ololand-forensic-qoe-verify

ololand-forensic-qoe-verify is a skill for Claude Code from ololand-ai/ololand-plugins. It costs 165 tokens per session (1,647 once invoked), scanned A, original, Apache-2.0.

A verification workflow for checking every financial figure in a draft against documents stored in an OloLand deal's data room.

In plain words
What is it for?
Use it to check an investment memo, analysis, or answer before presenting it to an investment committee.
Why use it?
It catches unsupported numbers, incorrect sources, and figures that conflict with the deal documents.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the ololand-forensic-qoe plugin — 10 skills, 8 commands shipped together

Good fit Use it to check an investment memo, analysis, or answer before presenting it to an investment committee.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ololand-ai/ololand-plugins/cmd-verify
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.

Any agent
npx skills add ololand-ai/ololand-plugins --skill cmd-verify
Clone the repo
git clone --depth 1 https://github.com/ololand-ai/ololand-plugins

Made for: Claude Code.

Or install ololand-forensic-qoe, the plugin that ships this one along with the rest of its 10 skills, 8 commands.

Wrote 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.

agentmods badge for ololand-forensic-qoe-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/ololand-ai/ololand-plugins/cmd-verify.svg)](https://agentmods.dev/skills/ololand-ai/ololand-plugins/cmd-verify)
Your own site
<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>
Per session 165 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,647 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00165 $0.01647
Opus 5 $0.00082 $0.00823
Sonnet 5 $0.00033 $0.00329
Haiku 4.5 $0.00016 $0.00165

Measured 3d ago against content hash 4edfa3797f74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

plugins/ololand-forensic-qoe/skills/cmd-verify/SKILL.md · 93 lines

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:

  1. 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).
  2. 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_deal path.

Optional:

  • rubric — override the grader rubric (defaults to the institutional DD rubric).
  • mode (default strict) — strict fails closed: if a provider call (grader / NLI) fails or times out, the affected figures come back UNVERIFIED, never a silent pass. advisory lets such cases pass through.

Execution

  1. No deal yet? If the user has no deal_id, call mcp__ololand__grade_external_artifact with just the artifact_text — it returns status: "needs_deal". Relay its guidance: create a deal and upload the data room with mcp__ololand__create_deal, then re-run /verify with the returned deal_id. (This is the intended onboarding path — do not fall back to pasting evidence.)
  2. Verify. Call mcp__ololand__grade_external_artifact with artifact_text, deal_id, mode (and rubric if supplied).
  3. 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.
  4. Do not re-compute or second-guess the per-figure statuses — they come from the deterministic engines, the NLI check, and the independent grader.

Read the full file on GitHub · 93 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. 3d ago First seen · 93 lines · 165 tokens per session scan A 4edfa3797f74

Subscribe to this mod's changes

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.