drevendev/HungryCrab
Eat a foreign repository, digest it, and extract everything useful for your own repo without violating licenses.
stack: Python
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 drevendev/HungryCrab/agents ./rig-hungrycrab/agents $ npx degit drevendev/HungryCrab/commands ./rig-hungrycrab/commands $ npx degit drevendev/HungryCrab/skills ./rig-hungrycrab/skills $ npx degit drevendev/HungryCrab/hooks ./rig-hungrycrab/hooks
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 drevendev/HungryCrab/skills/cleanroom .claude/skills/cleanroom $ npx degit drevendev/HungryCrab/skills/eat .claude/skills/eat $ npx degit drevendev/HungryCrab/skills/loop .claude/skills/loop $ npx degit drevendev/HungryCrab/skills/serve .claude/skills/serve
$ curl -fsSL --create-dirs -o .claude/agents/crab-architect.md https://raw.githubusercontent.com/drevendev/HungryCrab/master/agents/crab-architect.md $ curl -fsSL --create-dirs -o .claude/agents/crab-cleanroom-impl.md https://raw.githubusercontent.com/drevendev/HungryCrab/master/agents/crab-cleanroom-impl.md $ curl -fsSL --create-dirs -o .claude/agents/crab-historian.md https://raw.githubusercontent.com/drevendev/HungryCrab/master/agents/crab-historian.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 (4)
Subagents (3)
| crab-architect model: inherit | Compares the architecture sections of the prey and maw digests and proposes at most three structural nutrients with evidence. Use for architecture candidates from crab compare, or when asked how anoth |
| crab-cleanroom-impl model: inherit | Implements a REIMPLEMENT nutrient inside the maw from a code-free clean-room specification, without access to prey source or the Hungry Crab cache. Use only after the cleanroom skill has produced the |
| crab-historian model: inherit | Turns the history and branches sections of a prey digest into 3-7 concrete lessons with evidence. Use for history-lesson candidates from crab compare, or when asked what a repository's commit history |
Slash commands (2)
/menu/sniff
Similar rigs
breezewish/CodexPotter
A better /goal
Minimalist 416 tok · · Q0
gwpicard/ai-loop-kit
[EXPERIMENTAL] A Claude Code plugin that builds software in small steps. A script checks each step, and you merge.
Fort Knox 1.9k tok · · Q37
trevhud/rote
Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop
Pragmatist 39.9k tok · · Q8
IsuruMaduranga/one-code
Claude Code with the model slot left open. The full workflow, open source, on any model or provider.
Pragmatist 1.2k tok · · Q3