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 four-fitsgit 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/four-fits)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/four-fits"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/four-fits/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/marcos-sponton/frameworks-as-skills/four-fits"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/four-fits.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 | $0.00257 | $0.02723 |
| Opus 5 | $0.00129 | $0.01362 |
| Sonnet 5 | $0.00051 | $0.00545 |
| Haiku 4.5 | $0.00026 | $0.00272 |
Grade A, and why
four-fits 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 11d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Four Fits
Brian Balfour's Four Fits framework — the four interdependent fits any venture-backed company needs to hit $100M+, plus Growth Loops as the compounding alternative to funnels. Distilled from Balfour's essays on brianbalfour.com, the Reforge blog, his Substack (blog.brianbalfour.com), and podcast appearances including Lenny Rachitsky's podcast (2023 + 2024). Balfour has not written a book — the entire body of work is essays, Reforge courses, and long-form conversations, so this skill IS the book, structured.
This skill helps your agent think about growth as a system of four coupled fits, not as a funnel or a bag of tactics. It's opinionated because Balfour is opinionated: growth isn't hacks, channels don't mold to products, funnels decay while loops compound, and the ARPU-CAC danger zone is where most SaaS companies die.
When this skill activates
Use this skill when the user is:
- Trying to diagnose why growth has stalled or slowed (almost always one of the four fits has broken).
- Deciding whether to move up-market, down-market, or launch a new tier.
- Debating channel strategy ("should we do paid?", "should we hire a sales team?", "what about content?").
- Pricing a new product or setting ARPU targets.
- Designing a growth model or growth loop from scratch.
- Critiquing a "growth plan" that reads as a funnel with tactics stapled to it.
- Deciding whether to copy another company's playbook (Airbnb, Slack, HubSpot, Notion).
- Hiring or scaling a growth team.
- Evaluating whether a new AI-era channel (ChatGPT, agent-driven discovery) fits their product.
- Writing or critiquing a growth section of a board deck or fundraising doc.
Do NOT use this skill when:
- The user is pre-PMF and searching for problem/solution. Balfour is explicit that the framework assumes you're past problem-solution and heading toward the $100M scale question. Suggest JTBD / continuous discovery / Lean instead.
- The user's question is purely tactical execution ("what's the best paid ad copy for X?"). That's below the level of the framework.
- The user just wants a summary of Four Fits. Point them at brianbalfour.com/four-fits-growth-framework and don't run the diagnostic.
- The user's problem is org design, hiring, or culture with no growth-system angle.
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 7.5 KB
- README.md 5.8 KB
- references/applications.md 8.6 KB
- references/author-live-sources.md 9.4 KB
- references/examples.md 12 KB
- references/heuristics.md 14 KB
- references/method.md 13 KB
- references/post-book.md 14 KB
- references/prompts.md 7.5 KB
- references/sources.md 7.9 KB
- references/voice-and-tone.md 12 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.
- 11d ago First seen · 99 lines · 257 tokens per session scan A 8ea6ea89d101
four-fits is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 257 tokens to every session and 2,723 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.