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 fatihguner/foreman --skill building-story-stakesgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/building-story-stakes)<a href="https://agentmods.dev/skills/fatihguner/foreman/building-story-stakes"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/building-story-stakes/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/fatihguner/foreman/building-story-stakes"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/building-story-stakes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 49 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00076 | $0.03508 |
| Opus 5 | $0.00038 | $0.01754 |
| Sonnet 5 | $0.00015 | $0.00702 |
| Haiku 4.5 | $0.00008 | $0.00351 |
Grade A, and why
building-story-stakes 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 6d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Building Story Stakes
What keeps a listener hooked is not curiosity. It is the elephant you planted at the beginning -- the question they desperately need answered. Stakes are the gears that make stories work; without them, any narrative, however polished, becomes something an audience can take or leave. The framework identifies five discrete techniques for infusing stakes into a story, each learnable and each deployable in settings ranging from a Moth stage to a Series A pitch meeting. The entrepreneur who masters these techniques does not merely tell stories. That entrepreneur controls attention.
The Framework
Stakes answer a deceptively simple question: would the audience want to hear the next sentence? If the answer is no, the story has failed -- not in content, but in architecture. These five strategies address different failure modes of attention, and they work in combination. Some stories need all five. Others, naturally loaded with drama, need only the first. The key is diagnosis: knowing which strategy a given moment demands.
1. The Elephant
Every story must have an Elephant. The Elephant is the large, obvious thing in the room -- a clear statement of the need, the want, the problem, the peril, or the mystery. It tells the audience what to expect, gives them a reason to wonder, and infuses the story with instantaneous stakes.
The Elephant should appear within the first sixty seconds. Thirty seconds is better. Storytellers lack the luxury of trailers; when a speaker begins, the audience has no idea whether they are hearing a comedy, a tragedy, or a waste of their morning. Without an early Elephant, listeners check out.
The distinction matters. Consider two openings for the same company origin story:
- Version A: "Our co-founder grew up in a small town in Ohio. She studied engineering at State. She worked at three companies before starting ours."
- Version B: "When our co-founder was twenty-six, she bet her entire savings -- $11,400 -- on a product nobody in her industry believed would work. Our co-founder grew up in a small town in Ohio..."
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.
- 6d ago Changed · +209 lines · +76 tokens per session 5b797a3f040f
- 12d ago First seen · 1 lines · 0 tokens per session scan A e437c84b232a
building-story-stakes is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 7d ago), licensed MIT. It adds 76 tokens to every session and 3,508 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 2026-08-30.
Other skills, from other repositories
apply-golden-circle
Use when communicating a vision, pitch, or call to action and the audience isn't moved despite the content being factually clear — restructure the message to lead with Why (the belief or purpose driving the work), then How (the specific approach that makes it distinct), then What (the product or action itself)…
emotional-appeal-selector
Choose the emotional lever that will make an audience actually care about a message — and strip out the analytical priming that kills charity before the emotional ask lands. Use this skill whenever a message is technically correct but emotionally flat, whenever the user asks "how do I make them care", "nobody cares…
story-plot-selector
Pick the right story plot (Challenge / Connection / Creativity) and structure it so it drives the specific action you need — and decide whether to deliver it as a springboard story or a direct argument. Use this skill whenever the user needs to find, pick, or shape a story, anecdote, or case study for a message, talk…
chapter-writing
This skill should be used when the user asks to "write a chapter", "next chapter", "chapter outline", "draft chapter", "continue the story", "write a scene", "outline a chapter", or wants to write prose for a story project.
story-init
This skill should be used when the user asks to "start a new story", "initialize a story project", "create a story", "new book", "set up a story", or wants to begin a new fiction writing project from scratch.
character-management
This skill should be used when the user asks to "create a character", "update a character", "add a character", "build a family tree", "character relationships", "character timeline", "character arc", "character profile", or needs to manage characters in a story project.