pathmodeio/claude-plugin
Pathmode plugin for Claude Code — MCP server + intent-engineering skill pack. Install: /plugin marketplace add pathmodeio/claude-plugin
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add pathmode -e PATHMODE_<redacted> -- npx -y @pathmode/mcp-server@1.38.0 $ npx degit pathmodeio/claude-plugin/commands ./rig-claude-plugin/commands $ npx degit pathmodeio/claude-plugin/skills ./rig-claude-plugin/skills $ npx degit pathmodeio/claude-plugin/hooks ./rig-claude-plugin/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.
$ claude mcp add pathmode -e PATHMODE_<redacted> -- npx -y @pathmode/mcp-server@1.38.0 $ npx degit pathmodeio/claude-plugin/skills/compile-intent .claude/skills/compile-intent $ npx degit pathmodeio/claude-plugin/skills/grill-intent .claude/skills/grill-intent $ npx degit pathmodeio/claude-plugin/skills/handoff-intent .claude/skills/handoff-intent $ npx degit pathmodeio/claude-plugin/skills/implement-intent .claude/skills/implement-intent $ npx degit pathmodeio/claude-plugin/skills/preflight .claude/skills/preflight $ npx degit pathmodeio/claude-plugin/skills/review-against-intent .claude/skills/review-against-intent $ npx degit pathmodeio/claude-plugin/skills/setup-pathmode-workflow .claude/skills/setup-pathmode-workflow $ npx degit pathmodeio/claude-plugin/skills/split-intent-to-issues .claude/skills/split-intent-to-issues $ npx degit pathmodeio/claude-plugin/skills/verify-intent .claude/skills/verify-intent
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)
| server | source | est. tokens |
|---|---|---|
| @pathmode/mcp-server · "pathmode" env: PATHMODE_API_KEY | npm | 2.5k |
Skills (9)
compile-intentgrill-intenthandoff-intentimplement-intentpreflightreview-against-intentsetup-pathmode-workflowsplit-intent-to-issuesverify-intent
Slash commands (1)
/preflight
Similar rigs
manpreet171/slopguard
Security guardrails for vibe coding. Blocks insecure AI-generated code at the moment it's written - hardcoded secrets, SQL injection, hallucinated packages, and agent supply-chain attacks.
Minimalist 2.4k tok ·
anveo/dotfiles
There's no place like ~/
Pragmatist 2.1k tok ·
ryankanno/dotfiles
All my dotfiles
Automator 2.3k tok ·
mmnto-ai/totem
Rules you can enforce, state you can derive, context you can query: plain files in your repo, under whichever coding agent you use.
Automator 102.9k tok ·