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 kazdenc/builder-skills --skill storiesgit clone --depth 1 https://github.com/kazdenc/builder-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/kazdenc/builder-skills/stories)<a href="https://agentmods.dev/skills/kazdenc/builder-skills/stories"><img src="https://agentmods.dev/badge/skills/kazdenc/builder-skills/stories/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/kazdenc/builder-skills/stories"><img src="https://agentmods.dev/badge/skills/kazdenc/builder-skills/stories.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 | $0.00074 | $0.01166 |
| Opus 5 | $0.00037 | $0.00583 |
| Sonnet 5 | $0.00015 | $0.00233 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
stories 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 9d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Stories & User Stories
Translate requirements into stories that a team can pick up and build. Prefer job stories over user stories — situations are more actionable than personas.
Why Job Stories Over User Stories
User stories anchor on a persona: "As a project manager..." But the same person behaves differently depending on context. A project manager at 9am triaging is doing a different job than at 3pm reporting to stakeholders.
Job stories anchor on the situation, which is what actually drives behavior.
| Format | Example | Strength |
|---|---|---|
| Job story: When [situation], I want to [motivation], so I can [outcome] | When I'm reviewing pull requests before standup, I want to see which ones block other work, so I can prioritize reviews that unblock the team | Captures context that shapes the solution |
| User story: As a [role], I want to [action], so that [benefit] | As a tech lead, I want to see PR priorities, so that I can review efficiently | Vague on when/why this matters |
Use user stories if the team is already fluent in them. Don't fight process for its own sake. But write the situation into the description either way.
Writing Good Stories
A good story is independent, negotiable, valuable, estimable, small, and testable (INVEST).
| Good | Bad | Why it's bad |
|---|---|---|
| When I'm halfway through a form and get interrupted, I want my progress saved, so I can resume without re-entering data | The system should auto-save forms | No situation, no outcome, not testable |
| When I receive a notification about a price drop, I want to see the item and the new price inline, so I can decide to buy without opening the app | As a user, I want push notifications | Too vague, no context, no clear done state |
| When I'm comparing two plans side by side, I want differences highlighted, so I can spot what matters without reading every line | Build a comparison table with highlighting | That's a solution, not a story |
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.
- 9d ago First seen · 100 lines · 74 tokens per session scan A e737f5e25f9b
stories is a skill published in the GitHub repository kazdenc/builder-skills (45 stars, last pushed 6mo ago), licensed MIT. It adds 74 tokens to every session and 1,166 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
commercial-opportunity-review
Review Product, offering, catalog, quote, and sale evidence for commercial opportunities.
demand-triage
Prepare classification, evidence gaps, and score inputs for product demand without crossing the funding boundary.
investment-preparation
Prepare an evidence-linked product investment packet while preserving the governed funding decision.
outcome-review
Review whether a funded product bet changed its intended outcome and append evidence-backed learning.
product-line-performance-review
Roll real Product evidence into a ProductLine review without changing the canonical reporting boundary.
stakeholder-brief
Prepare a concise owner or stakeholder brief with current decisions, evidence, bets, outcomes, roadmap, and provenance.