~ / rigs / iuliandita / agents

iuliandita/agents

Global prompts and subagent roles for coding agents, deployed to every harness you use.

↗ GitHub ★ 5 MIT updated 4d ago collection Claude CodeCodex
field: Developer tools workflow: Docs
stack: Python
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.5k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 3/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit iuliandita/agents/agents ./rig-agents/agents
$ npx degit iuliandita/agents/skills ./rig-agents/skills

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 iuliandita/agents/skills/consolidate-agents-md .claude/skills/consolidate-agents-md
$ curl -fsSL --create-dirs -o .claude/agents/builder.md https://raw.githubusercontent.com/iuliandita/agents/develop/agents/builder.md
$ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/iuliandita/agents/develop/agents/explorer.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/iuliandita/agents/develop/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/iuliandita/agents/develop/agents/researcher.md
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/iuliandita/agents/develop/agents/reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/iuliandita/agents/develop/agents/verifier.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 (6)

builderBounded editor for a specified change to named files with named check commands. Returns a diff receipt. Refuses design decisions and unnamed files.
explorerRead-only code locator. Use for where is X defined, what calls Y, list uses of Z, map this directory. Returns path:line rows. Never edits.
plannerRead-only planner. Turns a task into ordered steps with files, verification commands, risks, and stop conditions.
researcherRead-only docs and web researcher. Use for current API shapes, config keys, version changes. Returns a cited brief.
reviewerReviews a diff, branch, or files for bugs, regressions, edge cases, and security issues. One severity-tagged line per finding. No praise.
verifierRuns named lint, test, typecheck, or build commands and reports exit codes, a classification, and a redacted excerpt. Never fixes.

Similar rigs

copied ✓