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.
git clone --depth 1 https://github.com/ololand-ai/ololand-pluginsWrote 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/commands/ololand-ai/ololand-plugins/cap-table)<a href="https://agentmods.dev/commands/ololand-ai/ololand-plugins/cap-table"><img src="https://agentmods.dev/badge/commands/ololand-ai/ololand-plugins/cap-table/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/commands/ololand-ai/ololand-plugins/cap-table"><img src="https://agentmods.dev/badge/commands/ololand-ai/ololand-plugins/cap-table.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 | $0.00021 | $0.00727 |
| Opus 5.5 | $0.00008 | $0.00291 |
| Sonnet 5.5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00073 |
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.
What it actually says
Cap table
Use this workflow for holder ownership, dilution, supported SAFE/note conversion, and company-security proceeds. It is separate from an LP/GP fund waterfall.
- Resolve the deal explicitly, then call
mcp__ololand__get_cap_table(deal_id)to inspect issuers, exact baseline revision IDs, source references, and review state. A supplied ledger and a reviewed baseline are distinct from a published result. - For decision-facing ownership call
mcp__ololand__get_current_cap_table(deal_id, capability="capitalization.ownership"). For a published financing or proceeds workpaper selectcapitalization.pro_formaorcapitalization.proceeds. Report publication ID, receipt hash, revision and run IDs with the figures. A missing/currently ineligible publication is a gap; do not substitute a newer candidate or invent its missing values. - For an explicitly requested sensitivity, call
mcp__ololand__simulate_cap_tablewith the exact issuer/revision, a named scenario and a stable idempotency key. Reuse the key only to retry the identical request. Pass exact decimal strings. Financing usespre_money_value,subscriptions(holder ID/name/amount), optional fractionaltarget_unallocated_pool, and explicit confirmationsstandard_terms_confirmedandpricing_basis_confirmed. The supported price denominator includes outstanding common equivalents, awards, existing reserve, conversion shares and the round's pool increase. Ask for that convention and supported new-share rights; never infer confirmation. Post-money SAFE baselines also require explicit capitalization-definition confirmation; their cap denominator excludes the new round pool increase. - Proceeds require supplied equity consideration, seller expenses, escrow,
and
election_basis="hypothetical_optimization". Documented transaction elections are unsupported until dated election evidence can be bound by an adapter. Nonzero pro-rata escrow additionally requiresescrow_pro_rata_confirmed. Do not substitute enterprise value or add exercise/financing cash twice. - Show current and pro-forma ownership separately. Disclose treasury exclusions, pending convertibles, denominator, unsupported rights, assumptions, calculation gaps and source locations. Candidate calculations remain supplied-input scenarios even when arithmetic checks pass. No payment or securities issue occurs.
- Baseline creation/import, source correction, human review and inclusion in Full Analysis occur in the app's Cap table view. Never approve a baseline or IC package through MCP. Publication is independently gated by exact source and revision identity; a scenario does not become current on creation. Financing and proceeds also require a resolved, evidenced Assumption Controls record pinned to the exact transaction basis hash. The app can prepare an unverified control; human resolution and a new baseline revision pin the reviewed state.
If the connected server does not expose these tools, say the cap-table capability is unavailable on that server. Do not claim deployment from plugin installation. The first implementation supports US corporations and a restricted instrument matrix. Unsupported net exercise, bespoke conversion rights, anti-dilution, secondary/rollover transactions or contractual settlement rounding require an explicit gap and a supported adapter, not a generic formula.
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 · 54 lines · 21 tokens per session scan A a6aa616e5706
cap-table is a command published in the GitHub repository ololand-ai/ololand-plugins (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 21 tokens to every session and 727 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-21.
Other commands, from other repositories
analyze-bond-rv
Analyze a bond's relative value vs yield curves and credit spreads with scenario stress testing.
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
merit-reconcile
Preview or check the status of Stripe → Merit payout reconciliation (read-only).
cost-per-task
Compute cost-per-successful-task unit economics from usage and cost data, including retries, failures, and quality thresholds.
audit-checklist
Perform an internal audit, review controls, or prepare for an external financial audit.
scan
Scan AWS account for cost optimization.