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 swan-gtm/gtm-skills --skill vc-portfolio-researchgit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/vc-portfolio-research)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/vc-portfolio-research"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/vc-portfolio-research/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/swan-gtm/gtm-skills/vc-portfolio-research"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/vc-portfolio-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00099 | $0.00961 |
| Opus 5 | $0.00049 | $0.00481 |
| Sonnet 5 | $0.00020 | $0.00192 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
vc-portfolio-research 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 9d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VC portfolio research (demo-safe)
Analyzes a venture capital or private equity firm's portfolio companies to surface how those companies use your product — product penetration, plan mix, usage, AI adoption, and open CRM pipeline.
The core judgment is the demo-safe split: the partner-facing document excludes all financial figures (no ARR, revenue, or deal amounts). A separate internal spreadsheet keeps full account-level detail — including ARR — for your team only.
Typical trigger: paste a firm portfolio URL and ask for a usage / portco analysis, or a "demo-safe portfolio summary."
One-liner: paste a VC/PE portfolio URL → the skill runs → you get a partner-safe doc of product usage, AI adoption, and pipeline across the portfolio, plus an internal sheet with the ARR detail your team needs.
How it runs
- Extract the portfolio — fetch and parse the firm's portfolio page (with fallbacks for JS-rendered sites; a pasted company list works when the site doesn't scrape cleanly).
- Match accounts by email domain — resolve each portfolio company to an account in the data warehouse: paying status, plan type, tasks used (past 30 days), AI feature milestones, and ARR.
- Pull open pipeline — open CRM opportunities by company domain (deal name, stage, close date, owner).
- Produce the two-artifact output (below), then update a portfolio registry entry (firm, date, doc/sheet links, portco → domain → account IDs) so downstream skills — like pipeline-overlap analysis — can reuse the portfolio mapping without re-scraping.
Outputs
Three artifacts in a shared drive, under Partners > {Firm Name}:
- Folder —
{Firm Name}— container for the doc + sheet. - Partner-facing doc —
{Firm Name} — Portfolio Analysis(demo-safe, no financials): executive summary of the portfolio footprint; paying-vs-free penetration and plan-tier view; usage and AI-adoption highlights (feature-level, not dollars); open opportunities with no amounts; additional insights (upsell angles, growth signals, greenfield list); and an appendix on match quality and ambiguous domains. Default sharing: internal domain only — an external link is created only with explicit confirmation. - Internal sheet —
{Firm Name} — Account Data(never shared externally): account IDs, domains, ARR, plan, paying status, tasks (30d), plus a summary tab with the portfolio financial snapshot and plan breakdown.
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.
- 9d ago First seen · 59 lines · 99 tokens per session scan A 861ddb9bcb3e
vc-portfolio-research is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 961 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…