devcodex-labs/devcodex
Intent-driven AI coding workflow runtime for consistent context, skills, approvals, validation, and handoffs across six AI coding hosts.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ npx degit devcodex-labs/devcodex/agents ./rig-devcodex/agents $ npx degit devcodex-labs/devcodex/hooks ./rig-devcodex/hooks
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 devcodex-labs/devcodex/content/skills/accessibility-i18n .claude/skills/accessibility-i18n $ npx degit devcodex-labs/devcodex/content/skills/ai-agent-system-architecture .claude/skills/ai-agent-system-architecture $ npx degit devcodex-labs/devcodex/content/skills/ai-evaluation-engineering .claude/skills/ai-evaluation-engineering $ npx degit devcodex-labs/devcodex/content/skills/analyze-default .claude/skills/analyze-default $ npx degit devcodex-labs/devcodex/content/skills/analyze-research .claude/skills/analyze-research $ npx degit devcodex-labs/devcodex/content/skills/api-contract-architecture .claude/skills/api-contract-architecture $ npx degit devcodex-labs/devcodex/content/skills/api-verification .claude/skills/api-verification $ npx degit devcodex-labs/devcodex/content/skills/architecture-design .claude/skills/architecture-design $ npx degit devcodex-labs/devcodex/content/skills/audit-common .claude/skills/audit-common $ npx degit devcodex-labs/devcodex/content/skills/audit-dimensions .claude/skills/audit-dimensions $ npx degit devcodex-labs/devcodex/content/skills/audit-document .claude/skills/audit-document $ npx degit devcodex-labs/devcodex/content/skills/audit-execution-guide .claude/skills/audit-execution-guide $ npx degit devcodex-labs/devcodex/content/skills/audit-project .claude/skills/audit-project $ npx degit devcodex-labs/devcodex/content/skills/audit-readme .claude/skills/audit-readme $ npx degit devcodex-labs/devcodex/content/skills/audit-release .claude/skills/audit-release $ npx degit devcodex-labs/devcodex/content/skills/audit-report .claude/skills/audit-report $ npx degit devcodex-labs/devcodex/content/skills/audit-requirements .claude/skills/audit-requirements $ npx degit devcodex-labs/devcodex/content/skills/audit-session .claude/skills/audit-session $ npx degit devcodex-labs/devcodex/content/skills/audit-tech-design .claude/skills/audit-tech-design $ npx degit devcodex-labs/devcodex/content/skills/audit-user-manual .claude/skills/audit-user-manual $ npx degit devcodex-labs/devcodex/content/skills/backend-domain-architecture .claude/skills/backend-domain-architecture $ npx degit devcodex-labs/devcodex/content/skills/brand-visual-quality .claude/skills/brand-visual-quality $ npx degit devcodex-labs/devcodex/content/skills/business-model-review .claude/skills/business-model-review $ npx degit devcodex-labs/devcodex/content/skills/compliance .claude/skills/compliance $ npx degit devcodex-labs/devcodex/content/skills/consumer-validation-engineering .claude/skills/consumer-validation-engineering $ npx degit devcodex-labs/devcodex/content/skills/cp-gate .claude/skills/cp-gate $ npx degit devcodex-labs/devcodex/content/skills/data-architecture .claude/skills/data-architecture $ npx degit devcodex-labs/devcodex/content/skills/design-system-architecture .claude/skills/design-system-architecture $ npx degit devcodex-labs/devcodex/content/skills/dev-database .claude/skills/dev-database $ npx degit devcodex-labs/devcodex/content/skills/dev-default .claude/skills/dev-default $ npx degit devcodex-labs/devcodex/content/skills/dev-docs .claude/skills/dev-docs $ npx degit devcodex-labs/devcodex/content/skills/dev-init .claude/skills/dev-init $ npx degit devcodex-labs/devcodex/content/skills/dev-optimization .claude/skills/dev-optimization $ npx degit devcodex-labs/devcodex/content/skills/dev-plan-review .claude/skills/dev-plan-review $ npx degit devcodex-labs/devcodex/content/skills/dev-refactor .claude/skills/dev-refactor $ npx degit devcodex-labs/devcodex/content/skills/dev-scenario-test .claude/skills/dev-scenario-test $ npx degit devcodex-labs/devcodex/content/skills/dev-testing .claude/skills/dev-testing $ npx degit devcodex-labs/devcodex/content/skills/developer-experience-architecture .claude/skills/developer-experience-architecture $ npx degit devcodex-labs/devcodex/content/skills/distributed-systems-architecture .claude/skills/distributed-systems-architecture $ npx degit devcodex-labs/devcodex/content/skills/document-sync .claude/skills/document-sync
$ curl -fsSL --create-dirs -o .claude/agents/devcodex-auto.agent.md https://raw.githubusercontent.com/devcodex-labs/devcodex/main/agents/devcodex-auto.agent.md $ curl -fsSL --create-dirs -o .claude/agents/devcodex.agent.md https://raw.githubusercontent.com/devcodex-labs/devcodex/main/agents/devcodex.agent.md
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 (2)
| server | source | est. tokens |
|---|---|---|
| devcodex-memory | local / custom | 2.5k |
| devcodex-profile | local / custom | 2.5k |
Skills (88)
accessibility-i18nai-agent-system-architectureai-evaluation-engineeringanalyze-defaultanalyze-researchapi-contract-architectureapi-verificationarchitecture-designaudit-commonaudit-dimensionsaudit-documentaudit-execution-guideaudit-projectaudit-readmeaudit-releaseaudit-reportaudit-requirementsaudit-sessionaudit-tech-designaudit-user-manualbackend-domain-architecturebrand-visual-qualitybusiness-model-reviewcomplianceconsumer-validation-engineeringcp-gatedata-architecturedesign-system-architecturedev-databasedev-defaultdev-docsdev-initdev-optimizationdev-plan-reviewdev-refactordev-scenario-testdev-testingdeveloper-experience-architecturedistributed-systems-architecturedocument-syncevolution-governanceexecution-contractexpert-output-qualityexternal-integration-architecturefix-defaultfix-securityfrontend-architecturegrowth-analyticshost-capability-routinghost-contract-verificationhost-instruction-projectionimpact-reviewincremental-project-analysisintentload-profilemaintainer-docs-site-authoringmemoryperformance-engineeringplanplatform-ecosystem-architectureprivacy-compliance-architectureproduct-strategyproduction-readiness-sreprofile-bootstrapquality-strategyreadme-authoringrelease-verificationrepair-prevention-assessmentreportrequirement-parallel-orchestrationreview-checklistrework-prevention-engineeringroutingsecurity-threat-modelingskill-gap-analysisskill-lifecycle-governanceskill-load-verifysource-consumer-syncspec-absorptionspec-governancesummarytest-routertoken-checkuser-manual-authoringuser-visible-output-contractux-interaction-architectureworkspace-skill-authordevcodex-workspace
Subagents (2)
| DevCodex Auto | AI 开发规范助手（全自动模式 v1.2 sticky）— 按当前用户意图识别 @devcodex-auto、@rocky、Profile autoAliases 或自然语言授权，在已确认任务范围内持续推进。 |
| DevCodex | AI 开发规范助手 — 自动识别意图并路由到对应工作流（开发/修复/审计/分析/自修复/恢复/规划/问答）。所有规则由 instructions/ 自动注入。 |
Similar rigs
ibahgat/oh-my-iflow
Provide intelligent command-line workflows using multi-agent automation with built-in support for Python, Rust, Go, and shell languages.
Skill Collector 312 tok ·
nexika/nexika
The next wisdom for Claude Code: plugins that make Claude work smarter and help people learn deeper. First plugin: prof, a personal programming professor.
Skill Collector 6.7k tok ·
CodeShuX/tokenwise
Cut Claude Code spend without sacrificing quality — and prove it. Haiku/Sonnet/Opus router with real $-saved numbers, not vibes.
Pragmatist 386 tok ·
chengxuniucode/ForgeTeam
AI coding framework — one person, full team delivery. Pure Shell+Markdown, zero dependencies, works with Claude Code / Cursor / Codex / OpenCode. 开源 AI 编码框架，一人全栈交付。
Skill Collector 748 tok ·