phnx-labs/.agents
Curated upstream config for agents-cli users
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 phnx-labs/.agents/commands ./rig-.agents/commands $ npx degit phnx-labs/.agents/skills ./rig-.agents/skills $ npx degit phnx-labs/.agents/hooks ./rig-.agents/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 phnx-labs/.agents/plugins/code/skills/health .claude/skills/health $ npx degit phnx-labs/.agents/plugins/code/skills/learn .claude/skills/learn $ npx degit phnx-labs/.agents/plugins/code/skills/refactor .claude/skills/refactor $ npx degit phnx-labs/.agents/plugins/code/skills/review .claude/skills/review $ npx degit phnx-labs/.agents/plugins/design/skills/critique .claude/skills/critique $ npx degit phnx-labs/.agents/plugins/design/skills/design .claude/skills/design $ npx degit phnx-labs/.agents/plugins/design/skills/graphics .claude/skills/graphics $ npx degit phnx-labs/.agents/plugins/design/skills/prototype .claude/skills/prototype $ npx degit phnx-labs/.agents/plugins/design/skills/system .claude/skills/system $ npx degit phnx-labs/.agents/plugins/research/skills/product .claude/skills/product $ npx degit phnx-labs/.agents/plugins/research/skills/research .claude/skills/research $ npx degit phnx-labs/.agents/plugins/self/skills/reflect .claude/skills/reflect $ npx degit phnx-labs/.agents/plugins/sessions/skills/continue .claude/skills/continue $ npx degit phnx-labs/.agents/plugins/sessions/skills/finish .claude/skills/finish $ npx degit phnx-labs/.agents/plugins/sessions/skills/fork .claude/skills/fork $ npx degit phnx-labs/.agents/plugins/sessions/skills/insights .claude/skills/insights $ npx degit phnx-labs/.agents/plugins/sessions/skills/search .claude/skills/search $ npx degit phnx-labs/.agents/plugins/swarm/skills/debug .claude/skills/debug $ npx degit phnx-labs/.agents/plugins/swarm/skills/orchestrate .claude/skills/orchestrate $ npx degit phnx-labs/.agents/plugins/swarm/skills/plan .claude/skills/plan $ npx degit phnx-labs/.agents/plugins/swarm/skills/run .claude/skills/run $ npx degit phnx-labs/.agents/plugins/swarm/skills/spec .claude/skills/spec $ npx degit phnx-labs/.agents/plugins/work/skills/commit .claude/skills/commit $ npx degit phnx-labs/.agents/plugins/work/skills/demo .claude/skills/demo $ npx degit phnx-labs/.agents/plugins/work/skills/dispatch .claude/skills/dispatch $ npx degit phnx-labs/.agents/plugins/work/skills/loop .claude/skills/loop $ npx degit phnx-labs/.agents/plugins/work/skills/resume .claude/skills/resume $ npx degit phnx-labs/.agents/plugins/yc/skills/workweave .claude/skills/workweave $ npx degit phnx-labs/.agents/skills/artifacts .claude/skills/artifacts $ npx degit phnx-labs/.agents/skills/browser .claude/skills/browser $ npx degit phnx-labs/.agents/skills/cloud .claude/skills/cloud $ npx degit phnx-labs/.agents/skills/computer .claude/skills/computer $ npx degit phnx-labs/.agents/skills/docs .claude/skills/docs $ npx degit phnx-labs/.agents/skills/mq .claude/skills/mq $ npx degit phnx-labs/.agents/skills/routines .claude/skills/routines $ npx degit phnx-labs/.agents/skills/secrets .claude/skills/secrets $ npx degit phnx-labs/.agents/skills/sessions .claude/skills/sessions $ npx degit phnx-labs/.agents/skills/teams .claude/skills/teams $ npx degit phnx-labs/.agents/skills/tickets .claude/skills/tickets
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 (39)
healthlearnrefactorreviewcritiquedesigngraphicsprototypesystemproductresearchreflectcontinuefinishforkinsightssearchdebugorchestrateplanrunspeccommitdemodispatchloopresumeworkweaveartifactsbrowsercloudcomputerdocsmqroutinessecretssessionsteamstickets
Slash commands (14)
/blame/continue/debug/dispatch/finish/fork/insights/learn/plan/recall/recap/swarm/teams/visualize
Similar rigs
phnx-labs/agi-cli
AGI CLI ~ a meta-harness for building Agent Factories
Pragmatist 58.6k tok ·
snwlee/Nereus
An opinionated development harness for Claude Code — interview → spec → TDD build → parallel review → finish, with hooks that actually block.
Skill Collector 15.2k tok ·
pruthvidarji1993/ai-automation-jira
AI-assisted dev workflow: Jira ticket in, reviewed PR out. Claude Code plugin + GitHub Copilot prompts with human approval gates (plan, diff).
Pragmatist 2.0k tok ·
assaio/assaio
Is your AI coding spend delivering? Offline-first analytics for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI and Cline — $/100 AI lines per project, every verdict carrying its own confidence, a self-contained dashboard, exec plugi
Fort Knox 4.7k tok ·