hazeliscoding/axiomarium
Build, test, and debug your AI coding environment like software. My open lab of agents, skills, hooks, policies and evals, plus axm, a local CLI that inspects, validates and tests them.
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 hazeliscoding/axiomarium/scenarios/agents-md-and-claude-md/home/.claude ./rig-axiomarium # inspect, then merge into .claude/ 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 hazeliscoding/axiomarium/scenarios/claude-code-skills/home/.claude/skills/deploy .claude/skills/deploy $ npx degit hazeliscoding/axiomarium/scenarios/claude-code-skills/repo/.claude/skills/broken .claude/skills/broken $ npx degit hazeliscoding/axiomarium/scenarios/claude-code-skills/repo/.claude/skills/init .claude/skills/init $ npx degit hazeliscoding/axiomarium/scenarios/claude-code-skills/repo/.claude/skills/lint .claude/skills/lint $ npx degit hazeliscoding/axiomarium/scenarios/claude-code-skills/repo/.claude/skills/manual .claude/skills/manual $ npx degit hazeliscoding/axiomarium/scenarios/claude-code-skills/repo/.claude/skills/quiet .claude/skills/quiet $ npx degit hazeliscoding/axiomarium/scenarios/claude-code-skills/repo/.claude/skills/short .claude/skills/short $ npx degit hazeliscoding/axiomarium/scenarios/claude-code-skills/repo/.claude/skills/star-ts .claude/skills/star-ts $ npx degit hazeliscoding/axiomarium/scenarios/claude-code-skills/repo/.claude/skills/tables .claude/skills/tables $ npx degit hazeliscoding/axiomarium/scenarios/claude-code-skills/repo/src/api/.claude/skills/orders .claude/skills/orders $ npx degit hazeliscoding/axiomarium/scenarios/codex-skills/home/.codex/skills/old .claude/skills/old $ npx degit hazeliscoding/axiomarium/scenarios/codex-skills/repo/.agents/skills/aws .claude/skills/aws $ npx degit hazeliscoding/axiomarium/scenarios/codex-skills/repo/.agents/skills/chat .claude/skills/chat $ npx degit hazeliscoding/axiomarium/scenarios/codex-skills/repo/.agents/skills/folder-x .claude/skills/folder-x $ npx degit hazeliscoding/axiomarium/scenarios/codex-skills/repo/.agents/skills/long .claude/skills/long $ npx degit hazeliscoding/axiomarium/scenarios/codex-skills/repo/.agents/skills/no-description .claude/skills/no-description $ npx degit hazeliscoding/axiomarium/scenarios/codex-skills/repo/.agents/skills/off .claude/skills/off $ npx degit hazeliscoding/axiomarium/scenarios/codex-skills/repo/.codex/skills/local .claude/skills/local $ npx degit hazeliscoding/axiomarium/scenarios/codex-skills/repo/sub/.agents/skills/near .claude/skills/near $ npx degit hazeliscoding/axiomarium/scenarios/demo/repo/.agents/skills/db-migration .claude/skills/db-migration $ npx degit hazeliscoding/axiomarium/scenarios/demo/repo/.claude/skills/release .claude/skills/release $ npx degit hazeliscoding/axiomarium/scenarios/skills-and-hooks/home/.agents/skills/personal .claude/skills/personal $ npx degit hazeliscoding/axiomarium/scenarios/skills-and-hooks/repo/.claude/skills/docs .claude/skills/docs $ npx degit hazeliscoding/axiomarium/scenarios/skills-and-hooks/repo/.claude/skills/typescript .claude/skills/typescript $ npx degit hazeliscoding/axiomarium/scenarios/skills-and-hooks/repo/src/.claude/skills/api-style .claude/skills/api-style
$ curl -fsSL --create-dirs -o .claude/agents/agent.md https://raw.githubusercontent.<redacted>-auditor/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 *)"
]
}
} Skills (25)
deploybrokeninitlintmanualquietshortstar-tstablesordersoldawschatnamed-xlongno-descriptionofflocalneardb-migrationreleasepersonaldocstypescriptapi-style
Subagents (1)
| agent | — |
Slash commands (2)
/lint/tools/format
Similar rigs
syntaxixr/goalpost
Your agent says “All tests pass!” The hidden tests say 28/34. goalpost makes Claude Code's /goal prove it: frozen spec, real checks after every edit, read-only tests, fresh-eyes audit. Enforced by hooks, not by asking nicely.
Minimalist 120 tok ·
Jebel-Quant/rhiza-claude
Claude Code plugin marketplace for the rhiza plugin — slash commands for working in rhiza-managed repos.
Skill Collector 8.3k tok ·
PrefectHQ/fastmcp
🚀 The fast, Pythonic way to build MCP servers and clients.
Pragmatist 5.5k tok ·
serafim-builds/PersonaOS
An open-source AI that quietly remembers who you are — in plain markdown you fully own. Works with Claude Code, Codex CLI, opencode, and any other agent that reads AGENTS.md.
Skill Collector 13.4k tok ·