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 remake-deckgit 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/remake-deck)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/remake-deck"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/remake-deck/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/remake-deck"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/remake-deck.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 | $0.00290 | $0.01228 |
| Opus 5.5 | $0.00116 | $0.00491 |
| Sonnet 5.5 | $0.00058 | $0.00246 |
| Haiku 4.5 | $0.00029 | $0.00123 |
Grade A, and why
remake-deck 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
remake-deck
A thin entry point. The real procedure lives in the dididecks-ai repo as
versioned context-v documents, so the pipeline evolves in one place and this
skill never drifts from it:
| Layer | File (relative to the dididecks-ai root) |
|---|---|
| Variables, filesystem contract, how the layers compose | context-v/prompts/README.md |
| The plan you execute (orchestrator) | context-v/plans/Remake-Source-Deck-into-Design-Variants.md |
| Subagent briefs, one per role | context-v/prompts/{Extract-Source-Deck, Audit-Source-Deck-Extraction, Design-Deck-Variant-as-Single-HTML, Refactor-HTML-Variant-into-Astro-Scroll-Sections, Verify-Variant-Plays-in-Scroll-Shell}.md |
| Batch runner over many decks | context-v/loops/Remake-Source-Decks-Queue.md |
Step 1: Find the dididecks-ai repo
Walk up from the current directory looking for
context-v/plans/Remake-Source-Deck-into-Design-Variants.md. Also try
./ai-labs/dididecks-ai/ and ./dididecks-ai/ below the current directory. On
the maintainer's machine it's
~/code/lossless-monorepo/ai-labs/dididecks-ai. If none of these exist, ask
the user for the path once. Don't guess further.
If the chat has no file or shell access at all (a plain web chat with no connected workspace), say so plainly: this pipeline writes files and runs a build, so it needs an agent with the repo on disk. Stop there.
Step 2: Map the arguments
Read context-v/prompts/README.md, then map the user's arguments:
- The first argument is
COMPANY. Quote multi-word names. - The second is
CLIENT_SITE. Acceptclient-sites/<slug>or a bare<slug>. - The third is
SOURCE_DECK. - Any
KEY=valuepairs override the defaults in the README's variable table.
If any of the three required arguments is missing, ask for all the missing ones in one question. Don't ask anything else up front; the plan's step 0 covers the rest.
Step 3: Execute the plan as orchestrator
Read the plan file end to end and follow it. You hold the VP Eng role. You brief subagents and judge their work; you don't extract, design, or write Astro yourself.
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.
- 10d ago First seen · 83 lines · 290 tokens per session scan A 8fb9054c7f8c
remake-deck is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 2d ago), licensed MIT. It adds 290 tokens to every session and 1,228 once invoked, about $0.0012 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 2026-10-06.
Other skills, from other repositories
rag-pipelines
Best practices for Retrieval-Augmented Generation (RAG) pipelines. Use when working with vector databases, embeddings, chunking strategies, semantic search, or hybrid search architectures.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
rag-pipeline
A guide to RAG, a method where a system retrieves relevant passages from an external knowledge base before an AI model writes an answer. It covers splitting documents, searching by meaning or exact words, combining results, and measuring retrieval quality.
rag-patterns
RAG: embeddings, chunking, hybrid search (BM25+vector), reranking, CRAG, multi-hop. Triggers: RAG, embedding, pgvector, Qdrant, Pinecone, Weaviate, reranker, semantic search.
evaluate
Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.
index
Reindexes KB for semantic search via vector store (Qdrant). Triggers: reindex KB, rebuild index, vector reindex, refresh embeddings.