gandalf: Instructions file for Claude Code

CLAUDE.md

gandalf CLAUDE.md is an instructions file for Claude Code from sebacaro/gandalf. It costs 578 tokens per session, scanned A, original, MIT.

Instructions for Gandalf, a command-line tool for spec-driven development. Spec-driven development means writing a feature's requirements and acceptance conditions before building it.

In plain words
What is it for?
Use it to create feature specifications, initialize project structures, apply specs, verify results, and run basic stack-detection or startup tests.
Why use it?
It gives developers a defined way to activate the environment, run Gandalf, and perform its quick checks. This reduces uncertainty when generating, applying, or verifying project specifications.

Instructions file for Claude Code

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

This is sebacaro/gandalf's own configuration. It tells Claude Code how to work on gandalf 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 gandalf configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sebacaro/gandalf. 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/sebacaro/gandalf/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sebacaro/gandalf

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 gandalf CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sebacaro/gandalf/claude-md/github.svg)](https://agentmods.dev/instructions/sebacaro/gandalf/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sebacaro/gandalf/claude-md"><img src="https://agentmods.dev/badge/instructions/sebacaro/gandalf/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gandalf CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sebacaro/gandalf/claude-md"><img src="https://agentmods.dev/badge/instructions/sebacaro/gandalf/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 578 This file is loaded in full into every session.
When invoked 578 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 $0.00578 $0.00578
Opus 5.5 $0.00231 $0.00231
Sonnet 5.5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 2mo ago against content hash 68cb817f33dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gandalf 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 2mo 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gandalf — CLI para Spec Driven Development

Herramienta local para generar specs SDD y estructuras de proyecto en la terminal.

Comandos

# Activar entorno
source venv/bin/activate

# Ejecutar directamente
python main.py --help
python main.py spec
python main.py init
python main.py apply
python main.py verify

# O con gandalf global (después de install.sh)
gandalf spec
gandalf init
gandalf apply
gandalf verify

Tests rápidos

# Smoke test: que el CLI arranca
python main.py --help

# Test de detección de stack
python -c "from src.infrastructure.detectors.file_stack_detector import FileStackDetector; print(FileStackDetector().detect('.'))"

# Test de generación (requiere carpeta temporal)
python -c "
from src.domain.entities.feature_spec import FeatureSpec
from src.application.use_cases.create_feature_spec import create_feature_spec
spec = FeatureSpec(name='Test', slug='test', stack='generic', description='Test feature', context='Test context', new_components='TestComponent', modified_files='main.py', acceptance_criteria=['Given user / When action / Then result'], edge_cases='Empty state', project_path='/tmp/gandalf_test')
ok, files, err = create_feature_spec(spec)
print('OK', files) if ok else print('ERROR', err)
"

Instalación

bash scripts/install.sh

Arquitectura

gandalf/
├── main.py                              # Entry point
├── src/
│   ├── domain/                          # Entidades + interfaces
│   ├── application/use_cases/           # Lógica de cada comando
│   ├── infrastructure/
│   │   ├── detectors/                   # Auto-detección de stack
│   │   ├── generators/                  # Renderizado Jinja2
│   │   ├── templates/{stack}/           # Templates por stack
│   │   └── cursor/                      # Integración con Cursor
│   └── presentation/
│       ├── cli/commands/                # Comandos typer
│       ├── forms/                       # Formularios questionary
│       └── ui/display.py                # Componentes rich

Read the full file on GitHub · 75 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. 2mo ago First seen · 75 lines · 578 tokens per session scan A 68cb817f33dd

Subscribe to this mod's changes

gandalf CLAUDE.md is an instructions file published in the GitHub repository sebacaro/gandalf (2 stars, last pushed yesterday), licensed MIT. It adds 578 tokens to every session, about $0.0023 per session on Opus 5.5. 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.

Related

gandalf CLAUDE.md compared with instructions from other repositories

gandalf CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gandalf CLAUDE.mdsebacaro/gandalfInstructions file2yesterdayMITA578Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode