agentmods.dev

sparkling-skills: Instructions file for Claude Code

CLAUDE.md

sparkling-skills CLAUDE.md is an instructions file for Claude Code from sparklingneuronics/sparkling-skills. It costs 1,191 tokens per session, scanned A, original, MIT.

Maintainer instructions for a Claude Code marketplace, a catalogue that contains installable plugins. They describe the repository layout and a dispatch plugin that sends tasks to external AI command-line tools, including Codex and Antigravity.

In plain words
What is it for?
Use them to maintain the marketplace structure, update the dispatch plugin, and understand how its command aliases route work to external AI tools.
Why use it?
They help maintainers understand where marketplace entries, plugins, skills, references, and evaluations belong.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

This is sparklingneuronics/sparkling-skills's own configuration. It tells Claude Code how to work on sparkling-skills 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 sparkling-skills configures →

not rated 6repo changed 2d ago A scan 1,191 tokens original MIT
View source ↗ sparklingneuronics/sparkling-skills sparklingneuronics.ai
Reuse

Borrowing it

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

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 sparkling-skills CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sparklingneuronics/sparkling-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/sparklingneuronics/sparkling-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,191 This file is loaded in full into every session.
When invoked 1,191 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 $0.01191 $0.01191
Opus 5 $0.00596 $0.00596
Sonnet 5 $0.00238 $0.00238
Haiku 4.5 $0.00119 $0.00119

Measured 2d ago against content hash 7080b1debe8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sparkling-skills 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 2d 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sparkling-skills — maintainer notes

This repo is a Claude Code marketplace (sparkling-skills) that hosts plugins. Each plugin is a purpose-grouped set of skills under plugins/<name>/. Today there's one:

  • dispatch — delegate a task to an external AI CLI: /codex (OpenAI Codex) and /agy (Google Antigravity — multi-model: Gemini / Claude / GPT-OSS). /gemini is an alias that routes to agy. More plugins (e.g. diagrams, journeys) drop in as sibling folders later.

Gemini was retired (2026-06). Google deprecated gemini-cli's free individual tier (IneligibleTierError → "migrate to Antigravity"), so the gemini skill was replaced by agy, which signs in with a free Google account and runs Gemini and Claude and GPT-OSS. The /gemini command still works — it routes through agy on a Gemini model.

Layout

  • .claude-plugin/marketplace.json — the marketplace catalog (lists each plugin).
  • plugins/<name>/.claude-plugin/plugin.json — that plugin's manifest (metadata; skills auto-load from its skills/).
  • plugins/dispatch/skills/codex/, plugins/dispatch/skills/agy/ — each has SKILL.md, references/flags.md, and evals/. Their /-commands live in plugins/dispatch/commands/.
  • docs/PUBLISHING.md — how to publish/update the marketplace. Read before releasing.
  • docs/research/ — full background research on Claude Code plugin/marketplace mechanics.

Conventions (please follow)

  • Cross-platform. Shipped skills must run on Windows/macOS/Linux. No bash .sh inside a skill — keep it pure markdown (Claude builds commands per-platform). Use Python 3 stdlib for dev tooling (e.g. the eval lints).
  • Run the eval lints before committing skill changes — all must print "all N … valid/hold":
    • python3 plugins/dispatch/skills/codex/evals/lint_codex_commands.py
    • python3 plugins/dispatch/skills/agy/evals/lint_agy_commands.py
    • python3 plugins/dispatch/skills/codex/evals/probe_codex_capabilities.py — free tier; catches semantic drift the lints can't see (flags that exist but can't be combined, value sets that gained a variant).
  • Two heavier codex evals are opt-in, not pre-commit — see plugins/dispatch/skills/codex/evals/README.md: probe_codex_capabilities.py --matrix (paid; regenerates the model×effort table in flags.md) and probe_skill_behavior.py (runs the skill against a fake codex and asserts on the argv it builds — no codex usage; run it whenever routing or sandbox rules change).
  • Keep codex ↔ agy in lockstep where they overlap. Shared core: topic-aware sessions, the delta "bridge", peer-evaluation, explicit-naming, optimistic pre-flight. But they differ by CLI, deliberately — codex has a read-only sandbox; agy is agentic (no read-only mode) and multi-model. Both generate images — codex's built-in imagegen, agy's native generate_image on the Google subscription. Don't blindly mirror.
  • Explicit-naming triggers. Each skill fires only when its tool is named — codex; or agy / antigravity / gemini (all three route to agy). Keeps precision high. Descriptions are deliberately "pushy" to combat under-triggering; the /codex and /agy slash commands give a deterministic path.
  • Verify CLI/API facts against the live CLI or source — don't assume. This repo has been bitten by stale/changed CLI facts (codex web_search enablement; gemini's deprecated tier; agy's cache-file session ids + its no-read-only behavior). When in doubt, run <cli> --help or read the CLI's source.

Read the full file on GitHub · 68 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. 2d ago Changed · +13 lines · +259 tokens per session 7080b1debe8c
  2. 11d ago First seen · 55 lines · 932 tokens per session scan A d06719106878

Subscribe to this mod's changes

sparkling-skills CLAUDE.md is an instructions file published in the GitHub repository sparklingneuronics/sparkling-skills (6 stars, last pushed 3d ago), licensed MIT. It adds 1,191 tokens to every session, about $0.0060 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.

Claude CodeCode reviewai-agentsantigravityclaude-code-marketplaceclaude-code-plugin
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 · 5,153 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

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

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

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