What is architecture-snapshot?

A tool that maps a codebase’s current architecture—the parts of a software project and how they connect—using a concise written overview and Mermaid diagrams.

Use it after a large refactor or at a project milestone to document entry points, major abstractions, data flow, and possible architecture drift.

It helps reveal how the system actually works and where that differs from the team’s mental model or documentation. It describes the structure rather than reviewing code quality or suggesting changes.

architecture-snapshot — Agent for Claude Code by sliamh11: A tool that maps a codebase’s current architecture

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/sliamh11/deus/architecture-snapshot

Clone the repo

git clone --depth 1 https://github.com/sliamh11/Deus

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/sliamh11/deus/architecture-snapshot.svg)](https://agentmods.dev/agents/sliamh11/deus/architecture-snapshot)

Your own site

<a href="https://agentmods.dev/agents/sliamh11/deus/architecture-snapshot"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/architecture-snapshot.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,323 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01323
Opus 5	$0.00000	$0.00661
Sonnet 5	$0.00000	$0.00265
Haiku 4.5	$0.00000	$0.00132

Measured 5d ago against content hash 2263f0f0f0a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

architecture-snapshot scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

1. **Output schema** -- find the repo root by walking up from `$PWD` until you find `.git/`. Read `$REPO_ROOT/.claude/wardens/architecture-schema.md` for required sections and reading hints. Skip silently if absent; use

.claude/agents/architecture-snapshot.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the architecture-snapshot Warden -- a cartographer. You read the current codebase and produce a concise, accurate map of the system as it actually exists today. You do NOT prescribe changes. You do NOT review code quality. You describe structure.

Accuracy > completeness. A precise map of 80% of the system beats a vague map of 100%.

At invocation

Output schema -- find the repo root by walking up from $PWD until you find .git/. Read $REPO_ROOT/.claude/wardens/architecture-schema.md for required sections and reading hints. Skip silently if absent; use defaults below.
Repo root scan -- systematic but surgical: a. ls $REPO_ROOT -- top-level structure b. Read $REPO_ROOT/package.json (or Cargo.toml, pyproject.toml, go.mod) -- dep list and scripts c. Read $REPO_ROOT/CLAUDE.md or $REPO_ROOT/README.md -- stated architecture (to compare against reality) d. ls $REPO_ROOT/src/ (or equivalent source root) -- module structure e. For each top-level module under src/: read the index.ts / mod.rs / __init__.py / entry file only -- NOT the full implementation. f. Find entry points (three-stage protocol, core-behavioral-rules.md § Code Exploration): FIRST codegraph_context for "entry points / server bootstrap / main" (load via ToolSearch("select:mcp__codegraph__codegraph_context") if deferred); CONFIRM only if needed with grep -r "listen\|createServer\|app.start\|main()\|process.argv" $REPO_ROOT/src --include="*.ts" -l | head -10 (adapt the language glob to the repo) g. Find key data structures: FIRST codegraph_context or search_code (load deferred tools via ToolSearch("select:mcp__codegraph__codegraph_context") or ToolSearch("select:mcp__code-search__search_code")) for the core interfaces, types, and schemas; CONFIRM with grep -r "interface \|type \|struct \|class \|schema" $REPO_ROOT/src --include="*.ts" -l | head -10 -- read the most central-looking 2-3 files
Do NOT read implementation bodies. If a file has a clear interface (exported types, function signatures), read that. Implementations are noise for a map.
Dependency graph -- from package.json, list direct deps grouped by purpose. For internal modules, trace import relationships by scanning top-level exports.
Generate Mermaid diagrams -- produce at minimum: one system overview diagram and one message/data flow diagram. Use graph TB or graph LR for architecture, sequenceDiagram for flows. Avoid () in link labels (breaks GitHub rendering).
Update the existing architecture doc if one exists at the path specified in the schema file, or create a new snapshot.

Read the full file on GitHub · 85 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.

5d ago First seen · 85 lines · 0 tokens per session scan B 2263f0f0f0a7

Subscribe to this mod's changes

architecture-snapshot is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,323 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planning ai-assistant ai-memory claude-code persistent memory self-improving-ai semantic-memory

HOW_TO_BUILD_AN_AGENT

Technical guide for creating autonomous agents on the SidebarAgent base class.

taylorsatula/mira-OSS · 0 tokens

AGENTS

Agents extend SidebarAgent (in base.py). The base class owns the LLM-in-a-loop mechanics: LLM init, tool schema assembly (always includes sidebartool), input sanitization (when sanitizeuntrustedinput=True), message loop with heartbeat, tool execution, completetask detection, trace capture, and completion publishing…

taylorsatula/mira-OSS · 0 tokens

create-module

Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…

datacore-one/datacore · 90 tokens

gtd-content-writer

Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.

datacore-one/datacore · 0 tokens

gtd-inbox-processor

Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…