forensic-qoe

forensic-qoe is a skill for Claude Code from ololand-ai/ololand-plugins. It costs 64 tokens per session (620 once invoked), scanned A, original, Apache-2.0.

A procedure for checking a company's earnings quality using financial tests such as Beneish, Benford, EBITDA, revenue, working capital, and journal-entry analysis.

In plain words
What is it for?
Use it before preparing an investment-committee analysis of a target company.
Why use it?
It reduces the risk of drawing investment conclusions from claims or prose without checking the underlying financial data.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it before preparing an investment-committee analysis of a target company.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ololand-ai/ololand-plugins/forensic-qoe
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 forensic-qoe
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 forensic-qoe

README.md
[![agentmods](https://agentmods.dev/badge/skills/ololand-ai/ololand-plugins/forensic-qoe/github.svg)](https://agentmods.dev/skills/ololand-ai/ololand-plugins/forensic-qoe)
Your own site
<a href="https://agentmods.dev/skills/ololand-ai/ololand-plugins/forensic-qoe"><img src="https://agentmods.dev/badge/skills/ololand-ai/ololand-plugins/forensic-qoe/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.

agentmods 80×15 button for forensic-qoe

Your own site · 80×15
<a href="https://agentmods.dev/skills/ololand-ai/ololand-plugins/forensic-qoe"><img src="https://agentmods.dev/badge/skills/ololand-ai/ololand-plugins/forensic-qoe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 620 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 $0.00064 $0.00620
Opus 5 $0.00032 $0.00310
Sonnet 5 $0.00013 $0.00124
Haiku 4.5 $0.00006 $0.00062

Measured 5d ago against content hash 55ce11129207, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

forensic-qoe 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.

plugins/ololand-forensic-qoe/skills/forensic-qoe/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forensic Quality of Earnings

Use deterministic OloLand tools for forensic checks. Do not infer forensic conclusions from prose alone — the verifier-stack premise is that every QoE conclusion comes from a tool with a documented methodology and inputs.

Minimum screen — always run before IC

Each of these is available as an MCP tool / /-command in this plugin:

Procedure When required Tool / command
Beneish M-Score Every target. Earnings-manipulation probability. /cmd-beneish
Benford distribution review Whenever transaction-level GL data is available. Flags fabricated entries. /cmd-benford
EBITDA bridge and adjustment quality Every target. Walks from reported EBITDA to QoE-adjusted EBITDA with explicit adjustment categories. /cmd-ebitda-bridge
Revenue quality deep dive Whenever invoice-level or revenue-by-customer detail is available. manual + tool stack
Working capital anomaly review Every target. DSO/DIO/DPO trends + seasonality. manual + tool stack
Journal entry testing Whenever transaction-level data is available. Tests journal entries against fraud patterns (round numbers, period-end clustering, manual entries from privileged users). /cmd-journal-test
Lapping detection Whenever AR aging and cash receipts can be reconciled. /cmd-lapping-check

When inputs are missing

State the limitation explicitly. Do not fabricate a conclusion from incomplete data:

  • "Benford's review requires transaction-level GL data. The data room contains only summary financials; this procedure was not run."
  • "Lapping detection requires AR aging matched with cash receipts. AR aging was provided; cash receipts were not. Procedure deferred."

A QoE that skips a procedure because the data is missing is not a QoE failure — but the IC memo must surface the gap as a diligence condition.

Output format

For each procedure that ran:

  • Result — Pass / Yellow / Red
  • Evidence basis — what data was used (file, period)
  • Methodology note — one sentence on what the procedure tests
  • Next-step recommendation if Yellow or Red — what to ask management or what additional data to request

Read the full file on GitHub · 46 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. 5d ago First seen · 46 lines · 64 tokens per session scan A 55ce11129207

Subscribe to this mod's changes

forensic-qoe is a skill published in the GitHub repository ololand-ai/ololand-plugins (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 64 tokens to every session and 620 once invoked, about $0.0003 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.

Related

Other skills, from other repositories