decebal/chief-of-staff-v2
A chief of staff with two brains: a Rust CLI over headless Claude Code that briefs you daily, steers your goals weekly, and hands you a ready-to-paste agent handoff for each action.
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 decebal/chief-of-staff-v2/.claude ./rig-chief-of-staff-v2 # 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 decebal/chief-of-staff-v2/.claude/skills/prove-it .claude/skills/prove-it $ npx degit decebal/chief-of-staff-v2/.github/skills/prove-it-review .claude/skills/prove-it-review $ npx degit decebal/chief-of-staff-v2/plugins/chief-of-staff-starter/skills/chief-of-staff-starter .claude/skills/chief-of-staff-starter
$ curl -fsSL --create-dirs -o .claude/agents/tactician.md https://raw.githubusercontent.com/decebal/chief-of-staff-v2/main/.claude/agents/tactician.md 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)
Subagents (1)
| tactician model: sonnet | The user's chief of staff. Goals, this week's deliverables, then today — evidence from approved sources reconciled into a steer per goal and at most three actions that need the user. Use for "what's o |
Similar rigs
SylphxAI/skills
Universal Agent Skills and domain reference standards for Claude Code, Codex, OpenCode, and Agent Skills harnesses
Skill Collector 1.3k tok · · Q0
ravidsrk/open-fleet
Outcome-named autonomous fleets for coding agents across Orca, POSIX, and multi-runtime orchestrators — SHA-bound evidence definition of done, best-of-breed worker recipes, one router per worker.
Skill Collector 3.0k tok · · Q3
ravidsrk/orca-fleet
Outcome-named autonomous fleets for the Orca runtime — SHA-bound evidence definition of done, best-of-breed worker recipes, one router per worker.
Skill Collector 2.7k tok · · Q3
karloows/orchraft
A clan of orcs hauling a solo dev's mundane chores, so the code wins the glory.
Orchestrator 7.2k tok · · Q3