cap-table-analysis

A guide for analyzing a company's cap table, which is the record of who owns which shares and rights. It covers ownership, employee share pools, share classes, funding rounds, and related securities using Slice data.

In plain words
What is it for?
Use it to answer questions about stakeholder holdings, ownership percentages, employee option pools, share classes, and funding rounds.
Why use it?
It keeps ownership calculations tied to the company's source data and makes clear whether results use issued, fully diluted, or as-converted shares.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/global-slice/claude-plugin/cap-table-analysis
Any agent
npx skills add Global-Slice/claude-plugin --skill cap-table-analysis
Clone the repo
git clone --depth 1 https://github.com/Global-Slice/claude-plugin

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,377 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.01377
Opus 5 $0.00039 $0.00688
Sonnet 5 $0.00016 $0.00275
Haiku 4.5 $0.00008 $0.00138

Measured 2d ago against content hash 6514daa6bac9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cap-table-analysis 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 2d 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.

plugins/slice-global/skills/cap-table-analysis/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cap Table Analysis

Scope

Use for company or stakeholder ownership, ESOP pools, share classes, and rounds. For single-security deep dives or vesting timelines, use securities-analysis. For employee grant compensation or PTEP, use equity-compensation-analysis. For exit proceeds, use waterfall-analysis.

Ground Truth And Calculation Modes

Slice data is the source of truth for specific cap-table answers. Stay scoped to the authenticated company tenant and keep every analysis anchored to the same as-of date when possible.

Always label the calculation mode:

  • Outstanding: issued shares on the legal share register.
  • Fully diluted: issued shares plus share-settled grants, warrants, and convertibles where applicable.
  • As-converted: preferred shares converted into ordinary-equivalent shares using the current conversion ratio.

Use assumptions only as a last resort and state them. Common defaults are private company, current tenant only, and equity-based awards.

Company-Level Workflow

For cap-table-wide questions:

  1. Use companies_get_summary for a one-shot company snapshot: company identity, total stakeholders, total grants, outstanding and fully diluted shares, and ESOP pool breakdown.
  2. Use cap_table_get_summary for cap-table aggregates: company outstanding, company fully diluted, total available pool, totals by security type, and totals by share class.
  3. Use ownership_get_company_breakdown when the question is specifically about outstanding vs fully diluted ownership totals.
  4. Use share_classes_list and rounds_list to explain the share-class and funding-round structure behind the cap table.
  5. Use rounds_get_total_raised only after discovering the round's share class IDs with rounds_list.
  6. Use cap_table_search_entries for paginated per-stakeholder cap-table rows when aggregate totals are not enough.

Prefer cap_table_get_summary before cap_table_search_entries; it is cheaper and already includes the high-level share-class and security-type breakdowns.

Read the full file on GitHub · 85 lines

Changes

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.

  1. 2d ago First seen · 85 lines · 79 tokens per session scan A 6514daa6bac9

Subscribe to this mod's changes

cap-table-analysis is a skill published in the GitHub repository Global-Slice/claude-plugin (9 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,377 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 2026-08-31.

Related

Other skills, from other repositories