ggmcp: Skill for Claude Code

.claude/skills/use-settings-not-environ/SKILL.md

use-settings-not-environ is a skill for Claude Code from GitGuardian/ggmcp. It costs 41 tokens per session (294 once invoked), scanned A, original, MIT.

A project rule for reading environment variables, which are settings supplied outside the program, through the project's Settings object.

In plain words
What is it for?
Use it when adding environment-driven configuration or reviewing code that reads environment variables, including defining settings fields and derived configuration properties.
Why use it?
It prevents production code from reading configuration directly with os.environ or os.getenv, which can bypass the project's conventions and make tests unreliable.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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

Reuse

Borrowing it

Nothing to install: this file belongs to GitGuardian/ggmcp. 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/GitGuardian/ggmcp/main/.claude/skills/use-settings-not-environ/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GitGuardian/ggmcp

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 use-settings-not-environ

README.md
[![agentmods](https://agentmods.dev/badge/skills/gitguardian/ggmcp/use-settings-not-environ/github.svg)](https://agentmods.dev/skills/gitguardian/ggmcp/use-settings-not-environ)
Your own site
<a href="https://agentmods.dev/skills/gitguardian/ggmcp/use-settings-not-environ"><img src="https://agentmods.dev/badge/skills/gitguardian/ggmcp/use-settings-not-environ/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 use-settings-not-environ

Your own site · 80×15
<a href="https://agentmods.dev/skills/gitguardian/ggmcp/use-settings-not-environ"><img src="https://agentmods.dev/badge/skills/gitguardian/ggmcp/use-settings-not-environ.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.00294
Opus 5 $0.00020 $0.00147
Sonnet 5 $0.00008 $0.00059
Haiku 4.5 $0.00004 $0.00029

Measured 10d ago against content hash 9b9029575614, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

use-settings-not-environ 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 10d 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/skills/use-settings-not-environ/SKILL.md · 32 lines

What it actually says

Use Settings, not os.environ

All env-var access in gg-mcp goes through gg_api_core.settings.Settings. Adding os.environ.get(...) to non-test code is a review-blocker.

Pattern

# 1. Declare the field on Settings (packages/gg_api_core/src/gg_api_core/settings.py)
github_token: str | None = None   # → reads GITHUB_TOKEN (case-insensitive)

# 2. Read it
from gg_api_core.settings import get_settings
token = get_settings().github_token

Derived booleans/lists → add a @property on Settings (see is_oauth_enabled, requested_scopes).

Don't

  • os.environ.get(...) / os.getenv(...) in production code.
  • Module-level capture: _S = get_settings() — breaks monkeypatch.setenv in tests.
  • @lru_cache on get_settings — same reason. It is intentionally uncached.

OK exceptions

Tests (monkeypatch.setenv), pre-Settings-import bootstrap, and constructing a subprocess env=.

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. 10d ago First seen · 32 lines · 41 tokens per session scan A 9b9029575614

Subscribe to this mod's changes

use-settings-not-environ is a skill published in the GitHub repository GitGuardian/ggmcp (37 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 294 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.

Related

Other skills, from other repositories

idapython

IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida modules (50+), idautils iterators, and common…

mrexodia/ida-pro-mcp · 77 tokens

vibeue

Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…

kevinpbuckley/VibeUE · 82 tokens

n8n-code-python

Write Python code in n8n Code nodes. Use when writing Python in n8n, using input/json/node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes. Use this skill when the user specifically requests Python for an n8n Code node. Note — JavaScript is recommended for 95% of use…

czlonkowski/n8n-mcp · 157 tokens

python-type-safety

Modern Python type safety with type hints, generics, protocols, and strict type checking using ty and ruff. Use when adding type annotations, implementing generic classes, defining structural interfaces, configuring ty/ruff, or writing type-safe Python 3.13+/3.14+ code. Triggers on mentions of type hints, typing…

AI-Riksarkivet/ra-mcp · 104 tokens

python-design-pattern

Python design patterns and anti-patterns. Use when designing new components, refactoring, reviewing code for common mistakes, choosing abstractions, or evaluating pull requests for structural issues like tight coupling, leaking internal types, or error handling problems.

AI-Riksarkivet/ra-mcp · 51 tokens

testing-python

Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, async testing, and CI integration.

AI-Riksarkivet/ra-mcp · 48 tokens