~ / rigs / Tamircohen28 / tamirs-superpowers

Tamircohen28/tamirs-superpowers

A portable agent toolkit — 31 skills, 10 specialist agents, worktree hooks and MCP stubs — shipped from one canonical source to six agent surfaces across five platforms: Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI and OpenCode.

↗ GitHub ★ 2 MIT updated 13d ago project Claude CodeCodexCursorGemini CLI Claude plugin
stack: PythonShell
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~7.0k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details
Quality 18/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit Tamircohen28/tamirs-superpowers/.claude ./rig-tamirs-superpowers  # 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 Tamircohen28/tamirs-superpowers/.claude/skills/run-tamirs-superpowers .claude/skills/run-tamirs-superpowers
$ curl -fsSL --create-dirs -o .claude/agents/architecture-reviewer.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/architecture-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/debugging-specialist.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/debugging-specialist.md
$ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/integrator.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/integrator.md
$ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/orchestrator.md
$ curl -fsSL --create-dirs -o .claude/agents/performance-reviewer.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/performance-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/research-agent.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/research-agent.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/security-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/spec-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/test-engineer.md https://raw.githubusercontent.com/Tamircohen28/tamirs-superpowers/master/agents/test-engineer.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 *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
github
env: GITHUB_PERSONAL_ACCESS_TOKEN
local / custom 2.5k

Skills (1)

Subagents (10)

architecture-reviewer
model: sonnet
Reviews architecture for unnecessary complexity, tight coupling, and layering violations, and proposes concrete simplifications. Use when adding a subsystem, before a large refactor, or when code feel
debugging-specialist
model: sonnet
Root-cause analysis for bugs, test failures, and unexpected behavior — reproduces, isolates, and finds the true cause before proposing a fix. Use for any non-trivial bug or a failure that recurred.
implementer
model: sonnet
Executes exactly one scoped task — changes code inside its scope, runs targeted validation, commits, and returns a structured handoff. Ends at commit, never at a pull request. Use for a single unit of
integrator
model: sonnet
Assembles completed worker branches into one integration branch, resolves conflicts, runs integration-level validation, and applies fixes review demands. Use once an objective's tasks are done and the
orchestrator
model: sonnet
Owns a multi-task objective end to end — builds the task graph, dispatches roles in dependency order, tracks handoffs, and drives integration to a single delivery. Use when a request needs more than o
performance-reviewer
model: sonnet
Finds performance bottlenecks and concrete optimization opportunities (hot paths, N+1 queries, unnecessary work, bundle/render cost). Use when something is slow or before shipping a perf-sensitive pat
research-agent
model: sonnet
Verifies library/API/framework details against current documentation before you rely on them — prevents outdated-pattern and hallucinated-API mistakes. Use when unsure of an API signature, config opti
security-reviewer
model: sonnet
Reviews changes for vulnerabilities, leaked secrets, and over-broad permissions. Use before merging anything touching auth, input handling, secrets/env, IAM/permissions, or external I/O.
spec-reviewer
model: sonnet
Reviews the combined integrated diff for completeness and correctness against the stated objective — did it do what was asked, all of it, and nothing extra. Use before delivery, after integration, and
test-engineer
model: sonnet
Generates focused tests, analyzes coverage gaps, and adds regression tests for fixed bugs. Use after implementing a feature/fix, or when coverage of a critical path is thin.

Cursor rules (13)

commit-conventionscross-platform-handoffdev-files-workspace · alwaysgh-cli-preferencegit-worktree-agent-workflowgithub-repository-policyhooks-guideplugin-structure · alwaysplugin-version-bumpskill-frontmatterskill-quality-standardsskills-guideuser-facing-script-standards

Similar rigs

copied ✓