agentrigs
+ submit rig
~ / rigs / ArtemkaGoldMan / docbase

ArtemkaGoldMan/docbase

Turn exported documentation into a knowledge base an AI agent can actually use — restores lost hyperlinks, rebuilds reading order, retrieves fragments instead of whole documents

↗ GitHub ★ 0 MIT updated today project Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit ArtemkaGoldMan/docbase/.claude ./rig-docbase  # 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 ArtemkaGoldMan/docbase/.agents/skills/docs-import .claude/skills/docs-import
$ npx degit ArtemkaGoldMan/docbase/.agents/skills/docs-search .claude/skills/docs-search
$ npx degit ArtemkaGoldMan/docbase/.agents/skills/docs-tailor .claude/skills/docs-tailor

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 (3)

docs-importdocs-searchdocs-tailor

Hooks (2)

eventmatcherruns
SessionStart*python -m docbase sync --quiet || python3 -m docbase sync --quiet || py -m docbase sync --quiet || echo docbase: no Python could run docbase, so the base is not updated. See AGENTS.md, When the base does not update.
UserPromptSubmit*python -m docbase sync --quiet || python3 -m docbase sync --quiet || py -m docbase sync --quiet || echo docbase: no Python could run docbase, so the base is not updated. See AGENTS.md, When the base does not update.

Similar rigs

23blocks-OS/ai-maestro-plugins
Build complete AI agents — 150+ personalities + 7 skills + messaging + identity. The skill builder for AI Maestro.
★ 11 collection Claude Code 9 skills today
Pragmatist 771 tok ·
equwal/ai-config
One canonical AI agent config (rules, skills, MCP servers) rendered into Claude Code, Codex, Copilot CLI and Antigravity by acsync
★ 0 setup Claude Code 25 skills 4d ago
Skill Collector 1.3k tok ·
yulonglin/dotfiles
Highly-opinionated setup for AI safety research with coding agents
★ 13 setup Claude CodeCodex 61 skills today
Skill Collector 8.0k tok ·
anomalyco/opencode
The open source coding agent.
★ 212k project Codex 2 skills 1d ago
Pragmatist 4.2k tok ·
copied ✓