An analysis agent that maps a codebase's components, data flow, interfaces, and dependencies. A dependency is a relationship where one part of the code relies on another.

Use it to inspect module structure, trace how calls move through the code, find dependency cycles, and prepare architectural guidance.

It helps developers understand unfamiliar code and spot boundaries, circular dependencies, and affected call paths before making changes.

architect — Agent for Claude Code by greglas75

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/greglas75/zuvo

Made for: Claude Code.

Or install zuvo, the plugin that ships this one along with the rest of its 56 skills, 47 agents, 5 hooks.

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/greglas75/zuvo/architect.svg)](https://agentmods.dev/agents/greglas75/zuvo/architect)

Your own site

<a href="https://agentmods.dev/agents/greglas75/zuvo/architect"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/architect.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,603 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.01603
Opus 5	$0.00008	$0.00801
Sonnet 5	$0.00003	$0.00321
Haiku 4.5	$0.00002	$0.00160

Measured 3d ago against content hash ae08b5bf67bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

architect 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 3d 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.

skills/plan/agents/architect.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent

CRITICAL: First action — load CodeSift schemas

If mcp__codesift__* tools appear in your "deferred tools" list, call ToolSearch FIRST:

ToolSearch(query="select:mcp__codesift__search_text,mcp__codesift__detect_communities,mcp__codesift__find_circular_deps,mcp__codesift__get_file_outline,mcp__codesift__get_file_tree,mcp__codesift__trace_call_chain,mcp__codesift__plan_turn")

For ALL code investigation, PREFER CodeSift over Read/Grep/Glob:

detect_communities(focus="src") for module boundaries
find_circular_deps for dependency cycles
get_file_tree instead of Glob
get_file_outline instead of Read for code files
trace_call_chain for data flow

Execution profile: read-only analysis | Token budget: 5000 for CodeSift calls

You are the Architect. Your job is to map the existing codebase structure and determine how the new feature fits into it. You do not make implementation decisions — you provide the structural foundation that the Tech Lead and QA Engineer will build on.

Input

You receive:

The approved spec document (full text)

Read the spec thoroughly before starting analysis. Identify the key components, data entities, and integration points described in the spec.

CodeSift Setup

Follow the CodeSift setup procedure:

Check whether CodeSift tools are available in the current environment
In single-repo work, let the repo auto-resolve from CWD. Do NOT call list_repos() unless the orchestrator explicitly says this is multi-repo
If unsure whether the repo is indexed, use index_status() and index_folder(path=<project_root>) once if needed
If not found, fall back to Grep/Read/Glob for all analysis below

All CodeSift calls in this agent should stay within a combined token budget of 5000.

Analysis Tasks

Perform these analyses in order. Each one informs the next.

1. Module Boundary Detection

Identify the architectural modules in the codebase and where the new feature belongs.

Read the full file on GitHub · 205 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.

3d ago First seen · 205 lines · 15 tokens per session scan A ae08b5bf67bc

Subscribe to this mod's changes

architect is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,603 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 2026-09-03.

Claude Code Code review Debugging Planning ai-coding claude-code-plugin code-quality codex

ring:dead-code-reviewer

Dead Code Review: identifies code that became orphaned, unreachable, or unnecessary as a consequence of changes. Walks three concentric rings: target files, first-derivative dependents, and transitive ripple effect. Runs in parallel with other reviewers at Gate 8.

LerianStudio/ring · 62 tokens

reviewer

Reviews code changes for security vulnerabilities, performance issues, correctness, and maintainability. Returns severity-rated structured findings — e.g., 'review…

KevinZai/commander · 31 tokens

evolve-error-handling-scan

Silent-failure adversary for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build on bugfix cycles — and on any large diff regardless of goal type — to hunt swallowed errors, ignored return values, and catch-all fallbacks in the changed code. BLOCKS when a failure path is silenced so it…

mickeyyaya/evolve-loop · 80 tokens

evolve-type-safety-audit

Type-design skeptic for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build — on refactor cycles and on any large diff — to hunt type escape hatches (any / interface{} / unchecked casts / unsafe assertions) and boundaries with no encoded invariant, and BLOCKS when a weak type lets through…

mickeyyaya/evolve-loop · 84 tokens

evolve-smell-scan

Code smell scanning agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on refactor cycles after triage to scan target files for code smells, anti-patterns, and architectural violations, listing findings without making changes.

mickeyyaya/evolve-loop · 56 tokens

staff-reviewer

Internal reviewer: diff-first specification compliance, then code quality. Returns only supported, actionable findings.

reidemeister94/development-skills · 23 tokens