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/ololand-ai/ololand-plugins/cim-generategit 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/cim-generate)<a href="https://agentmods.dev/commands/ololand-ai/ololand-plugins/cim-generate"><img src="https://agentmods.dev/badge/commands/ololand-ai/ololand-plugins/cim-generate.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.01346 |
| Opus 5 | $0.00018 | $0.00673 |
| Sonnet 5 | $0.00007 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
cim-generate 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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIM Generate
Generate a Confidential Information Memorandum (CIM) — the sell-side marketing document used in M&A to present a target company to potential buyers. OloLand's generator pulls from the deal's reconciled financial snapshots, knowledge-graph risk/opportunity insights, and market research already on the platform, and only falls back to fresh web research for gaps that platform data doesn't cover — so exhibits are traceable to a source, not synthesized whole-cloth.
Usage
/cim-generate <deal_id> [section, section, ...]
/cim-generate read <deal_id> [section, section, ...]
Arguments
deal_id(required) — The deal to generate or read a CIM for. Must already exist in OloLand with at least a financial snapshot; run due diligence first if it doesn't.sections(optional) — A subset of the 14 sections to generate or read, if the user only wants part of the CIM (see the list below). Default: all 14.
Execution — generate (default)
- If the user asked for specific sections, map each user-phrased name to its exact snake_case identifier from the 14-section list below before calling the tool (e.g. "Executive Summary" →
executive_summary, "risk section" →risk_factors, "financials" →financial_performanceand/orfinancial_projections— confirm with the user when ambiguous). Only these identifiers are validsectionsvalues; the backend silently drops anything else. - Call
generate_cim(deal_id, sections=<optional list>)from the MCP server. This is a long-running operation — it returns atask_id, not the CIM itself. - Tell the user generation has started and poll
check_task_status(task_id)every ~5 seconds, up to a maximum of ~24 attempts (~2 minutes), until the status issuccessorfailure. A full 14-section CIM typically takes 30-90 seconds (platform data aggregation, then targeted market research for gaps, then section synthesis). - If the task is still pending after the polling budget, stop polling — do not loop indefinitely. Tell the user generation continues server-side, give them the
task_id, and invite them to ask again in a minute (you'll re-check withcheck_task_status(task_id)); the finished CIM also appears in the deal workspace regardless. - On success, the task result includes the
cim_id,sections_count, andword_count. - On failure, surface the error from the task result — do not retry silently more than once.
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.
- 5d ago First seen · 62 lines · 36 tokens per session scan A f3571829ef56
cim-generate is a command published in the GitHub repository ololand-ai/ololand-plugins (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 1,346 once invoked, about $0.0002 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
earnings-preview
Earnings preview presentation — 4-6 slide deck with consensus estimates, historical surprises, forward catalysts.
budget
Grant budget spreadsheet generation with forcing questions and task integration.
balance
Show KolmoPDF account credit balance.
convert
Use when the user attaches a bank statement PDF or asks for CSV/XLSX/QBO/Xero export of a converted statement. Do not use for spending analysis, reconciliation, or benchmark scoring — those have their own skills.
clean
Turn messy or multi-format CSV exports into one clean, categorized, analysis-ready file.
summary
Generate a one-page IBKR account summary from loaded Flex or local activity data.