architecture_lens

architecture_lens is a skill for Claude Code, Codex from chama-x/GroundRules. It costs 25 tokens per session (257 once invoked), scanned A, original, MIT.

A method for drawing a simple dependency map of an unfamiliar codebase. It focuses on how data moves, how application state is managed, and how main routes connect.

In plain words
What is it for?
Use it to create Mermaid diagrams showing the main frontend, state, API, database, and routing relationships, with a short summary of important structural issues.
Why use it?
It turns a large codebase into a smaller diagram that is easier to understand, without filling the map with every helper or user-interface detail.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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 skills/chama-x/groundrules/architecture_lens
Any agent
npx skills add chama-x/GroundRules --skill architecture_lens
Clone the repo
git clone --depth 1 https://github.com/chama-x/GroundRules

Made for: Claude Code, Codex.

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_lens

README.md
[![agentmods](https://agentmods.dev/badge/skills/chama-x/groundrules/architecture_lens.svg)](https://agentmods.dev/skills/chama-x/groundrules/architecture_lens)
Your own site
<a href="https://agentmods.dev/skills/chama-x/groundrules/architecture_lens"><img src="https://agentmods.dev/badge/skills/chama-x/groundrules/architecture_lens.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 257 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 5.1 $0.00025 $0.00257
Opus 5 $0.00013 $0.00129
Sonnet 5 $0.00005 $0.00051
Haiku 4.5 $0.00003 $0.00026

Measured 6d ago against content hash 9366c7cd09e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

architecture_lens 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_diagram.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/architecture_lens/SKILL.md · 23 lines

What it actually says

Architecture Lens Configuration

How we use Architecture Lens here: Follow these strict constraints for mapping unfamiliar codebases:

Abstraction Rules

  1. Focus: Map ONLY the primary data flow layer, state management, and core routing.
  2. Ignore: Exclude utility functions, helpers, pure UI components, types/interfaces, and test files.
  3. Depth Limit: Maximum 2 levels of nesting. Do not attempt to map every function call.

Mermaid Formatting

  1. Type: Use flowchart TD (Top-Down) or LR (Left-Right) based on which creates fewer intersecting lines.
  2. Grouping: Group related modules into subgraph blocks (e.g., "Frontend", "State", "API", "Database").
  3. Nodes: Keep node labels concise. Use IDs and labels separately (e.g., db[(Database)]).

Output Protocol

  1. Render the Mermaid graph in a standard markdown block.
  2. Provide a 3-bullet summary of the most critical structural bottleneck or insight revealed by the graph.
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 23 lines · 25 tokens per session scan A 9366c7cd09e2

Subscribe to this mod's changes

architecture_lens is a skill published in the GitHub repository chama-x/GroundRules (5 stars, last pushed 22d ago), licensed MIT. It adds 25 tokens to every session and 257 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.