spectral: Instructions file for Claude Code

CLAUDE.md

spectral CLAUDE.md is an instructions file for Claude Code from spectral-mcp/spectral. It costs 2,285 tokens per session, scanned A, original, MIT.

A project guide for Spectral, a Python codebase, that records documentation, import, and internal-function conventions.

In plain words
What is it for?
Use it when editing Spectral modules or documentation, especially when deciding how to organize imports, public APIs, and prose.
Why use it?
It gives coding agents the project’s local rules so they can make changes that fit its structure and style.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is spectral-mcp/spectral's own configuration. It tells Claude Code how to work on spectral itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything spectral configures →

Reuse

Borrowing it

Nothing to install: this file belongs to spectral-mcp/spectral. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/spectral-mcp/spectral/dev/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/spectral-mcp/spectral

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.

agentmods badge for spectral CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/spectral-mcp/spectral/claude-md.svg)](https://agentmods.dev/instructions/spectral-mcp/spectral/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/spectral-mcp/spectral/claude-md"><img src="https://agentmods.dev/badge/instructions/spectral-mcp/spectral/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,285 This file is loaded in full into every session.
When invoked 2,285 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02285 $0.02285
Opus 5 $0.01143 $0.01143
Sonnet 5 $0.00457 $0.00457
Haiku 4.5 $0.00229 $0.00229

Measured 7d ago against content hash 2a327d91c9b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spectral 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 7d 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spectral — Project Specification

Style preferences

  • No code samples in documentation. Documentation files should describe concepts in prose and tables, not paste code. The code lives in the code.
  • Import convention. All imports go at the top of the file (standard Python style). Internal CLI code (cli/…) is always imported at the top level — no lazy imports. Heavy external dependencies (e.g., mitmproxy, yaml, pydantic_ai) may be lazy-imported inside helper functions to keep spectral --help fast. Optional dependencies may use a lazy try/except with a user-friendly error. For mutable module-level state (e.g., _model in llm/_client.py), import the module at the top and access the attribute at call time to avoid stale references.
  • Private function convention. Every module should clearly separate its public API from internal helpers. Prefix internal functions with _ (e.g. _build_timeline_text, _resolve_url). The public API of a module is the set of unprefixed functions and classes — only those should be imported by other packages. Tests may import private functions for unit testing, but production code in other packages should only depend on the public API.

Development environment

  • Package manager is uv. Use uv run to execute commands (no need to activate the venv):
    • uv run pytest tests/ — run tests
    • uv run spectral mcp analyze ... — run the CLI
    • uv add <package> — add a dependency (updates pyproject.toml + uv.lock)
    • uv add --dev <package> — add a dev dependency
  • The LLM provider and API key are resolved from stored config at ~/.local/share/spectral/config.json or created interactively on first use via spectral config. Supports Anthropic, OpenRouter, OpenAI, and Ollama. No .env file needed.
  • Before finishing any code change, run the full verification suite and fix any new errors:
    • uv run pytest tests/ -x -q — all tests must pass
    • uv run ruff check — zero lint errors (use --fix for auto-fixable import sorting)
    • uv run pyright — zero new type errors (pre-existing errors in proxy.py, test_proxy.py are known)
  • Shell completion scripts (cli/completions/spectral.bash and spectral.zsh) are static — they must be updated manually whenever a CLI command, subcommand, or option is added, removed, or renamed.
  • Conventional Commits are mandatory. Every commit message must follow the format type(scope): description (e.g. fix:, feat:, chore:, docs:, refactor:, test:, ci:). This drives python-semantic-release: fix: bumps patch, feat: bumps minor, BREAKING CHANGE: bumps major. Use chore:/docs:/refactor:/test:/ci: for changes that should not trigger a release.

Read the full file on GitHub · 151 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. 7d ago First seen · 151 lines · 2,285 tokens per session scan A 2a327d91c9b9

Subscribe to this mod's changes

spectral CLAUDE.md is an instructions file published in the GitHub repository spectral-mcp/spectral (114 stars, last pushed 5mo ago), licensed MIT. It adds 2,285 tokens to every session, about $0.0114 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens