agentrigs
+ submit rig
~ / rigs / hams-ollo / zen-agent-skills

hams-ollo/zen-agent-skills

This is a portable engineering toolkit, cross-harness AI agent skills library of AI agent workflows that helps teams turn ideas into well-scoped, verifiable software changes, across Claude Code, Copilot, Codex, Cursor, and other coding envi

↗ GitHub ★ 2 MIT updated 28d ago project Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~8.1k tokens
Heavy · 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 hams-ollo/zen-agent-skills/.claude ./rig-zen-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 hams-ollo/zen-agent-skills/.agents/skills/agent-handoff .claude/skills/agent-handoff
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/agent-observatory .claude/skills/agent-observatory
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/doc-author .claude/skills/doc-author
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/doc-revise .claude/skills/doc-revise
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/doc-sync .claude/skills/doc-sync
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/fix-batch .claude/skills/fix-batch
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/house-review .claude/skills/house-review
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/human-handoff .claude/skills/human-handoff
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/init-worktracking .claude/skills/init-worktracking
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/new-task .claude/skills/new-task
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/pr-describe .claude/skills/pr-describe
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/project-bootstrap .claude/skills/project-bootstrap
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/reconcile-worktrees .claude/skills/reconcile-worktrees
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/review-depth .claude/skills/review-depth
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/spec-author .claude/skills/spec-author
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/spec-conformance .claude/skills/spec-conformance
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/spec-plan-readiness .claude/skills/spec-plan-readiness
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/spec-quality .claude/skills/spec-quality
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/systematic-debugging .claude/skills/systematic-debugging
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/test-author .claude/skills/test-author
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/test-quality .claude/skills/test-quality
$ npx degit hams-ollo/zen-agent-skills/.agents/skills/verifier-agent .claude/skills/verifier-agent

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 (22)

agent-handoffagent-observatorydoc-authordoc-revisedoc-syncfix-batchhouse-reviewhuman-handoffinit-worktrackingnew-taskpr-describeproject-bootstrapreconcile-worktreesreview-depthspec-authorspec-conformancespec-plan-readinessspec-qualitysystematic-debuggingtest-authortest-qualityverifier-agent

Hooks (1)

eventmatcherruns
SessionStartstartuppython3 .agents/hooks/skill-reachability-reminder.py || python .agents/hooks/skill-reachability-reminder.py

Similar rigs

fancyboi999/open-tag
Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub Copilot, and more) work as teammates in channels, threads, DMs, and shared tasks. Your data stays o
★ 200 project Claude CodeCodex 1 skills 2 hooks 2mo ago
Pragmatist 4.1k tok ·
Tokiki17/okf-doc-sync
Host-neutral Agent Skill that keeps living docs, agent instruction files, and an OKF knowledge bundle in sync
★ 0 project Codex 1 skills today
Minimalist 884 tok ·
jpicklyk/task-orchestrator
Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. W
★ 207 project Claude Code 29 skills today
Skill Collector 8.5k tok ·
antgrid-ai/antgrid
Agentic Development Environment and E2E-encrypted control plane for coding agents
★ 2 project Claude CodeCodex 1 mcp 3 skills 1 hooks today
Pragmatist 28.5k tok ·
copied ✓