agentrigs
+ submit rig
~ / rigs / ferraroroberto / fleet-config

ferraroroberto/fleet-config

Versioned home for my user-scope Claude Code config: hooks, helpers, and slash commands that shape Claude across the home-stack fleet.

↗ GitHub ★ 1 no license updated today personal setup Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~4.8k tokens
Moderate · 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 ferraroroberto/fleet-config/.claude ./rig-fleet-config  # 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 ferraroroberto/fleet-config/.claude/skills/audit-fleet .claude/skills/audit-fleet
$ npx degit ferraroroberto/fleet-config/.claude/skills/chief .claude/skills/chief
$ npx degit ferraroroberto/fleet-config/.claude/skills/cleanup-fleet-all .claude/skills/cleanup-fleet-all
$ npx degit ferraroroberto/fleet-config/.claude/skills/cleanup-fleet .claude/skills/cleanup-fleet
$ npx degit ferraroroberto/fleet-config/.claude/skills/config-map .claude/skills/config-map
$ npx degit ferraroroberto/fleet-config/.claude/skills/context-audit .claude/skills/context-audit
$ npx degit ferraroroberto/fleet-config/.claude/skills/context-purge .claude/skills/context-purge
$ npx degit ferraroroberto/fleet-config/.claude/skills/design-sweep .claude/skills/design-sweep
$ npx degit ferraroroberto/fleet-config/.claude/skills/fleet-10x .claude/skills/fleet-10x
$ npx degit ferraroroberto/fleet-config/.claude/skills/fleet-health .claude/skills/fleet-health
$ npx degit ferraroroberto/fleet-config/.claude/skills/insights-weekly .claude/skills/insights-weekly
$ npx degit ferraroroberto/fleet-config/.claude/skills/learning-log .claude/skills/learning-log
$ npx degit ferraroroberto/fleet-config/.claude/skills/prompt-audit .claude/skills/prompt-audit
$ npx degit ferraroroberto/fleet-config/.claude/skills/sota-watch .claude/skills/sota-watch
$ npx degit ferraroroberto/fleet-config/.claude/skills/system-map .claude/skills/system-map
$ npx degit ferraroroberto/fleet-config/skills/codebase-audit .claude/skills/codebase-audit
$ npx degit ferraroroberto/fleet-config/skills/design-review .claude/skills/design-review
$ npx degit ferraroroberto/fleet-config/skills/design-sync .claude/skills/design-sync
$ npx degit ferraroroberto/fleet-config/skills/docs-shots .claude/skills/docs-shots
$ npx degit ferraroroberto/fleet-config/skills/e2e-audit .claude/skills/e2e-audit
$ npx degit ferraroroberto/fleet-config/skills/handoff-commit .claude/skills/handoff-commit
$ npx degit ferraroroberto/fleet-config/skills/issue-add .claude/skills/issue-add
$ npx degit ferraroroberto/fleet-config/skills/issue-batch .claude/skills/issue-batch
$ npx degit ferraroroberto/fleet-config/skills/issue-finish-batch .claude/skills/issue-finish-batch
$ npx degit ferraroroberto/fleet-config/skills/issue-finish .claude/skills/issue-finish
$ npx degit ferraroroberto/fleet-config/skills/issue-start .claude/skills/issue-start
$ npx degit ferraroroberto/fleet-config/skills/issue-triage .claude/skills/issue-triage
$ npx degit ferraroroberto/fleet-config/skills/issue-yolo .claude/skills/issue-yolo
$ npx degit ferraroroberto/fleet-config/skills/perf-review .claude/skills/perf-review
$ npx degit ferraroroberto/fleet-config/skills/propagate-vendored .claude/skills/propagate-vendored
$ npx degit ferraroroberto/fleet-config/skills/quick .claude/skills/quick
$ npx degit ferraroroberto/fleet-config/skills/screen .claude/skills/screen
$ npx degit ferraroroberto/fleet-config/stream-deck/.claude/skills/streamdeck-deploy .claude/skills/streamdeck-deploy

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 *)"
    ]
  }
}

Skills (33)

audit-fleetchiefcleanup-fleet-allcleanup-fleetconfig-mapcontext-auditcontext-purgedesign-sweepfleet-10xfleet-healthinsights-weeklylearning-logprompt-auditsota-watchsystem-mapcodebase-auditdesign-reviewdesign-syncdocs-shotse2e-audithandoff-commitissue-addissue-batchissue-finish-batchissue-finishissue-startissue-triageissue-yoloperf-reviewpropagate-vendoredquickscreenstreamdeck-deploy

Slash commands (1)

/restart-webapp

Similar rigs

sebastian-software/dalo
Your team's agent skills, versioned like code.
★ 1 project Claude CodeCodex 2 skills today
Minimalist 976 tok ·
whanksta/Multi-Agent-Setup
One canonical rulebook every AI coding agent reads (Claude Code, Codex, Antigravity) — survives cloud sync, self-heals, audits its own docs.
★ 1 setup Claude CodeCodex 2 skills 1mo ago
Minimalist 885 tok ·
talhayme/claude-plugins
Claude Code plugins built around one idea: AI tooling should be measurable
★ 0 collection Claude Code 3 skills today
Minimalist 257 tok ·
AshwinSathian/workdeck
Run a project as cards: one card per Claude Code session, with a scope gate, a separate review and one pull request.
★ 0 project Claude Code 4 skills today
Minimalist 222 tok ·
copied ✓