a plugin backed by an external service, satisfy its documented prerequisites; for example, antigravity requires GEMINI_API_KEY and uv.
What are this agent's strengths and limitations?
- Plugins are separated by responsibility, so users can install only the Git, GitHub, refactoring, research, hardware, or interface workflows they need.
- Engineering coverage is concrete: GitFlow, semantic versioning, TDD and BDD, persistent PR monitoring, and TruffleHog secret-leak checks are all represented.
- The collection extends beyond code into KiCad and OpenSCAD outputs, image and video generation, long-form research, and active memory workflows.
- Several plugins expose named slash commands that can be triggered directly from a Claude Code session.
- The core delivery model is tied to Claude Code, with no evidence that the plugins run unchanged in ChatGPT, Codex, or a standalone service.
- The source omits the command for adding the
frad-dotclaudemarketplace, leaving a gap in clean-environment onboarding. - Dependencies vary substantially: Antigravity needs
GEMINI_API_KEYanduv, while hardware workflows need KiCad 9.0 or OpenSCAD. - Plugins can involve external models, search, CLIs, and remote sandboxes, but no unified cost, permission, data-handling, or failure policy is documented.
- Repository metadata is inconsistent: the badge reports 23 plugins while the introductory sentence says 22.
How does this agent compare with similar options?
Some plugins derive from or bridge to named projects. mattpocock forks mattpocock/skills v1.2.3 and adds a self-improving checklist subsystem; storm is a Claude-native port of Stanford STORM’s two-stage research-to-article pipeline; and pi delegates execution or read-only review to dev/pi rather than replacing Claude Code. Their distinguishing value here is packaging those workflows as installable Claude Code components instead of using the upstream projects in their original form.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Frad’s Claude Code Plugins This agent | 45 · Major gaps | Agent plugin / skillFree | ★ 596 | 15d ago | JavaScript | Claude Code |
| Workflow Plugin: Claude Workflow V2 | 47 · Major gaps | Agent plugin / skillFree + model costs | ★ 1.4k | 1mo ago | Python | Claude Code |
| OpenCode Swarm | 53 · Major gaps | Agent plugin / skillFree + model costs | ★ 540 | 1d ago | TypeScript | — |
| ECC Engineering Harness | 63 · Some gaps | Agent plugin / skillFreemium | ★ 308k | 1d ago | JavaScript | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The materials show broad capabilities, including Lark messaging and drive operations, Git writes, remote Antigravity execution, and image generation, but do not establish least privilege, confirmation gates, data transfers, or sensitive-data safeguards for these features; those criteria receive 1. Antigravity requires GEMINI_API_KEY and uv, and Lark requires reading authentication and permission rules first, but the sample does not show the full safeguards. The cancel/delete test code covers cleanup in a specific scenario and does not establish general rollback. The README and marketplace provide author and upstream attribution clues, earning 2; publisher identity remains unknown as instructed.
AGENTS.md says README, plugin inventory, and plugin versions can drift silently and require manual synchronization, weakening self-consistency (1). Dependencies and environment requirements are listed only in scattered places, with no evidence of repository-wide availability or pinning (1). The Antigravity scripts and CI show some failure/exit paths and test-skipping behavior, but the sample does not establish clear failure messages across all plugins (1).
The repository covers identifiable development, productivity, video, marketing, Lark, and hardware scenarios, with routers and sub-skill indexes that clarify scope; score 2. Trigger descriptions are fairly specific in the sampled HyperFrames, Lark, and Marketing skills, but this cannot be generalized to all plugins; score 2. Installation is mostly a one-line command, with incomplete environment and permission setup; environment fit scores 1.
The repository has plugin directories, a marketplace manifest, skill indexes, and contributor guidance, making its structure legible (2), though the sample cannot establish consistency across the large collection. The README gives install commands but not full prerequisites, configuration, or upgrade instructions (1). The README, manifest, and version-sync instructions acknowledge drift risk, so naming/version stability scores 1. Router examples and validation commands exist, but no user-facing FAQ is shown (1). Some skill descriptions state limits and delegation boundaries, but there is no systematic limitations guide (1). The MIT license text is complete (3). Marketplace and plugin versions are present, but no changelog appears in the sample (1). Author fields and upstream-sync rules clarify some maintenance and update paths, but publisher identity is unverified, so responsibility scores 1.
Workflow-specific skills, commands, and structured outputs can produce usable results (2); actual result quality was not executed or verified. Specialized plugins and routing/automation offer identifiable marginal utility (2). The collection's size, external service keys, and CLI dependencies add setup and maintenance costs, while the sample does not quantify benefits (1).
The README, marketplace manifest, skill indexes, and code/CI provide traceable evidence for some scope, dependency, and workflow claims (2). README descriptions are corroborated by selected skill samples, but most plugins are not represented, so cross-source corroboration scores 1. The review distinguishes documentation claims from demonstrated implementation and treats gaps as uncertainty rather than inferred success or failure (2).
- This is a static sample review of a multi-plugin repository and does not establish the implementation or safeguards of plugins not shown.
- Before using Lark, remote Gemini, Git write operations, or other external services, review the relevant skill's permissions, data transfers, confirmation, and recovery guidance; the supplied materials do not fully show these controls.
- The README and AGENTS.md explicitly warn that inventory, versions, and README content can drift; check the specific plugin manifest and prerequisites before installation.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Added - autoresearch — New plugin with rolling research loop, git worktree isolation, hybrid plateau escalation, Gemini agent bridge, temporary experiment commits, and unified /start entry point - antigravity — New managed agent plugin with Gemini worker stability enhancements - storm — Article generation plugin - office — Image and video media generation skills, automatic backup pruning, lark-note skill, and lark workspace sync …View on GitHub ↗ -
Release notes excerpt
[v1.12.2] - 2026-06-03 Added - superpowers 3.x — Plan-completion and stop hooks, retrospective memory recall, unified retro event helpers, stall detection with phase recovery, stricter batch execution in executing-plans, design/code evaluation checklists (v2/v3), and read-only superpowers-evaluator for design folders and sprint contracts …View on GitHub ↗ -
Release notes excerpt
Added - Add use-git-agent skill to git plugin for explicit git-agent invocation - Add need-vet skill to refactor plugin for verification gate control - Add need_vet verification flag to devtools plugin for slash command classification - Add shared utility functions to utils plugin for JSON handling and output formatting - Add prd creation skill and templates to office plugin - Add vet skill to superpowers for verification workflow control Changed - Refactor git plugin to streamline git-agent workflow with unified skill structure …View on GitHub ↗
FAQ
Must I install the whole collection?
Can these plugins run directly in ChatGPT, Codex, or a generic terminal agent?
Do all plugins work without API credentials?
antigravity explicitly requires GEMINI_API_KEY; the image plugin also connects to Gemini or an OpenAI-compatible endpoint, although credential setup is not documented in the supplied material.Is there one failure-recovery mechanism for every plugin?
Is the repository only for software engineering?
Is Frad’s Claude Code Plugins free?
Is Frad’s Claude Code Plugins open source?
Is Frad’s Claude Code Plugins safe to use?
Is Frad’s Claude Code Plugins still maintained?
Who makes Frad’s Claude Code Plugins?
What is Frad’s Claude Code Plugins's official website?
Thanks — we use this to improve the page.