agentrigs
+ submit rig
~ / rigs / markmdev / meridian

markmdev/meridian

Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after compaction, plug-in code standards, optional TDD mode, and zero behavior changes for developers.

↗ GitHub ★ 138 no license updated 7mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~296 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit markmdev/meridian/skills ./rig-meridian/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.

$ npx degit markmdev/meridian/skills/add-frontmatter .claude/skills/add-frontmatter
$ npx degit markmdev/meridian/skills/create-docs .claude/skills/create-docs
$ npx degit markmdev/meridian/skills/error-audit .claude/skills/error-audit
$ npx degit markmdev/meridian/skills/observability-audit .claude/skills/observability-audit
$ npx degit markmdev/meridian/skills/planning .claude/skills/planning
$ npx degit markmdev/meridian/skills/ux-states-audit .claude/skills/ux-states-audit

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "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(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Skills (6)

add-frontmattercreate-docserror-auditobservability-auditplanningux-states-audit

Similar rigs

jon-greeff-katsini/outside-dave
—
★ 2 project Claude Code 4 skills 28d ago
Minimalist 1.4k tok ·
grumps/claude-dotfiles
—
★ 0 setup Claude Code 5 skills 8mo ago
Pragmatist 1.0k tok ·
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 ·
LongTermSupport/fedora-desktop
Taking a freshly installed Fedora desktop and getting it ready for development
★ 6 project Claude Code 7 skills 4 agents 30 hooks today
Automator 30.8k tok ·
copied ✓