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 agentmods add skills/ferdinandobons/startup-skill/startup-designnpx skills add ferdinandobons/startup-skill --skill startup-designgit clone --depth 1 https://github.com/ferdinandobons/startup-skillWrote 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/ferdinandobons/startup-skill/startup-design)<a href="https://agentmods.dev/skills/ferdinandobons/startup-skill/startup-design"><img src="https://agentmods.dev/badge/skills/ferdinandobons/startup-skill/startup-design.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 | $0.00108 | $0.07204 |
| Opus 5 | $0.00054 | $0.03602 |
| Sonnet 5 | $0.00022 | $0.01441 |
| Haiku 4.5 | $0.00011 | $0.00720 |
Grade A, and why
startup-design 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 6d 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Startup Design
A structured, multi-phase skill that takes a startup idea from raw concept to validated design. It produces a complete set of markdown documents organized by domain, with built-in progress tracking so work survives session interruptions.
How It Works
The process has 8 numbered phases executed sequentially, plus a Pre-Flight Check (Phase 0.5) and a Customer Discovery gate (Phase 3.7). Each phase produces output files and updates the progress tracker. If a session is interrupted, resume from the last completed checkpoint.
PRE-FLIGHT → INTAKE → BRAINSTORM → RESEARCH → [Research Gate] → CUSTOMER DISCOVERY → [Interview Gate] → STRATEGY → BRAND → PRODUCT → FINANCIAL → VALIDATION
Modes
Full Mode (default): Execute all phases in order, including Pre-Flight and Customer Discovery. Best for thoroughly designing a startup from scratch.
Fast Track Mode: When the user says they want a "quick validation," "rapid assessment," or similar, or when time/budget is clearly limited, run a compressed version:
- Phase 0.5 (Pre-Flight Check) — always run, takes 5 minutes
- Phase 1 (Intake) — shortened to 1 round of questions; capture any prior customer conversations
- Phase 2 (Brainstorm) — 3 variations instead of 5-8
- Phase 3 (Research) — Wave 1 + Wave 2 only (skip customer voice and distribution deep-dives)
- Phase 3.5 (Research Gate) — go/no-go checkpoint
- Phase 3.7 (Customer Discovery) — if founder has 5+ prior conversations, document them; if not, run at least 3 interviews before proceeding
- Phase 4 (Strategy) — Lean Canvas only
- Skip Phase 5 (Brand) and Phase 6 (Product)
- Phase 7 (Financial) — Revenue model only, Stage A (assumption-based), no full projections
- Phase 8 (Validation) — Scorecard + top 3 experiments only
Fast Track produces fewer files but still gives the founder a clear go/no-go signal with evidence. Note in PROGRESS.md that Fast Track mode was used, so a future session can expand to full mode if the idea passes validation.
What ships with it
15 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.
- references/customer-interview.md 8.6 KB
- references/frameworks.md 6.1 KB
- references/honesty-protocol.md 5.0 KB
- references/industry-benchmarks.md 2.8 KB
- references/intake-questions.md 2.6 KB
- references/output-guidelines.md 6.5 KB
- references/output-specs.md 5.7 KB
- references/research-principles.md 2.7 KB
- references/research-scaling.md 4.8 KB
- references/research-synthesis.md 6.4 KB
- references/research-wave-1-market.md 6.7 KB
- references/research-wave-2-competitors.md 7.5 KB
- references/research-wave-3-customers.md 8.3 KB
- references/research-wave-4-distribution.md 4.1 KB
- references/verification-agent.md 5.1 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.
- 6d ago First seen · 477 lines · 108 tokens per session scan A 08f5ea98d6fc
startup-design is a skill published in the GitHub repository ferdinandobons/startup-skill (888 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 7,204 once invoked, about $0.0005 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
battlecard-competitive-intelligence
Know your competitor's weaknesses before the call. Practice your pitch against an AI buyer. Capture intel after every deal. 11 tools for sales teams. Free tier, no signup needed.
saas-recon
Deep OSINT reconnaissance on any SaaS/tech company. Discovers subsidiaries, maps infrastructure, finds every site embedding or linking to the target's technology via certificate transparency, DNS, archives, code search, live browser inspection, analytics correlation, and business intelligence. Produces a comprehensive…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
golden-rss
Use when testing the rss golden build.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…