GulDmitry/jagt
Local orchestration for AI CLI sessions
field: Developer tools workflow: Git & commitsPlanning & specsPR / code reviewTesting & TDDCI/CD & deploy
stack: Java
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 GulDmitry/jagt/.claude ./rig-jagt # 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 GulDmitry/jagt/.claude/skills/loop-review .claude/skills/loop-review $ npx degit GulDmitry/jagt/.claude/skills/master-lesson .claude/skills/master-lesson $ npx degit GulDmitry/jagt/.claude/skills/release-review .claude/skills/release-review
$ curl -fsSL --create-dirs -o .claude/agents/jagt-implementer.md https://raw.githubusercontent.com/GulDmitry/jagt/main/.claude/agents/jagt-implementer.md $ curl -fsSL --create-dirs -o .claude/agents/jagt-reviewer.md https://raw.githubusercontent.com/GulDmitry/jagt/main/.claude/agents/jagt-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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| jagt-orchestrator | local / custom · remote | 2.5k |
Skills (3)
Subagents (2)
| jagt-implementer model: sonnet | Implements one exact brief on jagt — a fix, a step of a feature, its tests and docs — as one commit on its own branch. Use when the brief names the files, the test proving it and the done command. |
| jagt-reviewer model: opus | Reviews a range of jagt commits in a fresh context, read-only, against AGENTS.md and the specs. Use at a batch's end, given the range, never the reasoning behind it. |
Permissions
deny (0)
—
ask (0)
—
allow (1)
mcp__jagt-orchestrator
Similar rigs
pariveo/salesforce-agent-skills
Audit-first Salesforce Flow skill for Claude Code and Codex
Minimalist 778 tok · · Q0
rshankras/claude-code-apple-skills
Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation, App Store optimization, and more
Skill Collector 2.5k tok · · Q0
nielsmadan/skills
Agent skills for code review, planning, testing, and daily dev workflow
Skill Collector 3.4k tok · · Q0
koutsosg/claude-dotfiles
Portable Claude Code setup — global rules, 25+ skills, DevOps plugins, and install scripts for any machine or project.
Skill Collector 4.0k tok · · Q5