~ / rigs / Zejnilovic / agentic-defaults

Zejnilovic/agentic-defaults

Instructions, agents and skills for coding agents (Claude Code, GitHub Copilot). Test-first, cheap models, context that stays current. Install with agd.

↗ GitHub ★ 1 MIT updated 13d ago project Claude CodeCodex
stack: Python
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~5.6k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 10/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit Zejnilovic/agentic-defaults/kit/.claude ./rig-agentic-defaults  # 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 Zejnilovic/agentic-defaults/kit/.claude/skills/aws .claude/skills/aws
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/commits-and-prs .claude/skills/commits-and-prs
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/context-md .claude/skills/context-md
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/debugging .claude/skills/debugging
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/diagrams .claude/skills/diagrams
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/flask .claude/skills/flask
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/heroku .claude/skills/heroku
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/implementation .claude/skills/implementation
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/project-profile .claude/skills/project-profile
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/project-scan .claude/skills/project-scan
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/react .claude/skills/react
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/relational-database .claude/skills/relational-database
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/research .claude/skills/research
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/session-retro .claude/skills/session-retro
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/spring .claude/skills/spring
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/task-plans .claude/skills/task-plans
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/tdd .claude/skills/tdd
$ npx degit Zejnilovic/agentic-defaults/kit/.claude/skills/terraform .claude/skills/terraform
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/analyst.md
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/developer.md
$ curl -fsSL --create-dirs -o .claude/agents/documenter.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/documenter.md
$ curl -fsSL --create-dirs -o .claude/agents/flask-developer.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/flask-developer.md
$ curl -fsSL --create-dirs -o .claude/agents/react-developer.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/react-developer.md
$ curl -fsSL --create-dirs -o .claude/agents/relational-database-developer.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/relational-database-developer.md
$ curl -fsSL --create-dirs -o .claude/agents/research-collector.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/research-collector.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/researcher.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/security-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/spring-developer.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/spring-developer.md
$ curl -fsSL --create-dirs -o .claude/agents/terraform-developer.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/terraform-developer.md
$ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/Zejnilovic/agentic-defaults/master/kit/.claude/agents/tester.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 (18)

Subagents (14)

analyst
model: haiku
Discovers the lay of the land before planned work. Scans a project to record its purpose, tech stack, structure and commands, or turns a task's notes in .local_context into the discovery part of a pla
architect
model: sonnet
Designs the approach for a change that spans modules, adds a component or dependency, or needs a design decision, and writes it into the task's plan file as steps, diagrams and decisions. Not for smal
developer
model: haiku
Implements a well-defined task or plan steps test-first, in small verified increments. Use for work no framework developer covers (scripts, tools, libraries, infrastructure, other stacks) or small cha
documenter
model: haiku
Keeps documentation true to the code, CONTEXT.md files first, then README and user-facing docs. Use when asked to update, check or write docs, to close a finished plan, or to add CONTEXT.md files to a
flask-developer
model: haiku
Implements well-defined tasks or plan steps in Python Flask backends (endpoints, services, background jobs, integrations) test-first with pytest. Use for Flask work; relational-database-developer hand
react-developer
model: haiku
Implements well-defined tasks or plan steps in React frontends (pages, components, hooks, forms, API calls) test-first with React Testing Library. Use for React work; backend developers handle the API
relational-database-developer
model: haiku
Implements well-defined database tasks or plan steps on relational databases (schema changes, migrations with Alembic, Flyway or Liquibase, indexes, queries, data fixes) safely and test-first. Use for
research-collector
model: haiku
Gathers sources on a question (official docs, release notes, source code, tickets and discussions, write-ups) into notes in .local_context for the researcher or a person. Collects and summarizes; does
researcher
model: sonnet
Answers a question that needs outside knowledge (comparing libraries or approaches, understanding an API, standard or upgrade, checking current practice) with options, a recommendation, confidence and
reviewer
model: sonnet
Reviews a change for real problems (bugs, missing tests for important behavior, stale CONTEXT.md, over-engineering) without nitpicking, and checks that a plan's goal was actually met. Use before commi
security-reviewer
model: sonnet
Reviews a change for exploitable security problems such as injection, broken access control, leaked secrets, weak crypto or risky dependencies, and reports only issues with a plausible attack path. Us
spring-developer
model: haiku
Implements well-defined tasks or plan steps in Java Spring Boot backends (controllers, services, repositories, configuration) test-first with JUnit. Use for Spring work; relational-database-developer
terraform-developer
model: haiku
Implements well-defined infrastructure-as-code tasks or plan steps in Terraform, OpenTofu or Terragrunt (modules, units, resources, variables, tests), checking every change with a plan and never apply
tester
model: haiku
Finds untested behavior that matters in a change or module, writes the missing tests, and reports the bugs they expose. Also turns a bug report into a failing test.

Similar rigs

copied ✓