agent-teams
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team…
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
$ npx -y skills add rohitg00/pro-workflow --skill permission-tuner --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/permission-tunerContext preview
The summary Claude sees to decide when to auto-load this skill.
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
name: permission-tuner description: Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials. user-invocable: true
Reduce permission prompt fatigue by analyzing denial patterns and suggesting targeted rules.
Use when:
1. Scan recent session data for permission patterns 2. Identify frequently-approved tools and patterns 3. Generate safe `alwaysAllow` rules 4. Present rules for approval before applying
Check current permission rules:
cat .claude/settings.json 2>/dev/null | grep -A 20 "permissions" cat ~/.claude/settings.json 2>/dev/null | grep -A 20 "permissions"
**Allow-list candidates** (low risk):
**Ask candidates** (medium risk — prompt user every time):
**Deny-list candidates** (high risk):
{
"permissions": {
"allow": [
"Read",
"Glob",
"Grep",
"Bash(git status)",
"Bash(git diff*)",
"Bash(git log*)",
"Bash(npm test*)",
"Bash(npm run lint*)",
"Bash(npm run typecheck*)"
],
"deny": [
"Bash(rm -rf *)",
"Bash(git push --force*)",
"Bash(git reset --hard*)"
]
}
}PERMISSION TUNER REPORT
Current rules: [X] allow, [Y] deny, [Z] ask
Recommendations:
Auto-approve (safe, read-only):
+ Read, Glob, Grep
+ Bash(git status), Bash(git diff*), Bash(git log*)
Auto-approve (medium risk, frequently used):
+ Edit (approved X times this session)
+ Bash(npm test*) (approved X times)
Keep asking:
~ Bash(git commit*) — verify commit messages
~ Write — verify new file creation
Auto-deny (dangerous):
- Bash(rm -rf *)
- Bash(git push --force*)
Estimated prompts saved per session: ~[N]Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
Repo: rohitg00/pro-workflow
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team…
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change…
Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never…
Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual…
Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to…