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 oncesylvia/fundraising-skills --skill warm-path-findergit clone --depth 1 https://github.com/oncesylvia/fundraising-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/oncesylvia/fundraising-skills/warm-path-finder)<a href="https://agentmods.dev/skills/oncesylvia/fundraising-skills/warm-path-finder"><img src="https://agentmods.dev/badge/skills/oncesylvia/fundraising-skills/warm-path-finder/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/oncesylvia/fundraising-skills/warm-path-finder"><img src="https://agentmods.dev/badge/skills/oncesylvia/fundraising-skills/warm-path-finder.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 | $0.00130 | $0.01933 |
| Opus 5 | $0.00065 | $0.00966 |
| Sonnet 5 | $0.00026 | $0.00387 |
| Haiku 4.5 | $0.00013 | $0.00193 |
Grade A, and why
warm-path-finder 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warm path finder
Targeting tells a founder which firms. This skill closes the gap everyone gets stuck on: which specific human to reach, and who can warmly introduce them. It does two jobs:
- Pinpoint the person — the partner / principal / senior investment manager
who actually owns your sector and stage at the target firm (pitching the
wrong person wastes the shot). See
references/finding-the-person.md. - Map & rank warm paths to that person — surface every legitimate route
from the founder's network, score by trust × reachability, and hand the best
one to the
warm-introskill. Seereferences/connection-mapping.md.
Read shared/references/outreach-ethics.md first. The whole skill lives or dies
on staying inside what's authorized and public (see the data-source tiers
below). Same anti-hallucination rule as the other research skills: a person or a
connection you assert must come from real data or live research, with a source —
never invent a partner, a title, or a mutual contact.
The hard line on data (read this before doing anything)
| ✅ Allowed | ❌ Not allowed |
|---|---|
| The founder's own authorized data: their Gmail, their Google/phone contacts, a LinkedIn connections export they downloaded | Reading the founder's LinkedIn graph via API or scraping (no API exists; scraping breaks ToS and risks a ban) |
| Public info: X/Twitter bios, firm team pages, portfolio lists, podcasts, conference speakers, Crunchbase/AngelList people | Crawling login-walled content at scale |
| The founder manually checking shared connections / DM-open status while logged in | Guessing or buying personal email addresses to blast |
If a step would cross this line, stop and tell the founder.
Step 1 — Pinpoint the right person
For a target firm, identify the specific decision-maker, not "the firm." See
references/finding-the-person.md. In short:
- Find the partner/principal who leads your sector & stage — via the firm's team page, who led the round for portfolio companies like yours (search " partner"), their public thesis/posts.
- A senior associate / principal / senior investment manager who covers your space can be the better first target than a famous GP — they're more reachable and looking to source. Note who sources vs. who decides.
- Capture their public footprint: firm bio, LinkedIn URL, X handle, recent writing/podcasts. This is research input, not contact-harvesting.
What ships with it
6 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 · 142 lines · 130 tokens per session scan A d68a72481871
warm-path-finder is a skill published in the GitHub repository oncesylvia/fundraising-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 130 tokens to every session and 1,933 once invoked, about $0.0006 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
nock
Nock — pressure-test a startup pitch deck against the real questions and bar that Nikunj Kothari applies to founders, before you take the shot. Use when someone wants to prep for a VC pitch, "see what a VC would ask," find the holes in their deck, or rehearse tough diligence questions. Also covers raise mechanics …
pitch-deck-review
Review a pre-seed or seed pitch deck the way a VC partner would. Finds the gaps, ranks them by how much damage they do, and rewrites the worst slides. Use whenever someone shares a pitch deck, fundraising deck, investor deck, seed deck, or pre-seed deck as a PDF, PPTX, images, or a link and wants feedback, a teardown…
thai-vc-fundraising
แผนระดมทุนสำหรับ Thai startup จาก Thai VC จริงปี 2026 (500 Global, AddVentures, Beacon VC, Krungsri Finnovate, SCB10X, KX, Bualuang Ventures, InnoSpace) — stage, check size, thesis จริงไม่ใช่ YC template ฝรั่ง.
thai-cashflow-survival
กางปฏิทิน 90 วันของ cashflow สำหรับ SME ไทย โดย lock timing ที่ฝรั่งไม่รู้ — credit term 30/60/90, VAT refund 3-6 เดือน, PND.1 (วันที่ 7), SSO (15), ภพ.30 (15), ภงด.50/51, เงินเดือน.
thai-financial-projection
คำนวน 3-yr P&L + cashflow สำหรับ SME ไทย ใช้ corporate tax tier ที่ถูกต้อง (0/15/20%), VAT cycle, SSO 5%+5%, ภงด.50/51 timing — ไม่ใช้ tax 20% flat แบบ template ฝรั่ง.
thai-influencer-deal
คำนวน net payout ของดีล KOL/KOC ที่ถูกกฎหมาย WHT ไทย (3% talent fee ในประเทศ, 5%/15% non-resident, affiliate revenue share หัก WHT แยก) — output รวมโครงสร้างสัญญา KOL ที่ใช้ได้จริง.