d10or/workspace-guardian
Preflight coordination for parallel Claude Code sessions on one repo: task-level path ownership, overlap checks before merging, evidence-based handoff. CLI + Claude Code mod.
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code
$ npx degit d10or/workspace-guardian/.claude ./rig-workspace-guardian # 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 d10or/workspace-guardian/.claude/skills/checkpoint .claude/skills/checkpoint $ npx degit d10or/workspace-guardian/.claude/skills/gate .claude/skills/gate $ npx degit d10or/workspace-guardian/.claude/skills/resume .claude/skills/resume
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (3)
Hooks (1)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | bash "$CLAUDE_PROJECT_DIR/scripts/session-context.sh" |
Similar rigs
radozaprazny/attest
A Claude Code kit: a push guard that holds a push until a leak scan and one audit have cleared HEAD.
Automator 276 tok · · Q15
SatymSingh01/claude-code-pack
Drop-in config pack for Claude Code: CLAUDE.md best practices, safety hooks, auto-checkpoint, session logging, and slash commands. One install script.
Minimalist 344 tok · · Q3
Cairn-ink/cairn-memory
Cairn.ink Memory: lightweight cross-session memory for AI agents, with receipts.
Pragmatist 2.6k tok · · Q0
jovesun-lab/arcgram
Arcgram — an interactive diagram engine for human–AI collaboration: an AI agent draws its reasoning as an auditable node-and-edge flow and self-audits it, delivered as one standalone HTML file. (Arcgram the AI diagram tool — not Archigram.)
Minimalist 31 tok · · Q0