AgentStack
SKILL verified MIT Self-run

Production Agent Architecture

skill-xuanhieu2611-build-your-own-agents-skill-production-agent-architecture · by xuanhieu2611

Design production-ready AI agents using a loop-based architecture with explicit tools, context, memory, permissions, observability, evaluation, and rollout planning.

No reviews yet
0 installs
13 views
0.0% view→install

Install

$ agentstack add skill-xuanhieu2611-build-your-own-agents-skill-production-agent-architecture

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Production Agent Architecture? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Production Agent Architecture

When To Use This Skill

Use this skill when the task is to:

  • design a new AI agent
  • turn a chatbot idea into a real agent system
  • hand off an agent build to developers or another AI coding agent
  • adapt coding-agent architecture patterns to another domain

Core Rule

Do not design the system as a one-shot chatbot unless the user explicitly asks for that.

Default to a loop-based runtime with:

  1. controller loop
  2. context builder
  3. tool registry
  4. tool executor
  5. session state
  6. permissions and approvals
  7. observability
  8. evaluation
  9. reliability rules
  10. rollout phases

Design Workflow

  1. define the user goal and success condition
  2. define the controller loop
  3. define 2 to 5 domain tools
  4. define context inputs
  5. define session state
  6. define permissions and approval rules
  7. define observability minimums
  8. define evaluation plan
  9. define reliability and retry rules
  10. define rollout phases

Required Output

Always produce all of the following:

# Agent Build Spec

## Domain
## User goal
## Success condition
## Core workflow
## Controller loop
## Context inputs
## Tools
## Session state
## Permissions and approvals
## Stop conditions
## Observability
## Evaluation
## Reliability and failure handling
## Rollout phases
## Future extensions

After the spec, also produce:

  • controller loop pseudocode
  • tool contract table with input, output, side effects, timeout, and permission level
  • session state schema
  • approval matrix
  • failure and retry strategy
  • minimum logs and metrics

Guardrails

  • separate tool schemas from executors
  • treat permissions as runtime policy, not prompt text
  • make approval flows explicit
  • do not pretend a vague idea is production-ready
  • explain the design plainly if the user is learning

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.