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 ololand-ai/ololand-plugins --skill cmd-verifygit 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/skills/ololand-ai/ololand-plugins/cmd-verify)<a href="https://agentmods.dev/skills/ololand-ai/ololand-plugins/cmd-verify"><img src="https://agentmods.dev/badge/skills/ololand-ai/ololand-plugins/cmd-verify.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 | $0.00165 | $0.01647 |
| Opus 5 | $0.00082 | $0.00823 |
| Sonnet 5 | $0.00033 | $0.00329 |
| Haiku 4.5 | $0.00016 | $0.00165 |
Grade A, and why
ololand-forensic-qoe-verify 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 3d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex wrapper for /verify
Follow the OloLand command instructions below when the user asks for /verify or the equivalent workflow in Codex.
/verify (deal-scoped, corpus-based)
Runs OloLand's verification layer over an artifact you drafted anywhere — including in Claude Cowork or another tool — checked against an OloLand deal's ingested data room. For each figure it retrieves the supporting evidence from the corpus itself, so it catches numbers the author cited to the wrong source, or that the data room contradicts. Get back a per-figure verdict + a content-hashed provenance pack you can defend at IC.
It requires a deal with an ingested corpus. If you don't have one, this command walks you through creating it (create_deal + upload your documents) — that is the path from a Cowork draft to a verifiable OloLand deal.
Usage
/verify
Then provide the artifact and the deal to verify it against (see Inputs).
Inputs
Ask the user for these if missing:
- artifact_text (required) — the drafted memo / analysis / answer to verify. Accept any of: text pasted inline, a path to a local file (read it with your file tool and pass the contents), or the body of something the user generated elsewhere (e.g. a Cowork IC memo).
- deal_id (optional, required for verification) — the OloLand deal whose ingested data room backs the verification. If the user has no deal, do NOT block or repeatedly ask for one — proceed to the funnel (see Execution step 1) so they get the
create_dealpath.
Optional:
- rubric — override the grader rubric (defaults to the institutional DD rubric).
- mode (default
strict) —strictfails closed: if a provider call (grader / NLI) fails or times out, the affected figures come backUNVERIFIED, never a silent pass.advisorylets such cases pass through.
Execution
- No deal yet? If the user has no
deal_id, callmcp__ololand__grade_external_artifactwith just theartifact_text— it returnsstatus: "needs_deal". Relay its guidance: create a deal and upload the data room withmcp__ololand__create_deal, then re-run/verifywith the returneddeal_id. (This is the intended onboarding path — do not fall back to pasting evidence.) - Verify. Call
mcp__ololand__grade_external_artifactwithartifact_text,deal_id,mode(andrubricif supplied). - Handle the status field:
ok— render the verdict (see Output).needs_corpus— the deal exists but has no ingested documents. Tell the user to upload the data room (ingest), then re-run.search_error— a retryable corpus-search failure (not a missing corpus); tell the user to retry.
- Do not re-compute or second-guess the per-figure statuses — they come from the deterministic engines, the NLI check, and the independent grader.
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.
- 3d ago First seen · 93 lines · 165 tokens per session scan A 4edfa3797f74
ololand-forensic-qoe-verify is a skill published in the GitHub repository ololand-ai/ololand-plugins (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 165 tokens to every session and 1,647 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
excel-author
Build auditable financial workbooks headless via openpyxl.
lbo-model
This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transactions, deal materials, or investment committee presentations. The skill fills in formulas, validates calculations, and ensures professional formatting standards that adapt to any template structure.
pitch-deck
Populates investment banking pitch deck templates with data from source files. Use when: user provides a PowerPoint template to fill in, user has source data (Excel/CSV) to populate into slides, user mentions populating or filling a pitch deck template, or user needs to transfer data into existing slide layouts. Not…
audit-xls
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…