consciontologic/agentic-workspace
A model-agnostic scaffold for repositories where AI coding agents do real work. Drop-in instructions, configs, skills, tracking, and a tiny Makefile + xops layer
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ claude mcp add codegraph -e CODEGRAPH_MCP_TOOLS=YOUR_CODEGRAPH_MCP_TOOLS -- npx -y @colbymchenry/codegraph serve --mcp 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.
$ claude mcp add codegraph -e CODEGRAPH_MCP_TOOLS=YOUR_CODEGRAPH_MCP_TOOLS -- npx -y @colbymchenry/codegraph serve --mcp $ npx degit consciontologic/agentic-workspace/.agents/skills/adr-writing .claude/skills/adr-writing $ npx degit consciontologic/agentic-workspace/.agents/skills/ai-output-stability .claude/skills/ai-output-stability $ npx degit consciontologic/agentic-workspace/.agents/skills/anti-ask-permission-loop .claude/skills/anti-ask-permission-loop $ npx degit consciontologic/agentic-workspace/.agents/skills/anti-blind-retry .claude/skills/anti-blind-retry $ npx degit consciontologic/agentic-workspace/.agents/skills/anti-opportunistic-refactor .claude/skills/anti-opportunistic-refactor $ npx degit consciontologic/agentic-workspace/.agents/skills/anti-prompt-injection-trust .claude/skills/anti-prompt-injection-trust $ npx degit consciontologic/agentic-workspace/.agents/skills/anti-retry-until-green .claude/skills/anti-retry-until-green $ npx degit consciontologic/agentic-workspace/.agents/skills/anti-the-silent-skip .claude/skills/anti-the-silent-skip $ npx degit consciontologic/agentic-workspace/.agents/skills/brainstorming .claude/skills/brainstorming $ npx degit consciontologic/agentic-workspace/.agents/skills/changelog-discipline .claude/skills/changelog-discipline $ npx degit consciontologic/agentic-workspace/.agents/skills/clarifying-questions .claude/skills/clarifying-questions $ npx degit consciontologic/agentic-workspace/.agents/skills/code-review .claude/skills/code-review $ npx degit consciontologic/agentic-workspace/.agents/skills/codegraph-management .claude/skills/codegraph-management $ npx degit consciontologic/agentic-workspace/.agents/skills/cost-aware-tool-use .claude/skills/cost-aware-tool-use $ npx degit consciontologic/agentic-workspace/.agents/skills/dependency-upgrade .claude/skills/dependency-upgrade $ npx degit consciontologic/agentic-workspace/.agents/skills/documentation-first .claude/skills/documentation-first $ npx degit consciontologic/agentic-workspace/.agents/skills/flaky-test-triage .claude/skills/flaky-test-triage $ npx degit consciontologic/agentic-workspace/.agents/skills/git-bisect-strategy .claude/skills/git-bisect-strategy $ npx degit consciontologic/agentic-workspace/.agents/skills/human-in-the-loop .claude/skills/human-in-the-loop $ npx degit consciontologic/agentic-workspace/.agents/skills/incident-postmortem .claude/skills/incident-postmortem $ npx degit consciontologic/agentic-workspace/.agents/skills/mcp-usage .claude/skills/mcp-usage $ npx degit consciontologic/agentic-workspace/.agents/skills/minimal-change .claude/skills/minimal-change $ npx degit consciontologic/agentic-workspace/.agents/skills/non-zero-exit-recovery .claude/skills/non-zero-exit-recovery $ npx degit consciontologic/agentic-workspace/.agents/skills/parallel-subagents .claude/skills/parallel-subagents $ npx degit consciontologic/agentic-workspace/.agents/skills/phase-persistence .claude/skills/phase-persistence $ npx degit consciontologic/agentic-workspace/.agents/skills/progress-communication .claude/skills/progress-communication $ npx degit consciontologic/agentic-workspace/.agents/skills/prompt-injection-defense .claude/skills/prompt-injection-defense $ npx degit consciontologic/agentic-workspace/.agents/skills/refactor-discipline .claude/skills/refactor-discipline $ npx degit consciontologic/agentic-workspace/.agents/skills/release-checklist .claude/skills/release-checklist $ npx degit consciontologic/agentic-workspace/.agents/skills/safe-run-wrapper .claude/skills/safe-run-wrapper $ npx degit consciontologic/agentic-workspace/.agents/skills/security-by-default .claude/skills/security-by-default $ npx degit consciontologic/agentic-workspace/.agents/skills/self-review .claude/skills/self-review $ npx degit consciontologic/agentic-workspace/.agents/skills/session-recovery .claude/skills/session-recovery $ npx degit consciontologic/agentic-workspace/.agents/skills/systematic-debugging .claude/skills/systematic-debugging $ npx degit consciontologic/agentic-workspace/.agents/skills/test-driven-development .claude/skills/test-driven-development $ npx degit consciontologic/agentic-workspace/.agents/skills/tool-search-discipline .claude/skills/tool-search-discipline $ npx degit consciontologic/agentic-workspace/.agents/skills/verification-before-completion .claude/skills/verification-before-completion $ npx degit consciontologic/agentic-workspace/.agents/skills/writing-plans .claude/skills/writing-plans
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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| CodeGraph env: CODEGRAPH_MCP_TOOLS | npm | 3.0k |
Skills (38)
adr-writingai-output-stabilityanti-ask-permission-loopanti-blind-retryanti-opportunistic-refactoranti-prompt-injection-trustanti-retry-until-greenanti-the-silent-skipbrainstormingchangelog-disciplineclarifying-questionscode-reviewcodegraph-managementcost-aware-tool-usedependency-upgradedocumentation-firstflaky-test-triagegit-bisect-strategyhuman-in-the-loopincident-postmortemmcp-usageminimal-changenon-zero-exit-recoveryparallel-subagentsphase-persistenceprogress-communicationprompt-injection-defenserefactor-disciplinerelease-checklistsafe-run-wrappersecurity-by-defaultself-reviewsession-recoverysystematic-debuggingtest-driven-developmenttool-search-disciplineverification-before-completionwriting-plans
Similar rigs
nicolasaudran/claude-dotfiles
—
Pragmatist 320 tok ·
handsongice/vibe-rules
跨 coding agent（Claude <redacted> Harness 等）共用的 vibecoding 规范库，一次接入全工具生效，支持 macOS/Linux/Windows
Skill Collector 446 tok ·
RichardBray/dotfiles
My personal configuration files and settings
Skill Collector 671 tok ·
emanuelnicenboim/dotfiles
Personal dotfiles - Claude Code skills & config
Skill Collector 671 tok ·