pmall/curation
AI-agent curation harness for Drakkar, a database of virus–human protein–protein interactions.
field: Science & research
stack: Python
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
Copy this rig
# review before running: this installs third-party code
$ npx degit pmall/curation/.claude ./rig-curation # 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 pmall/curation/prompts/skills/curate .claude/skills/curate $ curl -fsSL --create-dirs -o .claude/agents/curator.md https://raw.githubusercontent.com/pmall/curation/master/.claude/agents/curator.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 (1)
| curator | — |
Similar rigs
policani/portable-cross-agent-second-brain-personal
Solo edition of the portable cross-agent second brain — plain markdown, routes to save tokens, no approval gate.
Minimalist 1.8k tok · · Q3
policani/portable-cross-agent-second-brain
A portable, plain-markdown second brain for Claude, Codex, and Cursor — routes to the note it needs to save tokens, with propose-then-approve trust.
Minimalist 1.7k tok · · Q3
tigerless-labs/autoharness
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
Pragmatist 2.6k tok · · Q0
pmall/drakkar
AI-agent curation harness for Drakkar, a database of virus–human protein–protein interactions.
Pragmatist 3.4k tok · · Q18