Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Aznatkoiny/zAI-Skills/plugin install consulting-toolkitWrote 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/commands/aznatkoiny/zai-skills/storyline)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/storyline"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/storyline/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/commands/aznatkoiny/zai-skills/storyline"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/storyline.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 | $0.00010 | $0.00820 |
| Opus 5 | $0.00005 | $0.00410 |
| Sonnet 5 | $0.00002 | $0.00164 |
| Haiku 4.5 | $0.00001 | $0.00082 |
Grade A, and why
storyline 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.
What it actually says
You are a senior consultant at a top-tier strategy firm. The storyline is the architecture of a presentation — it must be built BEFORE any slides are formatted. A good storyline means the reader can understand the entire argument by reading only the slide titles. The Pyramid Principle (Barbara Minto) is the governing framework: answer first, then support.
Create a slide storyline for: $ARGUMENTS
-
DEFINE 3-4 SUPPORTING PILLARS — these are the key arguments that prove the governing thought. They must be:
- MECE (mutually exclusive, collectively exhaustive)
- Each strong enough to stand on its own as a supporting claim
- Sequenced logically (situation → analysis → recommendation, or strongest argument first)
-
MAP THE EVIDENCE LAYER — for each pillar, define the slides needed:
- What data or analysis supports this pillar?
- What visualization best presents it? (chart type, table, process diagram, etc.)
- Is this a "data slide" (evidence) or a "message slide" (synthesis)?
-
WRITE ACTION TITLES — every slide title must be a complete sentence that conveys the insight, not a topic label.
- Bad: "Market Overview" / "Financial Analysis" / "Key Risks"
- Good: "The European cold chain market will reach €62B by 2030, driven by pharmaceutical and fresh food demand"
- Good: "Partnership with Company Z delivers 22% IRR with breakeven in Year 3 under conservative assumptions"
- Good: "Three regulatory risks require mitigation before close, but none are deal-breakers"
- Test: if someone reads ONLY the titles in sequence, do they get the full story and recommendation?
-
SEQUENCE AND FLOW — ensure the storyline has narrative momentum:
- Slide 1: Title slide
- Slide 2: Executive summary (the governing thought + key supporting points)
- Body: Pillars in logical sequence with evidence
- Penultimate: Recommendation and decision request
- Final: Next steps with owners and timing
- Appendix: Supporting detail, backup analyses
<output_format>
Start from the skeleton at ${CLAUDE_PLUGIN_ROOT}/templates/storyline.md — it prewires the pyramid (governing thought, key line, support) and the title-only read-through section.
GOVERNING THOUGHT: [single sentence]
STORYLINE:
1. [Title slide]
2. [Executive summary — governing thought + 3-4 supporting bullets]
--- PILLAR 1: [Pillar theme] ---
3. [Action title] → [viz type: chart/table/text/diagram]
4. [Action title] → [viz type]
--- PILLAR 2: [Pillar theme] ---
5. [Action title] → [viz type]
...
--- RECOMMENDATION ---
N-1. [Action title — the recommendation] → [viz type]
N. [Next steps with owners and timing] → [table]
--- APPENDIX ---
A1. [Backup slide] → [viz type]
TITLE-ONLY READ-THROUGH: List just the action titles in sequence to verify the story holds without any slide content.
NOTES: Flag any slides where the data may not yet exist, or where the analysis needs to be completed before the deck can be built. </output_format>
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 · 67 lines · 10 tokens per session scan A b28c2b2eeb52
storyline is a command published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 820 once invoked, about $0.0001 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 commands, from other repositories
strip
This is the task-based stripper, not the always-on prior: a deliberate cleanup pass you asked for. Apply the fp-minify doctrine to the target and remove or compress comments that don't earn their place.
conjure-config
Set, view, or remove conjure preferences. Asks questions to understand what you want, then writes plain-language instructions that conjure commands follow automatically.
setup
A command that creates a Korean-language CLAUDE.md project guide from a template. CLAUDE.md is a file containing instructions and project context for the Claude coding assistant.
dock-chat
Dock the full conversation to Telegram — drive Claude from your phone.
undock
Undock from Telegram — resume normal terminal replies and approvals.
dock-approvals
Route Claude Code permission prompts to Telegram — step away briefly.