agentrigs
+ submit rig
~ / rigs / drader / researcher_agent

drader/researcher_agent

An LLM-driven research assistance framework for Claude Code (CC BY-NC 4.0)

↗ GitHub ★ 2 NOASSERTION updated 5mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.9k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit drader/researcher_agent/commands ./rig-researcher_agent/commands
$ npx degit drader/researcher_agent/skills ./rig-researcher_agent/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 drader/researcher_agent/skills/compose .claude/skills/compose
$ npx degit drader/researcher_agent/skills/critique .claude/skills/critique
$ npx degit drader/researcher_agent/skills/orchestrate .claude/skills/orchestrate
$ npx degit drader/researcher_agent/skills/research .claude/skills/research

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (4)

composecritiqueorchestrateresearch

Slash commands (24)

/compose-abstract/compose-citation-check/compose-disclosure/compose-format/compose-full/compose-lit-section/compose-outline/compose-revision-triage/compose-revision/critique-calibration/critique-full/critique-guided/critique-methodology/critique-quick/critique-re-review/orchestrate-pipeline/orchestrate-resume/research-annotate/research-brief/research-evaluate/research-full/research-socratic/research-systematic/research-verify

Similar rigs

SynaLinks/synalinks
Keras based framework for neuro-symbolic LM systems
★ 462 project Claude CodeCodex 1 skills 14d ago
Minimalist 840 tok ·
snaplyze/claude-orchestration
Claude Code plugin for orchestration: five specialist subagents with explicit model and effort, subscription profiles, user-scope install, and runtime verification
★ 0 project Codex 1 skills today
Pragmatist 3.2k tok ·
GiaSip/giasip-skills
Turn research questions into reports with source links and open questions: Research for Codex and Claude Code, plus multi-model dispatch tooling for Claude Code.
★ 13 collection Claude Code 3 skills 11d ago
Minimalist 248 tok ·
Dart-ilder/claude-config
My Claude Code configuration: custom skills, slash commands, settings, and proxy setup guide
★ 1 setup Claude Code 3 skills 7mo ago
YOLO Cowboy 424 tok ·
copied ✓