agentrigs
+ submit rig
~ / rigs / GeiserX / agent-skills

GeiserX/agent-skills

Skills for Claude Code and Codex: durable goal loops, parallel review, research, investigation and implementation, and research grounded in your own knowledge base

↗ GitHub ★ 4 GPL-3.0 updated 3d ago project Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~2.0k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit GeiserX/agent-skills/.claude ./rig-agent-skills  # 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 GeiserX/agent-skills/codex/skills/docs-loop .claude/skills/docs-loop
$ npx degit GeiserX/agent-skills/codex/skills/eli5 .claude/skills/eli5
$ npx degit GeiserX/agent-skills/codex/skills/implement .claude/skills/implement
$ npx degit GeiserX/agent-skills/codex/skills/investigate .claude/skills/investigate
$ npx degit GeiserX/agent-skills/codex/skills/kb-research .claude/skills/kb-research
$ npx degit GeiserX/agent-skills/codex/skills/kb-review .claude/skills/kb-review
$ npx degit GeiserX/agent-skills/codex/skills/refine-loop .claude/skills/refine-loop
$ npx degit GeiserX/agent-skills/codex/skills/research .claude/skills/research
$ npx degit GeiserX/agent-skills/codex/skills/review-code .claude/skills/review-code
$ npx degit GeiserX/agent-skills/codex/skills/review-pr .claude/skills/review-pr
$ npx degit GeiserX/agent-skills/codex/skills/sergio-loop .claude/skills/sergio-loop

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 (11)

docs-loopeli5implementinvestigatekb-researchkb-reviewrefine-loopresearchreview-codereview-prsergio-loop

Hooks (1)

eventmatcherruns
SessionStart*bd prime --hook-json

Similar rigs

azamkhanuk/context-central
One central place for all the context behind your work in Claude Code: a map that routes each task to the right notes and keeps work in flight in small state files.
★ 1 project Claude Code 7 skills today
Pragmatist 1.5k tok ·
arunpaul-H/coding-agent-harness
Your coding agent's rules, enforced by code instead of prompts. Hooks block bad actions before they run; a committed baseline turns a deleted or skipped test into a red build. Zero dependencies. Hooks for Claude Code, gates for any CI.
★ 0 setup Claude CodeCodex 4 skills 4 agents 4 hooks today
Automator 3.1k tok ·
2found/2build
Product engineering workflows: plan, implement, review, test, QA and release. A 2found product.
★ 0 project Claude CodeCodex 23 skills today
Skill Collector 7.7k tok ·
yamanidev/claude-code-configuration
My personal Claude Code configuration.
★ 5 setup Claude Code 12 skills 4mo ago
Skill Collector 1.8k tok ·
copied ✓