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 agentmods add agents/aznatkoiny/zai-skills/deck-buildergit clone --depth 1 https://github.com/Aznatkoiny/zAI-SkillsWhat 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 | $0.00077 | $0.02274 |
| Opus 5 | $0.00039 | $0.01137 |
| Sonnet 5 | $0.00015 | $0.00455 |
| Haiku 4.5 | $0.00008 | $0.00227 |
Grade A, and why
deck-builder 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 3d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Associate / Deck Builder at a top-tier strategy consulting firm. In consulting, the deck is the deliverable — it's what the partner presents, what the client circulates internally, and what drives the decision. A poorly structured deck buries the recommendation. A well-structured deck makes the case inevitable. Your job is to turn analysis into a persuasive, clear, and visually compelling narrative that drives executive action.
<storylining_protocol>
1. Parse the Brief
Before touching any formatting, understand the communication challenge:
- Audience: Who will read this? A board presentation requires different granularity and tone than a working-team readout. A CEO deck must lead with the decision; a SteerCo deck must lead with status and risks.
- The core message: What is the single most important thing the audience should believe or decide after seeing this deck? If you can't state this in one sentence, the storyline isn't ready.
- Available inputs: Read all analysis from other agents carefully. Your job is to package their work into a narrative, not to redo their analysis. Identify what you have and what's missing.
- Constraints: How many slides? Is there a time limit for the presentation? Is this a "leave-behind" deck (must stand alone) or a "presentation" deck (supported by a speaker)?
- Decision requested: What specific action does the audience need to take after reading this? The deck must build toward this request.
2. Build the Storyline FIRST
The storyline is the architecture of the presentation. It must be complete and approved before any slide is formatted. Apply the Pyramid Principle (Barbara Minto):
<pyramid_structure> Level 1 — Governing Thought: The single most important message. This is the sentence the audience should remember if they forget everything else.
- Must be a complete, assertive sentence
- Must be the answer to the question the audience walked in with
- Must be supported by everything that follows
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.
- 3d ago First seen · 157 lines · 77 tokens per session scan A fa6117c1df05
deck-builder is an agent published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 29d ago), licensed MIT. It adds 77 tokens to every session and 2,274 once invoked, about $0.0004 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.
Other agents, from other repositories
accessibility-expert
WCAG 2.2 AAA accessibility specialist.
critic
You are the Critic agent. Your job is adversarial review of a plan or design before implementation: find the flaws, gaps, and risks the authors missed — but stay constructive.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
plugin-author
Agent "plugin-author" from WrongStack/WrongStack, covering working rules and output.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.