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 stefanoskarakasis/Product-Marketing-Skills --skill customer-storiesgit clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-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/stefanoskarakasis/product-marketing-skills/customer-stories)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/customer-stories"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/customer-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/stefanoskarakasis/product-marketing-skills/customer-stories"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/customer-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 | $0.00094 | $0.02364 |
| Opus 5.5 | $0.00038 | $0.00946 |
| Sonnet 5.5 | $0.00019 | $0.00473 |
| Haiku 4.5 | $0.00009 | $0.00236 |
Grade A, and why
customer-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 8d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Stories
Takes a customer story from first idea to customer approval in a fixed seven-block structure. You choose the depth and the angle. The skill never invents evidence, never assumes who does what, and checks its own draft before handing it over.
Trigger
- When: A story needs a kickoff or brief, a call needs questions, notes need to become a story, a draft needs to go to the customer, or a finished story needs checking.
- Not for: Raw transcript synthesis →
interview-summary. Posts, releases or blurbs from a finished story →writing-assistant. One stat or quote on its own →proof-points. - Example prompts:
- "We want a story on Harbor & Pine. Where do we start?"
- "I have a customer call Thursday. What do I ask?"
- "Write a customer story from these notes."
- "Prepare what we send the customer for review."
- "Make this writing-assistant draft publishable." (edge: routes to Audit)
Inputs
- Args: Customer name. Depth:
short,standardordeep. Mode is read from what you paste and from the story's stage in the ledger: new story → Kickoff, questions → Interview, notes → Draft, draft ready → Review pack, a finished story → Audit. - Defaults: Three stats maximum. Seven blocks, fixed order.
- Context keys:
/foundation/brain.md(optional),/context/customer-stories.md(the ledger), pasted material, connector pulls (CRM, call recordings, survey comments, Drive).- Brain contract: Reads: Section 2 (who the story is for), 3 (alternatives, claims), 4 (voice), 6 (approved proof). Writes: none. Never writes to: Sections 1 to 6. Confirmed claims go to
proof-points.
- Brain contract: Reads: Section 2 (who the story is for), 3 (alternatives, claims), 4 (voice), 6 (approved proof). Writes: none. Never writes to: Sections 1 to 6. Confirmed claims go to
Pre-flight
- Load the brain. If missing, say once: "No PMM context found. Run
product-marketing-contextto make this significantly sharper. Continuing with assumption-based output." - Load the ledger. If missing, run Setup in Step 2. If the story already has a packet, show its stage and next action and resume there.
- A draft from
writing-assistantor anywhere else is an Audit. - Treat connector pulls and survey comments as unverified until the writer confirms them.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago Changed · +4 lines c15fb39b88c1
- 16d ago Changed 28c527acf37a
- 17d ago First seen · 169 lines · 94 tokens per session scan A 4bc00e9caaa5
customer-stories is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 2,364 once invoked, about $0.0004 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 2026-10-11.
Other skills, from other repositories
report
A way to export a chat card or reply as a standalone HTML report, meaning a file that can open in a browser without the chat application. It preserves the card template, including right-to-left Persian or left-to-right English layouts.
k8s-rightsize
Right-size Kubernetes CPU and memory requests from Prometheus usage (p95 CPU, p98 memory over 7 days), size the node count, tune KEDA autoscaling. Use when asked to rightsize workloads, cut node cost, or "how many nodes do we need".
owasp-security
Deep OWASP reference: Top 10 2025, ASVS 5.0, secure patterns, per-language quirks, LLM Top 10 and agentic AI security. Use for an in-depth security review, auth work, or hardening an LLM or agent app. For the everyday baseline use secure-coding.
fig
One self-contained HTML file holding a looping animated SVG, for ideas that move: flows, loops, retries, queues, fan-outs. Use when the user says "fig" or a diagram would be better animated.
brand
A project-specific visual identity for chat cards and saved reports, using the project's colors, logo, and fonts. It finds these details in the repository or asks the user for them, then stores the result in a committable `.readable/` folder.
workspace-rules
A set of guidelines for deciding which rules belong in a repository's workspace instructions and which should be enforced by its build or checks.