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 marcos-sponton/frameworks-as-skills --skill pattern-breakersgit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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/marcos-sponton/frameworks-as-skills/pattern-breakers)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/pattern-breakers"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/pattern-breakers.svg" alt="Measured on agentmods" 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 | $0.00264 | $0.02850 |
| Opus 5 | $0.00132 | $0.01425 |
| Sonnet 5 | $0.00053 | $0.00570 |
| Haiku 4.5 | $0.00026 | $0.00285 |
Grade A, and why
pattern-breakers 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 7d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Breakers
Mike Maples Jr's framework for finding — and testing — breakthrough startup ideas. Distilled from the 2024 book Pattern Breakers: Why Some Start-Ups Change the Future (co-authored with Peter Ziebelman), plus 15+ years of Maples's essays on Medium and Substack, his Pattern Breakers podcast (formerly Starting Greatness), and long-form appearances (Lenny's Newsletter 2024, Guy Kawasaki, Christopher Lochhead, EUVC, Clearer Thinking, and others).
This skill helps the assistant (Claude or Codex) think in Maples's mode, not just recite his three-word framework. It's opinionated because Maples is opinionated: breakthroughs come from starting with the right insight about an inflection, not from iterating your way there from a consensus starting point. The whole method is built to resist the pattern-matching reflex that dominates most startup and investor thinking.
When this skill activates
Use this skill when the user is:
- Evaluating whether a startup idea is a real breakthrough or a me-too / Uber-for-X derivative.
- Asking "why now?" or "is this a real opportunity?" for a specific idea.
- Trying to distinguish an inflection from a trend.
- Testing whether their insight is both non-consensus AND right.
- Writing or critiquing a startup pitch, memo, or one-pager.
- Deciding whether to commit years (or capital) to a bet.
- Doing investor-side due diligence on an early-stage company.
- Planning to "iterate to PMF" and needs to check whether the starting insight is strong enough that iteration can compound.
- Thinking about AI (or any macro shift) as an inflection and where the specific new capability lives.
- Post-launch, checking whether the story still holds together as a pattern break or has quietly become an incremental optimization.
Do NOT use this skill when:
- The user has an existing product with proven PMF and is optimizing it — Maples's method is upstream of PMF. Suggest Playing to Win, continuous discovery, or the Lean Startup toolkit for that phase.
- The question is purely operational or execution ("how do we ship faster?", "how do we hire a VP Eng?").
- The user is at growth stage and asking about scaling — use Blitzscaling / GTM playbooks.
- The user needs a diagnosis of what's broken in a company — use Rumelt (
good-strategy-bad-strategy). - The user just wants a book summary. Give them the book link and don't run the framework at them.
What ships with it
11 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.
- evals/evals.json 7.8 KB
- README.md 6.2 KB
- references/applications.md 8.2 KB
- references/author-live-sources.md 8.5 KB
- references/examples.md 15 KB
- references/heuristics.md 21 KB
- references/method.md 13 KB
- references/post-book.md 13 KB
- references/prompts.md 7.7 KB
- references/sources.md 9.4 KB
- references/voice-and-tone.md 15 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.
- 7d ago First seen · 101 lines · 264 tokens per session scan A fa3cef6bcb42
pattern-breakers is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 264 tokens to every session and 2,850 once invoked, about $0.0013 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 skills, from other repositories
acquire-skills
Find and install skills for what you're doing — tech or reasoning gaps. Matches activity and tech context to relevant skills. Use when entering unfamiliar tech, stuck on a reasoning challenge, or no skill fits.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
endpoint-discovery
Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.
param-miner
Discover hidden HTTP parameters in web applications that could reveal hidden functionality or vulnerabilities. Use when testing APIs, when looking for hidden parameters like admin or debug, or when the user mentions parameter discovery.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.