agentrigs
+ submit rig
~ / rigs / scaccogatto / okf-skills

scaccogatto/okf-skills

The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.

↗ GitHub ★ 401 mit updated 11d ago collection Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~2.5k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add bundle -- uv run ${CLAUDE_PLUGIN_ROOT}/servers/okf_mcp.py
$ npx degit scaccogatto/okf-skills/skills ./rig-okf-skills/skills

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 bundle -- uv run ${CLAUDE_PLUGIN_ROOT}/servers/okf_mcp.py
$ npx degit scaccogatto/okf-skills/skills/backfill .claude/skills/backfill
$ npx degit scaccogatto/okf-skills/skills/okf .claude/skills/okf
$ npx degit scaccogatto/okf-skills/skills/validate .claude/skills/validate
$ npx degit scaccogatto/okf-skills/skills/visualize .claude/skills/visualize

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)

serversourceest. tokens
${claude_plugin_root}/servers/okf_mcp.py · "bundle" pypi 2.5k

Skills (4)

backfillokfvalidatevisualize

Similar rigs

display-dev/skill
Public agent skill for display.dev — publish HTML or Markdown behind company auth from your AI assistant. Works across Claude Code, Cursor, Codex, OpenCode, Hermes, Pi, and OpenClaw.
★ 12 collection Claude Code 1 mcp 2 skills 4d ago
Pragmatist 2.5k tok ·
liormesh/trestle
Scaffold a complete Claude Code AI workspace in 5 minutes. Brain, Skills, Context — the three legs your AI setup needs.
★ 2 project Claude Code 4 skills 2mo ago
Minimalist 327 tok ·
yxtay/dotfiles
dotfiles, managed with https://www.chezmoi.io/
★ 1 setup Claude CodeCodex 5 skills today
Pragmatist 1.5k tok ·
bpenwell/claude-config
Portable Claude Code setup: settings, hooks, skills, and templated MCP servers with a one-command installer
★ 0 setup Claude Code 6 skills 24d ago
Pragmatist 290 tok ·
copied ✓