~ / rigs / brignano / ai-tools

brignano/ai-tools

Personal AI tooling library — reusable prompts, agent definitions, and system instructions

↗ GitHub ★ 0 MIT updated 4d ago personal setup Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~2.0k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 3/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit brignano/ai-tools/agents ./rig-ai-tools/agents
$ npx degit brignano/ai-tools/commands ./rig-ai-tools/commands
$ npx degit brignano/ai-tools/skills ./rig-ai-tools/skills
$ npx degit brignano/ai-tools/hooks ./rig-ai-tools/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.

$ npx degit brignano/ai-tools/skills/design-system .claude/skills/design-system
$ npx degit brignano/ai-tools/skills/fleet-standard .claude/skills/fleet-standard
$ npx degit brignano/ai-tools/skills/hosting .claude/skills/hosting
$ npx degit brignano/ai-tools/skills/leads .claude/skills/leads
$ npx degit brignano/ai-tools/skills/releases .claude/skills/releases
$ npx degit brignano/ai-tools/skills/reverse-engineer-anything .claude/skills/reverse-engineer-anything
$ npx degit brignano/ai-tools/skills/ux-review .claude/skills/ux-review
$ curl -fsSL --create-dirs -o .claude/agents/Explore.md https://raw.githubusercontent.com/brignano/ai-tools/main/agents/Explore.md
$ curl -fsSL --create-dirs -o .claude/agents/codex-builder.md https://raw.githubusercontent.com/brignano/ai-tools/main/agents/codex-builder.md
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/brignano/ai-tools/main/agents/implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/brignano/ai-tools/main/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/test-runner.md https://raw.githubusercontent.com/brignano/ai-tools/main/agents/test-runner.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 (7)

Subagents (5)

Explore
model: haiku
Fast read-only codebase search. Use when answering means sweeping many files, directories or naming conventions and only the conclusion matters — where something is defined, which files touch a featur
codex-builder
model: sonnet
Hands one concrete build step to OpenAI Codex (`codex exec`, sandbox on) in an isolated git worktree and returns the diff for the caller to review. Use only when the Claude weekly limit is running low
implementer
model: sonnet
Carries out one concrete, already-planned implementation step (edit these files to do X, then run the tests) on a cheaper model. Use proactively once a plan or TSD is approved — hand each well-specifi
reviewer
model: opus
Independent pre-merge review of one fleet PR. The builder starts it once CI is green, passing only the PR number and its issue. Read-only; returns APPROVE or CHANGES with file, line and fix.
test-runner
model: haiku
Runs a project's tests, linter, type-checker or build and returns only what failed. Use proactively after changes when the output would be long, so the main conversation gets the failures instead of t

Slash commands (11)

/app-preview-deploy/handoff/homelab-health-check/merge-it/new-repo/new-tsd/next/plan-new-service/review-docker-compose/review-pr/write-setup-log

Similar rigs

copied ✓