Development
Plugin
myclaude
AI-powered development automation with multi-backend execution (Codex/Claude/Gemini/OpenCode)
Plugin Signal74/100Solid
maintained54
capable82
documented100
adopted73
Install on Claude Code
> /plugin marketplace add cexll/myclaude
Stats
2,745
Stars
307
Forks
Maintained
Maintenance
Go
Language
AGPL-3.0
License
3mo ago
Last commit
1y ago
Created
Repo: cexll/myclaude
What's inside
Skills
11/browserThis skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements. No MCP/codeagentExecute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, Gemini, and OpenCode backends with agent presets, skill injection, file references (@syntax), worktree isolation, parallel execution, and structured output./devExtreme lightweight end-to-end development workflow with requirements clarification, intelligent backend selection, parallel codeagent execution, and mandatory 90% test coverage/doThis skill should be used for structured feature development with codebase understanding. Triggers on /do command. Provides a 5-phase workflow (Understand, Clarify, Design, Implement, Complete) using codeagent-wrapper to orchestrate code-explorer, code-architect, code-reviewer,/harnessThis skill should be used for multi-session autonomous agent work requiring progress checkpointing, failure recovery, and task dependency management. Triggers on '/harness' command, or when a task involves many subtasks needing progress persistence, sleep/resume cycles across/omoUse this skill when you see `/omo`. Multi-agent orchestration for "code analysis / bug investigation / fix planning / implementation". Choose the minimal agent set and order based on task type + risk; recipes below show common patterns.
Show all 11 skillsShow fewer
/product-requirementsInteractive Product Owner skill for requirements gathering, analysis, and PRD generation. Triggers when users request product requirements, feature specification, PRD creation, or need help understanding and documenting project requirements. Uses quality scoring and iterative/prototype-prompt-generatorThis skill should be used when users need to generate detailed, structured prompts for creating UI/UX prototypes. Trigger when users request help with "create a prototype prompt", "design a mobile app", "generate UI specifications", or need comprehensive design documentation for/skill-installInstall Claude skills from GitHub repositories with automated security scanning. Triggers when users want to install skills from a GitHub URL, need to browse available skills in a repository, or want to safely add new skills to their Claude environment./sparvMinimal SPARV workflow (SpecifyโPlanโActโReviewโVault) with 10-point spec gate, unified journal, 2-action saves, 3-failure protocol, and EHRB risk detection./test-casesThis skill should be used when generating comprehensive test cases from PRD documents or user requirements. Triggers when users request test case generation, QA planning, test scenario creation, or need structured test documentation. Produces detailed test cases covering
Agents
23BMAD-WORKFLOW**BMAD (Business-Minded Agile Development)** - AI-driven agile development automation with role-based agentsbmad-architectInteractive System Architect agent for technical design with quality scoring and user confirmationbmad-devAutomated Developer agent for implementing features based on PRD, architecture, and sprint planbmad-orchestratorRepository-aware orchestrator agent for workflow coordination, repository analysis, and context managementbmad-poInteractive Product Owner agent for requirements gathering with quality scoring and user confirmationbmad-qaAutomated QA Engineer agent for comprehensive testing based on requirements and implementation
Show all 23 agentsShow fewer
bmad-reviewIndependent code review agentbmad-smAutomated Scrum Master agent for sprint planning and task breakdown based on PRD and architectureDEVELOPMENT-COMMANDSDirect slash commands for daily coding tasks without workflow overheadbugfix-verifyFix validation specialist responsible for independently assessing bug fixes and providing objective feedbackbugfixBug resolution specialist focused on analyzing, understanding, and implementing fixes for software defectscodeDevelopment coordinator directing coding specialists for direct feature implementationdebugUltraThink debug orchestrator coordinating systematic problem analysis and multi-agent debuggingoptimizePerformance optimization coordinator leading optimization experts for systematic performance improvementREQUIREMENTS-WORKFLOWLightweight alternative to BMAD for rapid prototyping and simple feature developmentrequirements-codeDirect implementation agent that converts technical specifications into working code with minimal architectural overheadrequirements-generateTransform user requirements into code-friendly technical specifications optimized for automatic code generationrequirements-reviewPragmatic code review agent focused on functionality, integration quality, and maintainability rather than architectural perfectionrequirements-testingPractical testing agent focused on functional validation and integration testing rather than exhaustive test coveragedev-plan-generatorUse this agent when you need to generate a structured development plan document (`dev-plan.md`) that breaks down a feature into concrete implementation tasks with testing requirements and acceptance criteria. This agent should be called after requirements analysis and beforecode-architectDesigns feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequencescode-explorerDeeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new developmentcode-reviewerReviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter
Commands
13/bmad-pilot`/bmad-pilot <PROJECT_DESCRIPTION> [OPTIONS]`/ask`project:/ask <TECHNICAL_QUESTION>`/bugfix`/project:bugfix <ERROR_DESCRIPTION>`/code`/project:code <FEATURE_DESCRIPTION>`/debug`/project:debug <TASK_DESCRIPTION>`/docs`/project:docs <CODE_SCOPE_DESCRIPTION>`
Show all 13 commandsShow fewer
/enhance-prompt`/enhance-prompt <task info>`/optimize`/project:optimize <PERFORMANCE_TARGET>`/refactor`/project:refactor.md <REFACTOR_SCOPE>`/review`/project:review.md <CODE_SCOPE>`/test`/project:test <COMPONENT_OR_FEATURE>`/think`/project:think <TASK_DESCRIPTION>`/requirements-pilot`/requirements-pilot <FEATURE_DESCRIPTION> [OPTIONS]`
README
1Claude Code Multi-Agent Workflow System
AI-powered development automation with multi-backend execution (Codex/Claude/Gemini/OpenCode)
Quick Start
npx github:stellarlinkco/myclaude
Modules Overview
| Module | Description | Documentation |
|---|---|---|
| do | Recommended - 5-phase feature development with codeagent orchestration | /do command |
| omo | Multi-agent orchestration with intelligent routing | /omo command |
| bmad | BMAD agile workflow with 6 specialized agents | /bmad-pilot command |
| requirements | Lightweight requirements-to-code pipeline | /requirements-pilot command |
| essentials | 11 core dev commands: ask, bugfix, code, debug, docs, enhance-prompt, optimize, refactor, review, test, think | /code, /debug, etc. |
| sparv | SPARV workflow (SpecifyโPlanโActโReviewโVault) | /sparv command |
| course | Course development (combines dev + product-requirements + test-cases) | Composite module |
| claudekit | ClaudeKit: do skill + global hooks (pre-bash, inject-spec, log-prompt) | Composite module |
Available Skills
Individual skills can be installed separately via npx github:stellarlinkco/myclaude --list (skills bundled in modules like do, omo, sparv are listed above):
| Skill | Description |
|---|---|
| browser | Browser automation for web testing and data extraction |
| codeagent | codeagent-wrapper invocation for multi-backend AI code tasks |
| codex | Direct Codex backend execution |
| dev | Lightweight end-to-end development workflow |
| gemini | Direct Gemini backend execution |
| product-requirements | Interactive PRD generation with quality scoring |
| prototype-prompt-generator | Structured UI/UX prototype prompt generation |
| skill-install | Install skills from GitHub with security scanning |
| test-cases | Comprehensive test case generation from requirements |
Installation
# Interactive installer (recommended)
npx github:stellarlinkco/myclaude
# List installable items (modules / skills / wrapper)
npx github:stellarlinkco/myclaude --list
# Detect installed modules and update from GitHub
npx github:stellarlinkco/myclaude --update
# Custom install directory / overwrite
npx github:stellarlinkco/myclaude --install-dir ~/.claude --force
--update detects already installed modules in the target install dir (defaults to ~/.claude, via installed_modules.json when present) and updates them from GitHub (latest release) by overwriting the module files.
Module Configuration
Edit config.json to enable/disable modules:
{
"modules": {
"bmad": { "enabled": false },
"requirements": { "enabled": false },
"essentials": { "enabled": false },
"omo": { "enabled": false },
"sparv": { "enabled": false },
"do": { "enabled": true },
"course": { "enabled": false }
}
}
Workflow Selection Guide
| Scenario | Recommended |
|---|---|
| Feature development (default) | /do |
| Bug investigation + fix | /omo |
| Large enterprise project | /bmad-pilot |
| Quick prototype | /requirements-pilot |
| Simple task | /code, /debug |
Core Architecture
| Role | Agent | Responsibility |
|---|---|---|
| Orchestrator | Claude Code | Planning, context gathering, verification |
| Executor | codeagent-wrapper | Code editing, test execution (Codex/Claude/Gemini/OpenCode) |
Backend CLI Requirements
| Backend | Required Features |
|---|---|
| Codex | codex e, --json, -C, resume |
| Claude | --output-format stream-json, -r |
| Gemini | -o stream-json, -y, -r |
| OpenCode | opencode, stdin mode |
Directory Structure After Installation
~/.claude/
โโโ bin/codeagent-wrapper
โโโ CLAUDE.md (installed by default)
โโโ commands/ (from essentials module)
โโโ agents/ (from bmad/requirements modules)
โโโ skills/ (from do/omo/sparv/course modules)
โโโ hooks/ (from claudekit module)
โโโ settings.json (auto-generated, hooks config)
โโโ installed_modules.json (auto-generated, tracks modules)
Documentation
Troubleshooting
Common Issues
Codex wrapper not found:
# Select: codeagent-wrapper
npx github:stellarlinkco/myclaude
Module not loading:
cat ~/.claude/installed_modules.json
npx github:stellarlinkco/myclaude --force
Backend CLI errors:
which codex && codex --version
which claude && claude --version
which gemini && gemini --version
FAQ
| Issue | Solution |
|---|---|
| "Unknown event format" | Logging display issue, can be ignored |
| Gemini can't read .gitignore files | Remove from .gitignore or use different backend |
| Codex permission denied | Set approval_policy = "never" in ~/.codex/config.yaml |
See GitHub Issues for more.
License
AGPL-3.0 - see LICENSE
Commercial Licensing
For commercial use without AGPL obligations, contact: support@stellarlink.co
Support
File tree
260cexll/myclaudeView on GitHub
.claude-plugin/
marketplace.json
.gitattributes
.github/
workflows/
ci.yml
release.yml
.gitignore
agents/
bmad/
.claude-plugin/
plugin.json
agents/
bmad-architect.md
bmad-dev.md
bmad-orchestrator.md
bmad-po.md
bmad-qa.md
bmad-review.md
bmad-sm.md
BMAD-WORKFLOW.md
commands/
bmad-pilot.md
README.md
development-essentials/
.claude-plugin/
plugin.json
agents/
bugfix-verify.md
bugfix.md
code.md
debug.md
optimize.md
commands/
ask.md
bugfix.md
code.md
debug.md
docs.md
enhance-prompt.md
optimize.md
refactor.md
review.md
test.md
think.md
DEVELOPMENT-COMMANDS.md
README.md
requirements/
.claude-plugin/
plugin.json
agents/
requirements-code.md
requirements-generate.md
requirements-review.md
requirements-testing.md
commands/
requirements-pilot.md
README.md
REQUIREMENTS-WORKFLOW.md
bin/
cli.js
CHANGELOG.md
cliff.toml
codeagent-wrapper/
.github/
workflows/
ci.yml
.gitignore
cmd/
codeagent-wrapper/
main.go
docs/
aec/
codeagent-wrapper-async-execution-refactor-aec.md
go.mod
go.sum
internal/
adapter/
cli/
architecture_test.go
cli.go
execute_test.go
execute.go
parallel_input_test.go
parallel_input.go
parallel_test.go
parallel.go
parse_test.go
parse.go
presentation_test.go
presentation.go
app/
agent_validation_test.go
app.go
architecture_test.go
backend_init.go
backend_registry.go
bench_test.go
cli.go
concurrent_stress_test.go
executor_alias.go
executor_concurrent_test.go
logger.go
main_integration_test.go
main_test.go
os_paths_test.go
parallel_config.go
parser.go
single_mode_runtime_test.go
single_mode_runtime.go
stdin_mode_test.go
task_runtime_adapter.go
terminal_test.go
test_aliases_test.go
tmpdir_test.go
tmpdir.go
utils_test.go
utils.go
wrapper_name.go
application/
cleanup/
cleanup_test.go
cleanup.go
output/
output_test.go
output.go
runtask/
config_plan_test.go
config_plan.go
runtask_test.go
runtask.go
spec.go
runtaskset/
parse_config_test.go
parse_config.go
runtaskset_test.go
runtaskset.go
backend/
backend_test.go
backend.go
claude.go
codex_paths_test.go
codex.go
gemini.go
opencode.go
registry.go
bootstrap/
bootstrap.go
config/
agent_config_test.go
agent.go
config.go
viper.go
domain/
task/
topology_test.go
topology.go
types.go
executor/
env_inject_test.go
env_logging_test.go
env_stderr_test.go
executor_runtime_test.go
executor.go
filter_test.go
filter.go
log_helpers.go
log_writer_limit_test.go
prompt_file_test.go
prompt.go
report_helpers.go
signal_unix.go
signal_windows.go
skills_test.go
stdin.go
task_types.go
testhooks.go
infrastructure/
backend/
backend_test.go
backend.go
janitor/
janitor_test.go
janitor.go
logstore/
logstore_test.go
logstore.go
logger/
active.go
logger_additional_coverage_test.go
logger_suffix_test.go
logger_test.go
logger.go
process_check_test.go
process_check.go
testhooks.go
wrapper_name.go
parser/
event.go
parser_opencode_test.go
parser_token_too_long_test.go
parser_unknown_event_test.go
parser.go
truncate_bytes_test.go
utils/
math_test.go
math.go
strings_test.go
strings.go
worktree/
worktree_test.go
worktree.go
Makefile
README_CN.md
README.md
scripts/
benchmark_claude.sh
USER_GUIDE.md
config.json
config.schema.json
go.work
go.work.sum
hooks/
hooks.json
inject-spec.py
log-prompt.py
pre-bash.py
install.bat
install.py
install.sh
LICENSE
Makefile
memorys/
CLAUDE.md
package.json
PLUGIN_README.md
README_CN.md
README.md
skills/
browser/
browser.zip
package-lock.json
package.json
scripts/
eval.cjs
nav.cjs
pick.cjs
screenshot.cjs
start.cjs
SKILL.md
codeagent/
SKILL.md
dev/
agents/
dev-plan-generator.md
SKILL.md
do/
agents/
code-architect.md
code-explorer.md
code-reviewer.md
hooks/
hooks.json
stop-hook.py
verify-loop.py
install.py
README.md
scripts/
get-context.py
setup-do.py
task.py
SKILL.md
harness/
hooks/
_harness_common.py
harness-claim.py
harness-renew.py
harness-sessionstart.py
harness-stop.py
harness-subagentstop.py
harness-teammateidle.py
hooks.json
self-reflect-stop.py
SKILL.md
tests/
e2e-100tasks.sh
test_hooks.py
omo/
.claude-plugin/
plugin.json
README.md
references/
develop.md
document-writer.md
explore.md
frontend-ui-ux-engineer.md
librarian.md
oracle.md
SKILL.md
product-requirements/
SKILL.md
prototype-prompt-generator/
references/
design-systems.md
prompt-structure.md
SKILL.md
README.md
skill-install/
references/
security_scan_prompt.md
SKILL.md
skill-rules.json
sparv/
.claude-plugin/
plugin.json
hooks/
hooks.json
README.md
references/
methodology.md
scripts/
archive-session.sh
changelog-update.sh
check-ehrb.sh
failure-tracker.sh
init-session.sh
lib/
state-lock.sh
reboot-test.sh
save-progress.sh
SKILL.md
test-cases/
references/
testing-principles.md
SKILL.md
templates/
models.json.example
test_install_path.bat
uninstall.py
uninstall.shFAQ
myclaude is a Claude Code plugin with 11 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes browser, codeagent, dev. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is myclaude?
- AI-powered development automation with multi-backend execution (Codex/Claude/Gemini/OpenCode)
- How do I install myclaude?
- Run these in Claude Code: /plugin marketplace add cexll/myclaude. Then prompt normally.
- Does myclaude auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is myclaude free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.