paulnsorensen/hallouminate
A per-repo markdown wiki your coding agent writes and searches — persistent memory for Claude Code and any MCP harness, stored as plain markdown
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ claude mcp add hallouminate -- hallouminate serve 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.
$ claude mcp add hallouminate -- hallouminate serve $ npx degit paulnsorensen/hallouminate/.agents/skills/rust-analyzer-ssr .claude/skills/rust-analyzer-ssr $ npx degit paulnsorensen/hallouminate/.agents/skills/rust-style .claude/skills/rust-style $ npx degit paulnsorensen/hallouminate/.agents/skills/rustdoc .claude/skills/rustdoc $ npx degit <redacted> .claude/skills/install $ npx degit <redacted>-harvest-memory .claude/skills/wiki-harvest-memory $ npx degit <redacted>-ingest .claude/skills/wiki-ingest $ npx degit <redacted>-init .claude/skills/wiki-init $ npx degit <redacted>-query .claude/skills/wiki-query $ npx degit <redacted>-reindex .claude/skills/wiki-reindex $ npx degit <redacted>-roadmap .claude/skills/wiki-roadmap
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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| hallouminate | binary | 2.5k |
Skills (10)
Similar rigs
boaz-hwang/boaz-wiki
BOAZ Wiki — 문서와 AI 세션으로 만드는 출처 기반 지식 위키 · Markdown, Obsidian, agent skills and versioned human review
Minimalist 422 tok · · Q0
wareagledusty/wiki-federation-starter-kit
A knowledge base your AI keeps current. You feed it sources. It writes linked, cited pages and keeps them up to date. When an answer is worth keeping, you file it back, so your thinking compounds instead of starting over in every new chat.
Pragmatist 4.3k tok · · Q5
zhuzhaoyun/Molio
A local-first personal knowledge layer for AI agents. Build evolving knowledge spaces with LLM Wiki, knowledge graphs, and agent workflows.
Pragmatist 8.7k tok · · Q0
choiyounggi/dev-loop
LLM Knowledge Management • Wiki-grounded verification • RFC-based documentation • Best practices automation • AI-native engineering
Pragmatist 7.5k tok · · Q0