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 sanky369/vibe-building-skills --skill foundation-sprintgit clone --depth 1 https://github.com/sanky369/vibe-building-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/sanky369/vibe-building-skills/foundation-sprint)<a href="https://agentmods.dev/skills/sanky369/vibe-building-skills/foundation-sprint"><img src="https://agentmods.dev/badge/skills/sanky369/vibe-building-skills/foundation-sprint/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/sanky369/vibe-building-skills/foundation-sprint"><img src="https://agentmods.dev/badge/skills/sanky369/vibe-building-skills/foundation-sprint.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 | $0.00223 | $0.02903 |
| Opus 5 | $0.00112 | $0.01452 |
| Sonnet 5 | $0.00045 | $0.00581 |
| Haiku 4.5 | $0.00022 | $0.00290 |
Grade A, and why
foundation-sprint 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 12d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundation Sprint
A method for starting a project the smart way: get clear on who you serve, what problem you solve, how you're radically different, and which approach to try first — then state it as one testable bet and prove it. Adapted from Click: How to Make What People Want (Jake Knapp & John Zeratsky, Character Capital). The original is a 2-day team workshop; here it runs as a fast, structured thinking session between you and the user.
Prime directive: the only question that matters is "Does it click?" A product clicks when it makes a simple, compelling promise that customers want, that the product delivers, and that they tell others about. Everything below exists to find that promise and expose where it might be wrong.
When to use it
| Mode | Trigger | Goal |
|---|---|---|
| A — Evaluate / start | A new idea, "should I build this?", "is this good?", choosing a direction | Produce a sharp, testable Founding Hypothesis + scorecard |
| B — Improve | An existing product, "how do I make this better?", stalled growth, weak differentiation | Reverse-engineer the current hypothesis, find the weakest prediction, fix it |
If it's unclear which, default to A. For B, see "Mode B" near the end.
Operating principles (these shape every output)
- Clarity is the bottleneck, not creativity. The "basics" are so obvious they get skipped — and that's exactly why teams misalign. Ask three founders who the customer is and you get three answers. Force them into the open.
- Differentiation is the #1 predictor of success. Aim for radical, not incremental. The goal is to make the strongest competitor (the "800-pound gorilla") look like junk for this customer. In an age where anyone can build anything fast with AI, what you build and how you stand out matter more than execution speed.
- Drag hidden predictions into the spotlight. Every idea secretly assumes a customer, a problem, an approach, and a reason people will switch. Name them. You may not like what you see (that's the point).
- Simple promises win. If the promise isn't simple, customers won't pay attention. "More storage + great search" beat every other inbox. Compress, don't accumulate features.
- Be the Decider, not a menu. At every convergence point, commit to one choice with a one-line reason. Offer a single backup, never an option buffet. (This is the book's "Decider decides" rule.)
- Honesty over optimism. "Differentiation only works if you can actually deliver it." Be aggressive about where you could win, then ruthless about whether you can keep the promise.
- Speed paradox: decide before you build. This whole exercise is a "pre-pivot" — pivot on paper, cheaply, before writing code.
What ships with it
2 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.
- 12d ago First seen · 136 lines · 223 tokens per session scan A ec36326ca31c
foundation-sprint is a skill published in the GitHub repository sanky369/vibe-building-skills (30 stars, last pushed 2mo ago), licensed MIT. It adds 223 tokens to every session and 2,903 once invoked, about $0.0011 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
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
dep-auditor
A read-only audit of a project’s third-party packages for known security issues, version health, and license facts. It uses the versions actually selected by lockfiles, which record the exact packages installed, rather than relying only on version ranges.
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
zh-readme
A tool for writing README files in Chinese after first examining a software project. A README is the main guide visitors see when they open a code repository.
env-manager
An environment-variable manager for project settings stored outside the code, often in .env files. It checks variable definitions and usage while keeping secret values out of reports and terminal output.