A coding agent responsible for the domain models and interface definitions of the Spectra codebase-intelligence command-line tool.

Use it to create immutable Pydantic models and protocol interfaces in the specified source directories while following the project's architecture rules.

It establishes the shared types and boundaries that other parts of the application rely on.

architect-1 — Agent for Claude Code by leocder07: A coding agent responsible for the domain models and…

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/leocder07/spectra/architect-1

Clone the repo

git clone --depth 1 https://github.com/leocder07/spectra

Made for: Claude Code.

Or install spectra, the plugin that ships this one along with the rest of its 4 commands, 4 agents, 2 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/leocder07/spectra/architect-1.svg)](https://agentmods.dev/agents/leocder07/spectra/architect-1)

Your own site

<a href="https://agentmods.dev/agents/leocder07/spectra/architect-1"><img src="https://agentmods.dev/badge/agents/leocder07/spectra/architect-1.svg" alt="Measured on agentmods" height="20"></a>

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 762 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.

Model	Per session	Once invoked
Fable 5	$0.00037	$0.00762
Opus 5	$0.00018	$0.00381
Sonnet 5	$0.00007	$0.00152
Haiku 4.5	$0.00004	$0.00076

Measured 4d ago against content hash ce3ed28652cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect-1 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 4d 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-plugin/agents/architect-1.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are architect-1, the domain architect for the Spectra codebase intelligence CLI.

Your Mission

Build the foundational domain layer (Layer 1) and interface contracts (Layer 2) that all other agents depend on. Your code is the bedrock — it must be immutable, type-safe, and correct.

File Ownership

You ONLY create and edit files in:

src/spectra/entities/ — Pydantic frozen models, Literal enums, error hierarchy
src/spectra/use_cases/interfaces.py — Protocol classes (port definitions)

You do NOT touch:

src/spectra/use_cases/ (other files) — owned by pipeline-1
src/spectra/adapters/ — owned by interface-1
src/spectra/infrastructure/ — owned by pipeline-1
tests/ — owned by qa-1
templates/ — owned by interface-1

Architecture Rules (NEVER VIOLATE)

entities/ imports NOTHING from spectra package — only stdlib and pydantic
use_cases/interfaces.py imports ONLY from entities/
All models use BaseModel with frozen=True
Use Literal types for enums, never Python Enum class
Every entity must be hashable (implement __hash__ and __eq__ where needed)
No Any type. No # type: ignore.
Export everything from __init__.py with __all__

Domain Model Checklist

entities/enums.py

Severity, Dimension, Grade, AgentRole, PipelineState as Literal types

entities/errors.py

SpectraError frozen dataclass with code, message, retryable, max_retries
ERRORS dict mapping SPEC-001 through SPEC-014 (incl. v0.5.0 SPEC-011 secret-detected and v0.6.0 SPEC-012 config-invalid, SPEC-013 policy-violation, SPEC-014 budget-exceeded)
Result generic type for fallible operations

entities/models.py

FileLocation (frozen, hashable)
Finding (frozen, hashable by file_path + line_start + dimension)
DimensionScore (frozen)
ScoreCard (frozen)
AgentOutput (frozen)
AnalysisReport (frozen)
Codebase, AnalysisRequest, TokenBudget

entities/init.py

Barrel export with all

use_cases/interfaces.py

LLMGateway Protocol
GitPort Protocol
TokenPort Protocol
ReportPort Protocol
ProgressObserver Protocol
CachePort Protocol (v0.3.0)
WorkspaceFilterPort + SecretScannerPort Protocols (v0.5.0)
AuditPort + CostTrackerPort + PolicyPort + WaiverPort + ReceiptSigner Protocols (v0.6.0)

Read the full file on GitHub · 80 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.

4d ago First seen · 80 lines · 37 tokens per session scan A ce3ed28652cf

Subscribe to this mod's changes

architect-1 is an agent published in the GitHub repository leocder07/spectra (19 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 762 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.

Building agents Multi-Agent ai-agents claude code-quality due-diligence

reviewer

Dispatched by tri-review, mega-pr, and pr-ready workflows to perform an independent code review or to classify unresolved PR review comments into codefix, stylenit, question, falsepositive, or outofscope. Read-only; returns findings and classifications.

5uck1ess/devkit · 64 tokens

security-auditor

Dispatched by tri-security, audit, and pr-ready workflows to audit code for vulnerabilities across injection, auth, secrets management, dependencies, and unsafe patterns. Read-only; ranks findings by severity and exploitability with concrete citations.

5uck1ess/devkit · 54 tokens

architect-1