gguard-config

gguard-config is a skill for Claude Code from sanjeewamadhuranga/grounding-guard. It costs 40 tokens per session (422 once invoked), scanned A, original, MIT.

A configuration helper for Grounding Guard, a checker that verifies package, import, and Git reference names against public sources.

In plain words
What is it for?
Use it to edit user or project configuration, set block, warn, or off modes, add allowed name patterns, set registries, and adjust time limits.
Why use it?
It lets projects avoid false warnings for private packages, use private registries, work offline, and choose which checks block work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grounding-guard plugin — 2 skills, 2 hooks shipped together

Good fit Use it to edit user or project configuration, set block, warn, or off modes, add allowed name patterns, set registries, and adjust time limits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sanjeewamadhuranga/grounding-guard/gguard-config
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.

Any agent
npx skills add sanjeewamadhuranga/grounding-guard --skill gguard-config
Clone the repo
git clone --depth 1 https://github.com/sanjeewamadhuranga/grounding-guard

Made for: Claude Code.

Or install grounding-guard, the plugin that ships this one along with the rest of its 2 skills, 2 hooks.

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 gguard-config

README.md
[![agentmods](https://agentmods.dev/badge/skills/sanjeewamadhuranga/grounding-guard/gguard-config/github.svg)](https://agentmods.dev/skills/sanjeewamadhuranga/grounding-guard/gguard-config)
Your own site
<a href="https://agentmods.dev/skills/sanjeewamadhuranga/grounding-guard/gguard-config"><img src="https://agentmods.dev/badge/skills/sanjeewamadhuranga/grounding-guard/gguard-config/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 gguard-config

Your own site · 80×15
<a href="https://agentmods.dev/skills/sanjeewamadhuranga/grounding-guard/gguard-config"><img src="https://agentmods.dev/badge/skills/sanjeewamadhuranga/grounding-guard/gguard-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 422 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.
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 $0.00040 $0.00422
Opus 5 $0.00020 $0.00211
Sonnet 5 $0.00008 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured 12d ago against content hash 238112209987, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gguard-config 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.

skills/gguard-config/SKILL.md · 45 lines

What it actually says

Grounding Guard Config

Help the user create or edit their Grounding Guard configuration.

Config files (later overrides earlier, deep-merged):

  1. ~/.gguard.json — user defaults
  2. .gguard.json in the project root — per-project overrides

Full schema with defaults:

{
  "verifiers": {
    "packages": "block",
    "imports": "warn",
    "gitrefs": "warn"
  },
  "allow": ["@myorg/*", "internal-*"],
  "registries": {
    "npm": "https://registry.npmjs.org",
    "pypi": "https://pypi.org"
  },
  "timeoutMs": 5000,
  "fetchTimeoutMs": 2500,
  "offline": false
}

Field notes:

  • verifiers.<name>: "block" (deny/exit-2), "warn" (non-blocking feedback), "off".
  • allow: glob patterns (* wildcard) of package/module names never checked against public registries. Use for private packages and monorepo-internal names.
  • Private npm registries in .npmrc are detected automatically: a non-npmjs default registry disables npm checks entirely; scoped overrides (@scope:registry=...) disable checks for that scope.
  • offline: true forces cache-only operation (never blocks on network).

Workflow:

  1. Ask (or infer from the request) what the user wants changed.
  2. Read the existing .gguard.json if present; merge, don't clobber.
  3. Write the file and show the resulting effective config.
  4. If the user reports false positives on private packages, add allowlist patterns rather than turning the packages verifier off.
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 · 45 lines · 40 tokens per session scan A 238112209987

Subscribe to this mod's changes

gguard-config is a skill published in the GitHub repository sanjeewamadhuranga/grounding-guard (1 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 422 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 2026-08-31.

Related

Other skills, from other repositories

album-art-director

Creates visual concepts for album artwork and generates AI art prompts. Use during planning for concept discussion, or after all tracks are Final for actual artwork generation.

bitwize-music-studio/claude-ai-music-skills · 35 tokens

lyric-refiner

Autonomous multi-pass lyric refinement for tightening, cohesion, and album unity. Use after lyrics are written to polish a track or entire album through iterative passes.

bitwize-music-studio/claude-ai-music-skills · 36 tokens

mastering-engineer

Guides audio mastering for streaming platforms including loudness optimization and tonal balance. Use when the user has approved tracks and wants to master audio files.

bitwize-music-studio/claude-ai-music-skills · 34 tokens

promo-writer

Generates platform-specific social media copy from album themes, track concepts, and lyrics. Use when promo/ templates need to be populated before release.

bitwize-music-studio/claude-ai-music-skills · 33 tokens

voice-checker

Reviews lyrics and prose for AI-written patterns (abstract noun stacking, over-explained metaphors, cliche escalation, missing idiosyncrasy, prose AI tells). Advisory Warning/Info severity — flags issues, does not block or rewrite. Use when reviewing lyrics for authenticity or before generation to catch AI-sounding…

bitwize-music-studio/claude-ai-music-skills · 70 tokens

album-ideas

Tracks and manages album ideas including brainstorming, planning, and status updates. Use when the user wants to add, review, or organize their album idea backlog.

bitwize-music-studio/claude-ai-music-skills · 35 tokens