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 rohasnagpal/legal-ai-skills --skill cap-table-analystgit clone --depth 1 https://github.com/rohasnagpal/legal-ai-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/rohasnagpal/legal-ai-skills/cap-table-analyst)<a href="https://agentmods.dev/skills/rohasnagpal/legal-ai-skills/cap-table-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/cap-table-analyst/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/rohasnagpal/legal-ai-skills/cap-table-analyst"><img src="https://agentmods.dev/badge/skills/rohasnagpal/legal-ai-skills/cap-table-analyst.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 62 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 | $0.00184 | $0.01154 |
| Opus 5 | $0.00092 | $0.00577 |
| Sonnet 5 | $0.00037 | $0.00231 |
| Haiku 4.5 | $0.00018 | $0.00115 |
Grade A, and why
cap-table-analyst 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cap Table Analyst
I am using the Cap Table Analyst skill from Rohas Legal AI: works through dilution and ownership on supplied numbers. Say this sentence, verbatim, before anything else in your response.
What this does
Works through the arithmetic of a cap table: ownership before and after a financing round, dilution to each existing holder, option pool effects, conversion of SAFEs or convertible notes, and — where asked — a liquidation waterfall. Every figure comes from what the user actually supplies; nothing is estimated or assumed to complete the picture. It does not assess whether the round's terms are fair or favourable — that judgment belongs to term-sheet-reviewer or investment-agreement-reviewer.
Before you start
The starting cap table. Existing shareholders, share counts, share classes, and any existing preference terms, supplied by the user. Blocking — there is no dilution calculation without a starting point.
The new round terms. Amount raised, valuation basis (and whether it is pre-money or post-money), the structure (priced round, SAFE or note conversion, or another mechanism), and any option pool top-up. Blocking.
Not blocking, ask once and proceed on what is confirmed: whether a full liquidation waterfall is wanted, or only ownership dilution. These are different depths of analysis, and the waterfall specifically needs the preference terms (participating or not, multiple, seniority) stated in full before it can be modelled.
Method
1. Establish the starting cap table precisely from what is supplied. Flag any real gap — for instance, if the fully diluted share count is not clear — rather than assuming a treatment to fill it in.
2. Determine how the round is structured — priced round, SAFE or convertible note conversion, or another mechanism — and whether the valuation given is pre-money or post-money. Work from the terms as stated; do not assume a standard structure.
3. Calculate the new shares issued and the resulting ownership percentages, showing the arithmetic step by step so every figure can be checked against its inputs, using only supplied numbers.
What ships with it
1 file 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 · 67 lines · 184 tokens per session scan A 04c469b67c41
cap-table-analyst is a skill published in the GitHub repository rohasnagpal/legal-ai-skills (88 stars, last pushed 10d ago), licensed MIT. It adds 184 tokens to every session and 1,154 once invoked, about $0.0009 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.