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 ericrisco/rsc-harness --skill investor-materialsgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/investor-materials)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/investor-materials"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/investor-materials/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/ericrisco/rsc-harness/investor-materials"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/investor-materials.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 47 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.03144 |
| Opus 5 | $0.00044 | $0.01572 |
| Sonnet 5 | $0.00017 | $0.00629 |
| Haiku 4.5 | $0.00009 | $0.00314 |
Grade A, and why
investor-materials 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investor Materials — Data Room, One-Pager, Investor Update
The packaging layer of fundraising. You consume the deck, the model, and the metrics — then you organize, name, and circulate the documents an investor reads on their own time. You do not build the story, the spreadsheet, or the round strategy.
This skill produces exactly three artifacts:
- The data room — the organized, numbered, access-tracked folder of diligence files an investor opens after the meeting.
- The one-pager / teaser — the single page that earns the first meeting and rides along on a cold email.
- The investor update — the recurring email that keeps existing backers warm and primed for the follow-on.
One-line route-out: the persuasive story in slides is ../pitch-deck/SKILL.md; the numbers in a spreadsheet are ../financial-model/SKILL.md; the round strategy and investor pipeline are ../fundraising/SKILL.md. You package what they produce.
Decision table — is it yours?
| The ask | Owned here? | Route to |
|---|---|---|
| Set up / clean / rename the data room | Yes | — |
| Write the one-pager / teaser | Yes | — |
| Draft the recurring investor update | Yes | — |
| Build the slide deck / narrative arc | No | pitch-deck |
| Build projections / burn / runway / cap-table math | No | financial-model |
| Investor list, outreach strategy, SAFE vs priced, term sheet | No | fundraising |
| Cold first-touch email to a named VC | No | cold-outreach (you supply the one-pager it attaches) |
| LTV / CAC / payback / contribution-margin deep dive | No | unit-economics |
| Grant / non-dilutive funding narrative | No | grants |
| How the one-pager LOOKS (layout, brand) | No | brand-identity / presentations |
Intake gate (run before producing anything)
Two questions decide everything. Ask them, do not assume.
- Stage? pre-seed / seed / Series A — sets data-room size (seed skews 30–40 docs, Series A 55–70) and whether the one-pager leads with team or traction.
- What already exists? Is there a deck, a model, current metrics? You consume these. If they are missing and the real ask is to create them, STOP and route — building the deck is
pitch-deck, building the model isfinancial-model. Producing a one-pager with invented traction or a data room that points at a nonexistent model is the failure this gate prevents.
What ships with it
5 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.
- 9d ago First seen · 176 lines · 87 tokens per session scan A 210b598dacdd
investor-materials is a skill published in the GitHub repository ericrisco/rsc-harness (82 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 3,144 once invoked, about $0.0004 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
Due Diligence Coordinator
Coordinate and prepare for investor due diligence with organized data rooms.
extract-facts
Extracts Service/Incident/Cause facts from an incident-report document against a fixed schema, rejecting anything the schema doesn't define.
data-room-management
Build and maintain the investor data room — organize financials, metrics, legal docs, contracts, and customer references for fundraising due diligence. Use when the user asks about setting up a data room, organizing documents for due diligence, or preparing for an investor audit.
Due Diligence Coordinator
Coordinate and prepare for investor due diligence with organized data rooms.
ib-pitch-book
OpenDesign's investor pitch book: market map, moat, unit economics, and the ask — analyst-grade and diligence-ready. Built as a decision-grade fundraising pitch deck for growth-equity investors.
officecli-financial-model
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value'…