~ / rigs / enojen / tenbox

enojen/tenbox

One task from plan to merge with Claude Code

↗ GitHub ★ 2 Apache-2.0 updated 11d ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~5.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit enojen/tenbox/agents ./rig-tenbox/agents
$ npx degit enojen/tenbox/skills ./rig-tenbox/skills
$ npx degit enojen/tenbox/hooks ./rig-tenbox/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 enojen/tenbox/skills/tenbox .claude/skills/tenbox
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/enojen/tenbox/main/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/enojen/tenbox/main/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/runner.md https://raw.githubusercontent.com/enojen/tenbox/main/agents/runner.md
$ curl -fsSL --create-dirs -o .claude/agents/worker.md https://raw.githubusercontent.com/enojen/tenbox/main/agents/worker.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 (1)

Subagents (4)

planner
model: opus
Plans one Tenbox task. Reads the task, the code and the spec, then writes .tenbox/plan.md as free text, the part files and the open questions, and returns the examples and decision cards. Also lists t
reviewer
model: sonnet
Reviews a Tenbox task diff against its plan through one lens. Reports must_fix items, nice_to_have items, unproven parts, the hunks a human must read and findings outside the task. Never edits.
runner
model: sonnet
Runs exactly one tenbox CLI command and returns its JSON output unchanged. Use for tenbox check, tenbox pr, tenbox sandbox and other deterministic commands inside a workflow.
worker
model: sonnet
Builds one part of a Tenbox task. Writes the code and unit tests for that part, commits, runs tenbox check, and records the result in the part file. Never touches files owned by another part or listed

Similar rigs

copied ✓