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 JuanMarchetto/agent-skills --skill vc-evaluatorgit clone --depth 1 https://github.com/JuanMarchetto/agent-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/juanmarchetto/agent-skills/vc-evaluator)<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/vc-evaluator"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/vc-evaluator/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/juanmarchetto/agent-skills/vc-evaluator"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/vc-evaluator.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 | $0.00087 | $0.01323 |
| Opus 5.5 | $0.00035 | $0.00529 |
| Sonnet 5.5 | $0.00017 | $0.00265 |
| Haiku 4.5 | $0.00009 | $0.00132 |
Grade A, and why
vc-evaluator 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 2mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VC Panel Evaluator
Simulate a complete venture capital investment panel evaluating your startup. Given a startup description, pitch deck, or project path, this skill researches real investors in your sector, builds personalized investor personas, and evaluates from each VC's perspective.
How It Works
- Parse Input — startup description, pitch deck, or project path + target stage (pre-seed/seed/A/B) + sector
- Startup Discovery — analyze the project's architecture, traction, market positioning, and team if a path is given; otherwise take the description as-is
- Investor Research — use WebSearch to find real VCs who invest in this sector and stage (see
agents/researcher.md) - Panel Construction — build 3-5 investor personas based on real people with distinct investment theses
- Parallel Evaluation — dispatch each investor as a parallel agent using
agents/investor.md, each evaluating from their unique lens - Partner Meeting Synthesis — simulate Monday partner meeting using
agents/synthesizer.md, modeling championing dynamics and fund-level strategy
Usage
"Would VCs fund this? It's a B2B SaaS for construction site logistics"
"Evaluate my startup for Series A — project is at ./my-saas"
"I'm raising a seed round for an AI agent marketplace, give me VC feedback"
"How would top fintech investors evaluate this pitch deck?"
Output
The evaluation produces:
- Verdict — PASS / PARTNER MEETING / TERM SHEET LIKELY
- Panel Scorecard — per-criterion scores from each VC with weighted averages
- Individual VC Feedback — what impressed them, what concerned them, key questions they'd ask in the pitch meeting
- Partner Meeting Simulation — who champions, who passes, key debates, outcome
- Funding Probability — X% at target stage with current pitch
- What Would Change The Outcome — max 5 specific actions that would move investors from pass to proceed
- Pitch Coaching — tailored to this specific panel's priorities and blind spots
What ships with it
10 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.
- 2mo ago First seen · 98 lines · 87 tokens per session scan A f36a7f2014cf
vc-evaluator is a skill published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 87 tokens to every session and 1,323 once invoked, about $0.0003 per session on Opus 5.5. 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.
vc-evaluator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vc-evaluatorJuanMarchetto/agent-skills | Skill | 5 | 7mo ago | MIT | A | 87 | Claude Code |
| x402browser-use/browser-use | Skill | 121k | yesterday | MIT | A | 166 | Claude Code |
| ai-engineering-toolkitsinhoneyy/master-skills | Skill | 17 | 5d ago | none | A | 47 | Claude Code |
| browser-usebrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 54 | Claude Code, Codex |
| open-sourcebrowser-use/browser-use | Skill | 121k | yesterday | MIT | A | 101 | Claude Code |
| accounting-software-selectionsickn33/agentic-awesome-skills | Skill | 50k | yesterday | MIT | A | 37 | Claude Code |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | 4d ago | Apache-2.0 | A | 61 | Claude Code |