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 K-Dense-AI/mimeographs --skill whitney-wolfe-herdgit clone --depth 1 https://github.com/K-Dense-AI/mimeographsWrote 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/k-dense-ai/mimeographs/whitney-wolfe-herd)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/whitney-wolfe-herd"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/whitney-wolfe-herd/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/k-dense-ai/mimeographs/whitney-wolfe-herd"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/whitney-wolfe-herd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00121 | $0.01054 |
| Opus 5 | $0.00060 | $0.00527 |
| Sonnet 5 | $0.00024 | $0.00211 |
| Haiku 4.5 | $0.00012 | $0.00105 |
Grade A, and why
whitney-wolfe-herd 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Whitney Wolfe Herd
Whitney Wolfe Herd is the founder and CEO of Bumble, known for fundamentally rewiring the social dynamics of the internet by empowering women to make the first move. Her thinking is characterized by a unique blend of deep emotional intelligence, trauma recovery, and strict product mechanics. She views technology not as an end in itself, but as a tool with a profound responsibility to engineer kindness and facilitate real-world connection.
Reach for this skill whenever you're advising on platform safety, double-sided marketplace dynamics, purpose-driven entrepreneurship, product constraints, or navigating professional setbacks and trauma.
Core principles
- Tech Responsibility & Engineered Kindness: Platform creators are inherently responsible for user behavior; you must design strict constraints that make kindness as viral as toxicity.
- Turn Personal Pain into Collective Strength: Shift your mindset from "me" to "we" after a setback, using your trauma as the foundational purpose to build solutions for others.
- Focus on Core Inputs, Not Outputs: Evaluate business health by looking at whether users are finding what they came for, rather than chasing lagging vanity metrics like sheer volume.
- Technology Should Facilitate Offline Connection: Design connection tools with the explicit goal of getting people off their screens and into the real world.
For detailed rationale and quotes, see references/principles.md.
How Whitney Wolfe Herd reasons
Wolfe Herd approaches business and product design through a deeply human, empathetic lens, always starting with the "why." She asks who a product is helping and whether it serves the greater good. She dismisses traditional Silicon Valley playbooks that prioritize sheer scale, screen time, or growth at all costs, recognizing that in a double-sided marketplace, uncurated volume destroys the user experience.
Instead of trying to invent entirely new behaviors, she looks for established habits and applies a single, powerful constraint to change the social outcome—a model she calls Reversing the Wheel. She also views virality as a neutral mechanism (The Viral Coin), believing that if platforms can scale hate, they can be intentionally designed to scale accountability and positivity. For a full list of her conceptual lenses, see references/mental-models.md.
What ships with it
60 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.
- _workspace/agents_output.e584bd6c.json 11 KB
- _workspace/clustered_corpus.e584bd6c.json 26 KB
- _workspace/discovery/books.json 11 KB
- _workspace/discovery/essays.json 9.9 KB
- _workspace/discovery/frameworks.json 11 KB
- _workspace/discovery/interviews.json 11 KB
- _workspace/discovery/letters.json 10 KB
- _workspace/discovery/papers.json 10 KB
- _workspace/discovery/podcasts.json 11 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 28 KB
- _workspace/discovery/talks.json 7.0 KB
- _workspace/distilled/src_001.e584bd6c.json 3.4 KB
- _workspace/distilled/src_003.e584bd6c.json 5.0 KB
- _workspace/distilled/src_005.e584bd6c.json 1.8 KB
- _workspace/distilled/src_006.e584bd6c.json 533 B
- _workspace/distilled/src_010.e584bd6c.json 4.5 KB
- _workspace/distilled/src_011.e584bd6c.json 5.2 KB
- _workspace/distilled/src_012.e584bd6c.json 6.3 KB
- _workspace/distilled/src_013.e584bd6c.json 5.4 KB
- _workspace/distilled/src_014.e584bd6c.json 602 B
- _workspace/distilled/src_015.e584bd6c.json 6.2 KB
- _workspace/distilled/src_016.e584bd6c.json 5.9 KB
- _workspace/distilled/src_017.e584bd6c.json 3.0 KB
- _workspace/distilled/src_020.e584bd6c.json 4.4 KB
- _workspace/distilled/src_021.e584bd6c.json 5.1 KB
- _workspace/distilled/src_022.e584bd6c.json 5.7 KB
- _workspace/distilled/src_025.e584bd6c.json 489 B
- _workspace/distilled/src_026.e584bd6c.json 5.5 KB
- _workspace/distilled/src_027.e584bd6c.json 556 B
- _workspace/distilled/src_028.e584bd6c.json 663 B
- _workspace/distilled/src_029.e584bd6c.json 1.1 KB
- _workspace/distilled/src_030.e584bd6c.json 474 B
- _workspace/distilled/src_031.e584bd6c.json 494 B
- _workspace/distilled/src_032.e584bd6c.json 3.2 KB
- _workspace/distilled/src_034.e584bd6c.json 4.0 KB
- _workspace/distilled/src_040.e584bd6c.json 2.5 KB
- _workspace/raw/src_001.json 2.8 KB
- _workspace/raw/src_003.json 8.3 KB
- _workspace/raw/src_005.json 1.3 KB
- _workspace/raw/src_006.json 1.9 KB
- _workspace/raw/src_010.json 7.2 KB
- _workspace/raw/src_011.json 12 KB
- _workspace/raw/src_012.json 62 KB
- _workspace/raw/src_013.json 15 KB
- _workspace/raw/src_014.json 2.7 KB
- _workspace/raw/src_015.json 96 KB
- _workspace/raw/src_016.json 22 KB
- _workspace/raw/src_017.json 2.9 KB
- _workspace/raw/src_020.json 50 KB
- _workspace/raw/src_021.json 26 KB
- _workspace/raw/src_022.json 43 KB
- _workspace/raw/src_025.json 1.8 KB
- _workspace/raw/src_026.json 45 KB
- _workspace/raw/src_027.json 4.3 KB
- _workspace/raw/src_028.json 2.6 KB
- _workspace/raw/src_029.json 35 KB
- _workspace/raw/src_030.json 17 KB
- _workspace/raw/src_031.json 3.4 KB
- _workspace/raw/src_032.json 6.3 KB
- _workspace/raw/src_034.json 6.4 KB
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 · 57 lines · 121 tokens per session scan A cb3dca3a9722
whitney-wolfe-herd is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 25d ago), licensed MIT. It adds 121 tokens to every session and 1,054 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…