gfi-scout: Instructions file for Claude Code

CLAUDE.md

gfi-scout CLAUDE.md is an instructions file for Claude Code from Rajveerx11/gfi-scout. It costs 1,712 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for the GFI Scout project, a tool that ranks GitHub issues suitable for first-time contributors. It documents the project, commands, architecture, and request flow.

In plain words
What is it for?
Use it when modifying, testing, linting, debugging, or understanding the GFI Scout codebase.
Why use it?
It gives an agent the project-specific information needed to work consistently in that repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Rajveerx11/gfi-scout's own configuration. It tells Claude Code how to work on gfi-scout 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 gfi-scout configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Rajveerx11/gfi-scout. 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/Rajveerx11/gfi-scout/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Rajveerx11/gfi-scout

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 gfi-scout CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rajveerx11/gfi-scout/claude-md/github.svg)](https://agentmods.dev/instructions/rajveerx11/gfi-scout/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rajveerx11/gfi-scout/claude-md"><img src="https://agentmods.dev/badge/instructions/rajveerx11/gfi-scout/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 gfi-scout CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rajveerx11/gfi-scout/claude-md"><img src="https://agentmods.dev/badge/instructions/rajveerx11/gfi-scout/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,712 This file is loaded in full into every session.
When invoked 1,712 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 $0.01712 $0.01712
Opus 5 $0.00856 $0.00856
Sonnet 5 $0.00342 $0.00342
Haiku 4.5 $0.00171 $0.00171

Measured 12d ago against content hash 1bebcb0ba2c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gfi-scout 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 12d 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 · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 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.

Project

GFI Scout — FastMCP server + standalone CLI/TUI that ranks GitHub "good first issues" by likelihood-of-success (repo health, merge rate, issue freshness, setup complexity) instead of raw label search. Python 3.12+, managed exclusively with uv.

Commands

All commands go through uv — no pip, no poetry.

uv sync                                  # install deps + create .venv
uv run gfi-scout                         # run MCP server (stdio)
uv run gfi-scout-cli find python --min-stars 500
uv run gfi-scout-tui                     # interactive TUI
uv run mcp dev src/gfi_scout/server.py   # MCP Inspector for debugging tools

uv run pytest                            # full suite, coverage gate at 70%
uv run pytest tests/unit/services/test_issue_scorer.py            # single file
uv run pytest tests/unit/services/test_issue_scorer.py::test_name # single test
uv run pytest -k "scorer and not integration"                     # filter
uv run pytest --no-cov                   # skip coverage when iterating

uv run ruff check src/ tests/            # lint
uv run ruff format src/ tests/           # format
uv run mypy src/                         # strict type-check (must pass)

All three of ruff, mypy, pytest must pass before any push. uv.lock is committed.

Environment: GITHUB_TOKEN is optional — without it the client runs unauthenticated at 60 req/h and logs a warning; a PAT with public_repo scope (read-only) gives 5,000 req/h. Copy .env.example.env to set it.

Architecture

Strict layered package at src/gfi_scout/. Layer rules are non-negotiable — crossing them is a review-blocker.

Layer May import Must NOT import
tools/ services/, models/ httpx directly, business logic
services/ httpx, models/, other services FastMCP, tool surfaces
models/ Pydantic, stdlib Anything with side effects
utils/ stdlib only I/O, mutable state

Read the full file on GitHub · 125 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. 12d ago First seen · 125 lines · 1,712 tokens per session scan A 1bebcb0ba2c0

Subscribe to this mod's changes

gfi-scout CLAUDE.md is an instructions file published in the GitHub repository Rajveerx11/gfi-scout (0 stars, last pushed 8d ago), licensed MIT. It adds 1,712 tokens to every session, about $0.0086 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 2026-08-31.

Related

Other instructions, from other repositories