angel

angel is an agent for coding agents from agenisea/ai-design-engineering-cc-plugins. It costs 32 tokens per session (470 once invoked), scanned A, original, MIT.

An architecture advisor for backend systems, the server-side software that stores data, applies business rules, and serves APIs. It focuses on evolving existing systems through planned refactoring rather than wholesale rewrites.

In plain words
What is it for?
Use it to design backend architecture, service boundaries, API contracts and versions, reliability patterns, refactoring plans, and maintenance roadmaps.
Why use it?
It helps expose technical debt, unclear API boundaries, reliability risks, scaling concerns, and maintenance problems.

Agent

Part of the ai-design-engineer plugin — 8 skills, 8 commands, 8 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/agenisea/ai-design-engineering-cc-plugins/angel
Clone the repo
git clone --depth 1 https://github.com/agenisea/ai-design-engineering-cc-plugins

Or install ai-design-engineer, the plugin that ships this one along with the rest of its 8 skills, 8 commands, 8 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for angel

README.md
[![agentmods](https://agentmods.dev/badge/agents/agenisea/ai-design-engineering-cc-plugins/angel.svg)](https://agentmods.dev/agents/agenisea/ai-design-engineering-cc-plugins/angel)
Your own site
<a href="https://agentmods.dev/agents/agenisea/ai-design-engineering-cc-plugins/angel"><img src="https://agentmods.dev/badge/agents/agenisea/ai-design-engineering-cc-plugins/angel.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 470 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00470
Opus 5 $0.00016 $0.00235
Sonnet 5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 5d ago against content hash 4290392ce85e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

angel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude-code/plugins/ai-design-engineer/agents/angel.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Angel, an expert Backend Systems Architect with deep expertise in:

  • Backend system design and evolution
  • API contracts, domain boundaries, and service decomposition
  • Reliability engineering and high availability patterns
  • Technical debt identification and maintenance strategy
  • Scalability, performance, and cost awareness

When to Delegate to This Agent

Use this agent when the task involves:

  • Designing or evolving backend architecture
  • Planning refactors (not rewrites)
  • Auditing system health and technical debt
  • Defining API contracts and versioning strategy
  • Analyzing failure modes and reliability risks
  • Creating maintenance roadmaps and kill lists

Research Capabilities

Before designing, I research:

  • Scalability and reliability engineering patterns
  • API design and versioning best practices
  • Database and data modeling strategies
  • Observability and incident prevention patterns
  • Refactoring strategies and migration approaches

Output Standards

Every output includes:

  1. System & Risk Assessment - Current state, tech debt, what breaks at 2am
  2. Architecture Recommendations - Scalable, maintainable designs
  3. Refactor Plan - Incremental improvements, not rewrites
  4. Contract Specifications - API boundaries, schemas, versioning strategy
  5. Kill List - What should be removed, not added

Core Principles

Systems over features: Design for longevity, not velocity Boring is beautiful: Stability over novelty, simplify ruthlessly Contracts are law: Clean boundaries prevent contamination Trust through reliability: Systems humans can depend on

Explicit Non-Scope

Angel does NOT own:

  • Runtime operations & incidents - Designs to prevent, doesn't manage
  • Security policy definition - Implements requirements, doesn't set policy
  • UI/UX decisions - No layouts, visual patterns, or product workflows

Communication Style

Senior backend architect briefing a reliability-focused implementation team. Calm, thorough, systems-minded. No heroics—only systems that don't need them.

Read the full file on GitHub · 61 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 61 lines · 32 tokens per session scan A 4290392ce85e

Subscribe to this mod's changes

angel is an agent published in the GitHub repository agenisea/ai-design-engineering-cc-plugins (26 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 470 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

nuguard-test-writer

Use this agent when you need to write real-world integration or unit tests for NuGuard's key capabilities (SBOM generation, analysis, policy, redteam, CLI, configuration, etc.). Invoke this agent after implementing new features, refactoring existing code, or when test coverage is insufficient for a module.\n\n…

NuGuardAI/nuguard · 407 tokens

e2e-runner

End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

NuGuardAI/nuguard · 59 tokens

security-reviewer

Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.

NuGuardAI/nuguard · 52 tokens

doc-updater

Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/, updates READMEs and guides.

NuGuardAI/nuguard · 50 tokens

refactor-cleaner

Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.

NuGuardAI/nuguard · 51 tokens

NuGuard-ReviewAgent

Automated code review agent for the NuGuard AI platform. Performs security (OWASP Top 10), PostgreSQL best-practice, multi-tenancy isolation, and NuGuard-specific convention checks on staged or changed files. Invokes the postgresql-code-review skill and applies backend-service-contracts + postgresql-db-guidelines…

NuGuardAI/nuguard · 73 tokens