frankieramirez/mana
Agent skills I use across projects: multi-reviewer review, planning maps, inbox triage, and prose that sounds like a person. Claude Code plugin and skills.sh source.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ npx degit frankieramirez/mana/agents ./rig-mana/agents $ npx degit frankieramirez/mana/skills ./rig-mana/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 frankieramirez/mana/skills/attune .claude/skills/attune $ npx degit frankieramirez/mana/skills/augur .claude/skills/augur $ npx degit frankieramirez/mana/skills/banish .claude/skills/banish $ npx degit frankieramirez/mana/skills/cast .claude/skills/cast $ npx degit frankieramirez/mana/skills/conjure .claude/skills/conjure $ npx degit frankieramirez/mana/skills/dispel .claude/skills/dispel $ npx degit frankieramirez/mana/skills/leyline .claude/skills/leyline $ npx degit frankieramirez/mana/skills/mend .claude/skills/mend $ npx degit frankieramirez/mana/skills/mimic .claude/skills/mimic $ npx degit frankieramirez/mana/skills/portal .claude/skills/portal $ npx degit frankieramirez/mana/skills/remedy .claude/skills/remedy $ npx degit frankieramirez/mana/skills/reveal .claude/skills/reveal $ npx degit frankieramirez/mana/skills/scan .claude/skills/scan $ npx degit frankieramirez/mana/skills/scry .claude/skills/scry $ npx degit frankieramirez/mana/skills/setup-mana .claude/skills/setup-mana $ npx degit frankieramirez/mana/skills/sift .claude/skills/sift $ npx degit frankieramirez/mana/skills/ultima .claude/skills/ultima $ npx degit frankieramirez/mana/skills/vision .claude/skills/vision $ npx degit frankieramirez/mana/skills/ward .claude/skills/ward
$ curl -fsSL --create-dirs -o .claude/agents/comment-reaper.md https://raw.githubusercontent.com/frankieramirez/mana/main/agents/comment-reaper.md $ curl -fsSL --create-dirs -o .claude/agents/ghost.md https://raw.githubusercontent.com/frankieramirez/mana/main/agents/ghost.md $ curl -fsSL --create-dirs -o .claude/agents/weaver.md https://raw.githubusercontent.com/frankieramirez/mana/main/agents/weaver.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 (19)
attuneaugurbanishcastconjuredispelleylinemendmimicportalremedyrevealscanscrysetup-manasiftultimavisionward
Subagents (3)
| comment-reaper | Deletes comments that do not earn their place and flags the code they were covering for. Report-only on code; edits comments only. Generated from skills/banish/references/comment-reaper.md, do not edi |
| ghost | Builds a voice profile from the user's own writing (session messages, PR comments, PR descriptions, commits) and returns a filled-in draft with the evidence. Read-only; never writes the profile. Gener |
| weaver | Resolves conflict hunks in an in-progress merge, rebase, cherry-pick, or revert. Keeps both intents when they fit. Edits conflicted files only; never aborts or commits. Generated from skills/mend/refe |
Similar rigs
AThevon/genjutsu
Creative coding skills for Claude Code, claude.ai and Cowork. Motion, micro-interactions and design systems across Web (GSAP, Motion, Three.js, CSS), Android (Jetpack Compose) and Apple (SwiftUI). Proposes an interaction thesis you approve
Minimalist 210 tok · · Q0
cfgaudit/cfgaudit
Static security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. SARIF output, OWASP LLM Top 10 mapping.
Minimalist 482 tok · · Q0
zhixuli0406/vettalon
Multi-model security audit for your own code: AI models from different vendors find bugs, a different-vendor model tries to refute each one. Local-first, bring your own model.
Minimalist 68 tok · · Q0
usmanmanii/realitygate
RealityGate: prove your AI-written code is real. Reality Score (0–100) for vibe-coded apps, a CI gate that blocks stubs, fake data, hallucinated npm packages & leaked secrets, a malware scanner for AI skills/plugins, and a spec-driven build
Pragmatist 745 tok · · Q8