andreiciobotar/isshoni
A self-improving software factory for Claude Code, with a live terminal dashboard. Looks delightful.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit andreiciobotar/isshoni/.claude ./rig-isshoni # 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 andreiciobotar/isshoni/.claude/skills/coding-taste .claude/skills/coding-taste $ npx degit andreiciobotar/isshoni/factory/skills/dispatch .claude/skills/dispatch
$ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/andreiciobotar/isshoni/main/.claude/agents/coder.md $ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/andreiciobotar/isshoni/main/.claude/agents/explorer.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/andreiciobotar/isshoni/main/.claude/agents/reviewer.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 (2)
Subagents (3)
| coder model: sonnet | Implements a well-scoped, already-planned change. Use when the plan names the files and the expected behavior. Not for open-ended design. |
| explorer model: haiku | Fast read-only codebase search. Use to locate files, symbols, call sites, config, or data formats. Returns evidence (paths, line numbers, short excerpts), not conclusions. Do NOT use for design judgme |
| reviewer model: opus | Strict review of a finished change against its plan. Use after the coder finishes and before reporting done. Give it the plan and tell it to read the actual diff. |
Similar rigs
jaqubowsky/fleet
Runs Claude Code and pi agents in parallel on your Mac, one Docker sandbox per issue. A host agent hands out the work, watches every sandbox and brings back tested, reviewed pull requests.
Minimalist 566 tok · · Q0
AegeanWorks/AIKit
Crash-resilient governance and delivery gates for AI coding agents: versioned task ledger, commit-level verification, secret scanning and per-project gates. Free for personal use under AL-1.1; commercial use under ACL-1.0.
Orchestrator 4.2k tok · · Q23
Rusty-Alucard/ai-dev-base
AI-driven development base template — reusable patterns for multi-agent Claude Code workflows
Pragmatist 1.3k tok · · Q5
MyrskyDev/claude-agent-template
Multi-agent dev workflow template for Claude Code
Pragmatist 195 tok · · Q0