agentrigs
+ submit rig
~ / rigs / Prompthon-IO / agent-systems-handbook

Prompthon-IO/agent-systems-handbook

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and manag

↗ GitHub ★ 317 other updated 2mo ago project Claude Code
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~1.6k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Prompthon-IO/agent-systems-handbook/skills ./rig-agent-systems-handbook/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 Prompthon-IO/agent-systems-handbook/skills/agent-runtime-cache-benchmark .claude/skills/agent-runtime-cache-benchmark
$ npx degit Prompthon-IO/agent-systems-handbook/skills/ai-search-visibility .claude/skills/ai-search-visibility
$ npx degit Prompthon-IO/agent-systems-handbook/skills/business-data-analysis .claude/skills/business-data-analysis
$ npx degit Prompthon-IO/agent-systems-handbook/skills/business-data-structuring .claude/skills/business-data-structuring
$ npx degit Prompthon-IO/agent-systems-handbook/skills/content-strategy .claude/skills/content-strategy
$ npx degit Prompthon-IO/agent-systems-handbook/skills/crm-operations .claude/skills/crm-operations
$ npx degit Prompthon-IO/agent-systems-handbook/skills/daily-news-watcher .claude/skills/daily-news-watcher
$ npx degit Prompthon-IO/agent-systems-handbook/skills/garbage-collector .claude/skills/garbage-collector
$ npx degit Prompthon-IO/agent-systems-handbook/skills/local-document-organizer .claude/skills/local-document-organizer
$ npx degit Prompthon-IO/agent-systems-handbook/skills/personal-knowledge-capture .claude/skills/personal-knowledge-capture
$ npx degit Prompthon-IO/agent-systems-handbook/skills/personal-workflow-automation .claude/skills/personal-workflow-automation
$ npx degit Prompthon-IO/agent-systems-handbook/skills/presentation-template-designer .claude/skills/presentation-template-designer
$ npx degit Prompthon-IO/agent-systems-handbook/skills/price-watcher .claude/skills/price-watcher
$ npx degit Prompthon-IO/agent-systems-handbook/skills/prompt-cache-agent-harness .claude/skills/prompt-cache-agent-harness
$ npx degit Prompthon-IO/agent-systems-handbook/skills/prompthon-social-campaign-manager .claude/skills/prompthon-social-campaign-manager
$ npx degit Prompthon-IO/agent-systems-handbook/skills/safety-escalation-review .claude/skills/safety-escalation-review
$ npx degit Prompthon-IO/agent-systems-handbook/skills/vercel-deploy .claude/skills/vercel-deploy
$ npx degit Prompthon-IO/agent-systems-handbook/skills/web-builder .claude/skills/web-builder
$ npx degit Prompthon-IO/agent-systems-handbook/skills/webapp-testing .claude/skills/webapp-testing

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 (19)

agent-runtime-cache-benchmarkai-search-visibilitybusiness-data-analysisbusiness-data-structuringcontent-strategycrm-operationsdaily-news-watchergarbage-collectorlocal-document-organizerpersonal-knowledge-capturepersonal-workflow-automationpresentation-template-designerprice-watcherprompt-cache-agent-harnessprompthon-social-campaign-managersafety-escalation-reviewvercel-deployweb-builderwebapp-testing

Similar rigs

DesiRichDev/Claude-Cowork-Linkedin-X
Social content agent for LinkedIn and X. Drop in your brand config, research signals, write platform-native posts, review quality, push to Supabase. Built on Claude Code.
★ 2 project Claude CodeCodex 5 skills 7mo ago
Pragmatist 505 tok ·
gzapi-org/agent-fabric
Control plane for the agents working on sibling repositories: identities, roles, memory, model routing, messaging.
★ 0 project Claude Code 6 skills 13 hooks 7d ago
Automator 3.8k tok ·
codeclawd/fable-mode
Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillation (FABLE_CODE.md), measured playbook, verification hooks, and design/MCP/test skills. "Fable 5 Lit
★ 16 project Claude Code 7 skills 3mo ago
Pragmatist 566 tok ·
shikharshikharshikhar/claude-dotfiles
—
★ 0 setup Claude Code 12 skills 5 hooks 1mo ago
Skill Collector 3.2k tok ·
copied ✓