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.
npx skills add lossless-group/lossless-agent-skills --skill maintain-splash-pagesgit clone --depth 1 https://github.com/lossless-group/lossless-agent-skillsWrote 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.
[](https://agentmods.dev/skills/lossless-group/lossless-agent-skills/maintain-splash-pages)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/maintain-splash-pages"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/maintain-splash-pages/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.
<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/maintain-splash-pages"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/maintain-splash-pages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00222 | $0.08565 |
| Opus 5.5 | $0.00089 | $0.03426 |
| Sonnet 5.5 | $0.00044 | $0.01713 |
| Haiku 4.5 | $0.00022 | $0.00856 |
Grade A, and why
maintain-splash-pages 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.
How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain Splash Pages
A splash is the source repo's own GitHub Pages presence — distinct from any future custom-domain marketing site. The directory is named
splash/precisely to keep that linguistic space open.
Status: Draft. This skill codifies the pattern after three confirmed instances. It pairs with a sibling habit titled "Maintain a Github Splash Page for each Repo" that explains the why; this skill is canonical for the how. The habit currently lives under lossless-monorepo/context-v/habits/ but may move — search for it by title before assuming a path. Always cross-reference the most recent reference implementation (currently lfm/splash/) before scaffolding fresh.
Reasoning step before implementation: does this repo deserve a splash?
The convention is "every important repo." That word is doing work — not every repo earns one. Use this rough cut:
Yes, scaffold a splash:
- The repo will be shared with people outside the team (clients, collaborators, hiring loops, conference talks)
- The repo has — or will have — a non-trivial
changelog/worth surfacing - The repo publishes a package (npm/JSR) and you'd like an installable-package landing page that isn't just the registry's auto-generated one
- The repo is an Astro Knots site or feature
- The repo is a study, blueprint, or reference that other repos will link to
- Someone has asked "where's the README rendered?" or "is there a page for this?"
Probably not (yet):
- The repo is purely internal scratch — experiments, sandboxes, throwaway studies that aren't meant to outlive the week
- The repo is a fork where we're contributing upstream
- The repo is a private tool with no external audience
When in doubt, ask the user. The cost of not having a splash is "no public face" — fixable later. The cost of having a stale, unmaintained one is worse than nothing.
Surface the question proactively. When working in a repo that meets the yes criteria but doesn't have a splash, mention it. ("This repo doesn't have a splash yet; want me to scaffold one?") That's how the convention spreads.
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.
- 2mo ago First seen · 430 lines · 222 tokens per session scan A fcbc49cf3559
maintain-splash-pages is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 2d ago), licensed MIT. It adds 222 tokens to every session and 8,565 once invoked, about $0.0009 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.
Other skills, from other repositories
agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK or build Model Context Protocol (MCP) servers. Load when creating stateful agents, durable workflows, MCP servers, checking MCP schema/error responses, or reviewing MCP code quality. Covers Agent class, state management, callable RPC, Workflows integration…
workers-best-practices
(APPLICATION CODE ONLY) Reviews and authors Cloudflare Workers code against production best practices. Use ONLY when writing or reviewing Worker code, configuring wrangler.jsonc, or checking for anti-patterns. Do NOT use for general Cloudflare product discovery (use cloudflare instead) or CLI management (use wrangler…
aws
Comprehensive AWS (Amazon Web Services) best practices and infrastructure guidelines. Use when deploying to AWS, writing CloudFormation/CDK/Terraform for AWS, configuring IAM permissions, S3 buckets, EC2 instances, Lambda functions, or ECS/EKS clusters. Do NOT trigger for generic "deploy my app" requests without…
azure
Microsoft Azure best practices. Use when deploying to Azure App Service, Azure Functions, AKS (Azure Kubernetes Service), Cosmos DB, configuring Azure Entra ID (Active Directory), or managing Azure Resource Manager (ARM/Bicep) templates. Do NOT trigger for generic "deploy my app" requests without clarifying the target…
cloudflare
(GENERIC ROUTING ONLY) General Cloudflare platform skill for infrastructure, storage, and networking. Use when choosing between Cloudflare products (KV vs D1 vs R2) or doing general Cloudflare tasks. NOT for building AI agents (use agents-sdk). NOT for building MCP servers (use mcp-builder). NOT for deploying…
gcp
Google Cloud Platform (GCP) best practices. Use when provisioning GCP infrastructure, configuring IAM, deploying to Cloud Run, GKE (Kubernetes Engine), Cloud Functions, Cloud SQL, or managing BigQuery. Do NOT trigger for generic "deploy my app" requests without clarifying the target platform.