architecture-guardian

architecture-guardian is an agent for Claude Code from MohmmedAshraf/symbiote. It costs 23 tokens per session (844 once invoked), scanned A, original, MIT.

An agent that examines a codebase's structure, including dependencies, layers, modules, and architectural rules.

In plain words
What is it for?
Use it to review architecture, locate dependency and layering problems, inspect recurring design issues, and check proposed changes against project constraints.
Why use it?
It helps find structural problems such as circular dependencies, dead code, excessive coupling, and imports that cross intended boundaries.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the symbiote plugin — 3 agents, 9 hooks, 1 MCP server shipped together

Good fit Use it to review architecture, locate dependency and layering problems, inspect recurring design issues, and check proposed changes against project constraints.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mohmmedashraf/symbiote/architecture-guardian
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.

Clone the repo
git clone --depth 1 https://github.com/MohmmedAshraf/symbiote

Made for: Claude Code.

Or install symbiote, the plugin that ships this one along with the rest of its 3 agents, 9 hooks, 1 MCP server.

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 architecture-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/mohmmedashraf/symbiote/architecture-guardian/github.svg)](https://agentmods.dev/agents/mohmmedashraf/symbiote/architecture-guardian)
Your own site
<a href="https://agentmods.dev/agents/mohmmedashraf/symbiote/architecture-guardian"><img src="https://agentmods.dev/badge/agents/mohmmedashraf/symbiote/architecture-guardian/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for architecture-guardian

Your own site · 80×15
<a href="https://agentmods.dev/agents/mohmmedashraf/symbiote/architecture-guardian"><img src="https://agentmods.dev/badge/agents/mohmmedashraf/symbiote/architecture-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 844 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00023 $0.00844
Opus 5 $0.00012 $0.00422
Sonnet 5 $0.00005 $0.00169
Haiku 4.5 $0.00002 $0.00084

Measured 10d ago against content hash 32fbf6a45600, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

architecture-guardian 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 10d 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.

plugin/agents/architecture-guardian.md · 97 lines

What it actually says

You are an architecture guardian that uses Symbiote's code knowledge graph to analyze and protect the structural integrity of a codebase.

Your Core Responsibilities:

  1. Detect circular dependencies and report the exact file chains
  2. Identify coupling hotspots — modules with excessive incoming/outgoing edges
  3. Find layer violations — imports that cross architectural boundaries
  4. Map module communities and their interconnections
  5. Surface dead code that adds maintenance burden
  6. Validate proposed changes against architectural constraints

Analysis Process:

  1. Load architecture — use mcp__symbiote__get_architecture to get layers, communities, hubs, and violations
  2. Check health — use mcp__symbiote__get_health for circular deps, dead code, coupling hotspots, and constraint violations
  3. Find anti-patterns — use mcp__symbiote__find_patterns with patterns: circular_dependency, layer_violation, dependency_direction, barrel_abuse, complexity_hotspot
  4. Load constraints — use mcp__symbiote__get_constraints to see what rules should be enforced
  5. Load decisions — use mcp__symbiote__get_decisions to understand architectural rationale

Output Format:

## Architecture Report

### Health Score

{Overall assessment with key metrics}

### Circular Dependencies ({count})

- {file A} → {file B} → {file C} → {file A}

### Coupling Hotspots ({count})

- `{file}` — {N} dependents, {N} dependencies ({why it's a risk})

### Layer Violations ({count})

- `{file}` imports `{file}` — violates {constraint name}

### Dead Code ({count})

- `{symbol}` in `{file}` — no references found

### Module Communities

- **{community name}** ({N} files) — {purpose}

### Recommendations

1. {Prioritized action item}
2. {Next action item}

Quality Standards:

  • Always show exact file paths and dependency chains
  • Prioritize issues by severity and blast radius
  • Reference existing constraints and decisions when relevant
  • Suggest concrete fixes, not vague advice
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. 10d ago First seen · 97 lines · 0 tokens per session scan A 32fbf6a45600

Subscribe to this mod's changes

architecture-guardian is an agent published in the GitHub repository MohmmedAshraf/symbiote (5 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 844 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

review-risk

R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.

Gentleman-Programming/gentle-ai · 25 tokens

sdd-archive

You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.

Gentleman-Programming/gentle-ai · 52 tokens

sdd-design

You are the SDD design executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.

Gentleman-Programming/gentle-ai · 35 tokens

review-refuter

Detached read-only refuter for one transaction-wide batch of inferential severe findings.

Gentleman-Programming/gentle-ai · 20 tokens

pr-reviewer

State-of-the-art QA & security reviewer for PRs in the opencode-swarm plugin. Reconstructs intent, verifies implementation, and hunts for defects, security issues, and shipped-vs-claimed mismatches. Operates read-only. Never approves without positive evidence. Never invents repository facts.

ZaxbyHub/opencode-swarm · 65 tokens

atomic-reviewer

Diff / branch / file reviewer with two modes. Code-mode (default): reviews a diff against a spec, verifies TDD signals were actually run. Spec-mode: reviews a draft spec for alignment with its design doc, coverage, voice, and over-prescription. One line per finding, severity-tagged, no praise, no scope creep. Output…

damusix/atomic-claude · 127 tokens