spectra CLAUDE.md

spectra CLAUDE.md is an instructions file for coding agents from leocder07/spectra. It costs 2,655 tokens per session, scanned A, original, MIT.

Repository instructions for Spectra, a Python command-line tool that uses several AI agents to review a whole code repository for architecture, security, quality, documentation, maintainability, and performance.

In plain words
What is it for?
Use them when developing Spectra, analyzing a repository, producing JSON or audit reports, or running its test and validation commands.
Why use it?
They explain how to install, run, test, lint, type-check, and verify Spectra’s reports.

Instructions file

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 instructions/leocder07/spectra/claude-md
Clone the repo
git clone --depth 1 https://github.com/leocder07/spectra

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 spectra CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/leocder07/spectra/claude-md.svg)](https://agentmods.dev/instructions/leocder07/spectra/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/leocder07/spectra/claude-md"><img src="https://agentmods.dev/badge/instructions/leocder07/spectra/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,655 This file is loaded in full into every session.
When invoked 2,655 The same file — it is already loaded in full.
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 $0.02655 $0.02655
Opus 5 $0.01327 $0.01327
Sonnet 5 $0.00531 $0.00531
Haiku 4.5 $0.00265 $0.00265

Measured 5d ago against content hash a19b2fe93f07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spectra CLAUDE.md 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 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.

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.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What is Spectra?

Spectra deploys 8 AI agents (6 parallel specialists + MetaPrompter + CritiqueAgent) to analyze entire repositories across 6 dimensions — architecture, security, quality, documentation, maintainability, performance — in under 5 minutes. Python CLI. Clean Architecture.

Tagline: "The full spectrum of your codebase." One-liner: "8 AI agents analyze your entire repository in under 5 minutes."


Development Commands

# Install dependencies
pip install -e ".[dev]"

# Run CLI
spectra analyze <repo-url>
spectra analyze <repo-url> --quick    # Skip CritiqueAgent
spectra analyze <repo-url> --format json
spectra analyze <repo-url> --audit-sink stdout|file:<path>|otlp:<url>
spectra verify spectra-report.json    # Verify Ed25519 receipt

# Run tests
pytest tests/ -v
pytest tests/entities/ -v              # Unit tests only
pytest tests/integration/ -v           # Integration tests
pytest tests/ --cov=spectra --cov-report=html

# Lint and type check
ruff check src/ tests/
ruff format src/ tests/
mypy src/

# Build and publish
python -m build
pip install dist/spectra_cli-*.whl

Architecture — ABSOLUTE RULES (NEVER VIOLATE)

The Dependency Rule

Source code dependencies ONLY point inward:

Layer 1 (entities/)         → imports NOTHING from spectra package
Layer 2 (use_cases/)        → imports ONLY from entities/
Layer 3 (adapters/)         → imports from entities/ + use_cases/
Layer 4 (infrastructure/)   → imports from all inner layers

Violation = immediate rejection. No exceptions.

Code Standards

  • Functions: ≤20 lines, ≤3 parameters, cyclomatic complexity ≤10
  • No Any type. No # type: ignore.
  • No print() in src/ — use ProgressObserver port via Rich Console
  • Every entity: frozen=True on Pydantic models. Immutable.
  • Fallible operations: Result dataclass pattern
  • All agent outputs: validated with Pydantic model BEFORE merge
  • Literal types for enums: Severity = Literal["critical", "high", "medium", "low", "info"]
  • Export everything from __init__.py with __all__

Read the full file on GitHub · 215 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.

  1. 5d ago First seen · 215 lines · 2,655 tokens per session scan A a19b2fe93f07

Subscribe to this mod's changes

spectra CLAUDE.md is an instructions file published in the GitHub repository leocder07/spectra (19 stars, last pushed 2mo ago), licensed MIT. It adds 2,655 tokens to every session, about $0.0133 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.