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 agentmods add commands/brainbytes-dev/everything-claude-finance/cap-tablegit clone --depth 1 https://github.com/brainbytes-dev/everything-claude-financeWhat 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 | $0.00008 | $0.01485 |
| Opus 5 | $0.00004 | $0.00743 |
| Sonnet 5 | $0.00002 | $0.00297 |
| Haiku 4.5 | $0.00001 | $0.00148 |
Grade A, and why
cap-table 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cap-table — Cap Table Analysis
What This Command Does
Builds, analyzes, and models capitalization tables including common stock, preferred stock (with all preference features), options/warrants, convertible instruments, and SAFEs. Models dilution impact of new rounds and produces waterfall analyses for exit scenarios.
When to Use
- Pre-funding cap table cleanup and modeling
- New round impact analysis (dilution to existing holders)
- Exit waterfall calculation (who gets what at various exit prices)
- SAFE/convertible note conversion modeling
- Option pool creation or expansion impact
- Secondary transaction pricing
How It Works
- Current State: Maps all outstanding securities — common, preferred (each series), options (vested/unvested), warrants, convertible notes, SAFEs
- Rights Mapping: Documents liquidation preferences, participation rights, anti-dilution provisions, conversion ratios
- Round Modeling: Applies new investment terms — pre/post-money valuation, option pool shuffle, pro-rata rights
- Dilution Analysis: Shows ownership percentages before and after, dilution per stakeholder class
- Waterfall Analysis: Calculates distribution at various exit values considering preference stacks
Example Usage
Input:
/cap-table company:"HealthOS" action:model-round round:series-a
Output:
# Cap Table — HealthOS Inc.
## Action: Series A Round Modeling | Date: 2026-03-14
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## Pre-Money Cap Table (Current State)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
| Holder | Shares | Type | Ownership |
|---------------------|-------------|---------------|-----------|
| Founder A | 4,000,000 | Common | 40.0% |
| Founder B | 3,000,000 | Common | 30.0% |
| Angel Investors | 1,000,000 | Common | 10.0% |
| SAFE Holders | (converts) | SAFE | ~8.3% |
| ESOP (allocated) | 800,000 | Options | 8.0% |
| ESOP (unallocated) | 200,000 | Option pool | 2.0% |
| Advisor pool | 170,000 | Options | 1.7% |
| **Fully Diluted** |**10,000,000**| | **100.0%**|
Outstanding SAFEs:
- SAFE 1: $500K at $6M cap, no discount (Angel Group Alpha)
- SAFE 2: $300K at $8M cap, 20% discount (Accelerator Beta)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## Series A Terms (Proposed)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
| Term | Value |
|---------------------------|------------------------------------|
| Pre-money valuation | $12,000,000 |
| Investment amount | $4,000,000 |
| Post-money valuation | $16,000,000 |
| Price per share | $1.20 |
| New shares issued | 3,333,333 |
| Option pool increase to | 15% post-money (shuffle) |
| Liquidation preference | 1x non-participating |
| Anti-dilution | Broad-based weighted average |
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## Post-Series A Cap Table
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
| Holder | Shares | Type | Pre-A % | Post-A % | Dilution |
|---------------------|-------------|-------------|---------|----------|----------|
| Founder A | 4,000,000 | Common | 40.0% | 27.6% | -12.4pp |
| Founder B | 3,000,000 | Common | 30.0% | 20.7% | -9.3pp |
| Angel Investors | 1,000,000 | Common | 10.0% | 6.9% | -3.1pp |
| SAFE → Common | 1,136,111 | Common | 8.3% | 7.8% | -0.5pp |
| Series A Investor | 3,333,333 | Pref A | — | 23.0% | New |
| ESOP (total) | 2,030,556 | Options | 10.0% | 14.0% | +4.0pp |
| Advisors | 170,000 | Options | 1.7% | — | (in ESOP)|
| **Fully Diluted** |**14,500,000**| |**100%** | **100%** | |
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## Exit Waterfall (1x Non-Participating Pref)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
| Exit Value ($M) | Series A | Founders | Angels/SAFEs | ESOP |
|-----------------|------------|------------|--------------|----------|
| $8M | $4.0M (pref)| $2.5M | $0.8M | $0.7M |
| $16M (1x) | $4.0M→conv | $4.4M | $2.4M | $2.2M |
| $30M | $6.9M | $8.3M | $4.4M | $4.2M |
| $50M | $11.5M | $13.8M | $7.4M | $7.0M |
| $100M | $23.0M | $27.6M | $14.7M | $14.0M |
Note: Series A converts to common at exit values where conversion
yields more than 1x preference ($17.4M+ exit).
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.
- 2d ago First seen · 121 lines · 8 tokens per session scan A 3c7ac4ebcda4
cap-table is a command published in the GitHub repository brainbytes-dev/everything-claude-finance (5 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 1,485 once invoked, about $0.0000 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.