jmagly/aiwg
Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and multi-platform deployment. Claude Code · Codex · Copilot · Cursor · Factory · Warp · Windsurf.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/jmagly/aiwg MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/agent-loop-ext .claude/skills/agent-loop-ext $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/agent-loop .claude/skills/agent-loop $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/auto-test-execution .claude/skills/auto-test-execution $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/cross-task-learner .claude/skills/cross-task-learner $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/debug-memory .claude/skills/debug-memory $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/execute-feedback .claude/skills/execute-feedback $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/infer-completion-criteria .claude/skills/infer-completion-criteria $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/mission-control .claude/skills/mission-control $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph-abort .claude/skills/ralph-abort $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph-analytics .claude/skills/ralph-analytics $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph-attach .claude/skills/ralph-attach $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph-config .claude/skills/ralph-config $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph-external .claude/skills/ralph-external $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph-memory .claude/skills/ralph-memory $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph-reflect .claude/skills/ralph-reflect $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph-resume .claude/skills/ralph-resume $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph-status .claude/skills/ralph-status $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/ralph .claude/skills/ralph $ npx degit jmagly/aiwg/agentic/code/addons/agent-loop/skills/reflection-injection .claude/skills/reflection-injection $ npx degit jmagly/aiwg/agentic/code/addons/agent-persistence/skills/agent-persistence .claude/skills/agent-persistence $ npx degit jmagly/aiwg/agentic/code/addons/agentic-installer/skills/cockpit-headless-deploy .claude/skills/cockpit-headless-deploy $ npx degit jmagly/aiwg/agentic/code/addons/agentic-installer/skills/setup-generate .claude/skills/setup-generate $ npx degit jmagly/aiwg/agentic/code/addons/agentic-installer/skills/setup-run .claude/skills/setup-run $ npx degit jmagly/aiwg/agentic/code/addons/agentic-installer/skills/setup-validate .claude/skills/setup-validate $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/dev-doctor .claude/skills/dev-doctor $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/dev-mode-init .claude/skills/dev-mode-init $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/devkit-create-addon .claude/skills/devkit-create-addon $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/devkit-create-agent .claude/skills/devkit-create-agent $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/devkit-create-command .claude/skills/devkit-create-command $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/devkit-create-extension .claude/skills/devkit-create-extension $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/devkit-create-framework .claude/skills/devkit-create-framework $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/devkit-create-skill .claude/skills/devkit-create-skill $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/devkit-test .claude/skills/devkit-test $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/devkit-validate .claude/skills/devkit-validate $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/link-check .claude/skills/link-check $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/validate-addon .claude/skills/validate-addon $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-dev/skills/validate-component .claude/skills/validate-component $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-evals/skills/eval-agent .claude/skills/eval-agent $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-evals/skills/eval-report .claude/skills/eval-report $ npx degit jmagly/aiwg/agentic/code/addons/aiwg-evals/skills/eval-workflow .claude/skills/eval-workflow
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (149)
agent-loop-extagent-loopauto-test-executioncross-task-learnerdebug-memoryexecute-feedbackinfer-completion-criteriamission-controlralph-abortralph-analyticsralph-attachralph-configralph-externalralph-memoryralph-reflectralph-resumeralph-statusralphreflection-injectionagent-persistencecockpit-headless-deploysetup-generatesetup-runsetup-validatedev-doctordev-mode-initdevkit-create-addondevkit-create-agentdevkit-create-commanddevkit-create-extensiondevkit-create-frameworkdevkit-create-skilldevkit-testdevkit-validatelink-checkvalidate-addonvalidate-componenteval-agenteval-reporteval-workflowaiwg-hooksactivity-logadd-agentadd-behavioradd-commandadd-skilladd-templateaiwg-delivery-praiwg-doctoraiwg-guideaiwg-helpaiwg-initaiwg-issueaiwg-language-mapaiwg-mcp-serveraiwg-missionaiwg-praiwg-refreshaiwg-regenerate-agentsaiwg-regenerate-claudeaiwg-regenerate-codexaiwg-regenerate-copilotaiwg-regenerate-cursorrulesaiwg-regenerate-existing-projectaiwg-regenerate-factoryaiwg-regenerate-legacyaiwg-regenerate-opencodeaiwg-regenerate-warpaiwg-regenerate-windsurfrulesaiwg-regenerate-workspaceaiwg-regenerateaiwg-statusaiwg-steward-routing-referenceaiwg-steward-worked-examplesaiwg-syncaiwg-utils-quickrefartifact-metadatabehaviorcatalogcheckpointclaims-validatorcleanup-auditcommit-and-pushconfig-validatorconfigcontext-firewallcontribute-startcost-historycost-reportcustomize-contribute-backcustomize-rebuildcustomize-setupcustomize-statuscustomize-upstream-syncdaemon-initdeploy-gendoc-consolidatedoc-synceffect-ledgerexecution-modefeedbackgit-mirror-audithook-disablehook-enablehook-regeneratehook-statusinstall-plugininstalllistmention-conventionsmention-lintmention-reportmention-validatemention-wiremetrics-tokensmigrate-hookmigrate-workspacenew-bundlenew-projectnl-routeropspackage-all-pluginspackage-pluginpackagesparallel-dispatchplugin-statusprefill-cardsproject-awarenessproject-statuspromoteremovereproducibility-validateroko-voicerollback-workspacerunruntime-infoscaffold-addonscaffold-extensionscaffold-frameworkschedulesdlc-acceleratesession-exploresession-harvestsessionskillssnapshotsoul-applysoul-blendsoul-create
Similar rigs
ChristopherALewis/claude-et-ay
Estimated time to completion for Claude Code: a live status line ETA for the prompt Claude is working on, learnt from your own history.
Pragmatist 183 tok ·
john-wilmes/claude-agentic-coding-playbook
Evidence-based practices for LLM-assisted development. Install scripts, Claude Code configuration, and a research-backed best practices guide with 34 verified citations.
Pragmatist 3.9k tok ·
nullbrainlabs/dotai
Unified AI coding tool config. Define rules, skills, agents, and MCP servers once in .ai/ and sync to Claude Code, Cursor, Codex, and GitHub Copilot.
Skill Collector 4.0k tok ·
svy04/ballast
Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already hold, learns what is missing, and leaves every solved path behind for the next goal. Nothing is cal
Skill Collector 1.2k tok ·