explain-exception

explain-exception is a command for coding agents from ethan-haas/docverify-mcp. It costs 24 tokens per session (312 once invoked), scanned A, original, MIT.

A document-checking explanation tool for one failed tie-out, meaning a comparison between figures that should agree.

In plain words
What is it for?
Use it to investigate one failed arithmetic check in a document, including its computed value, reported value, difference, labels, and source pages.
Why use it?
It shows exactly which numbers disagree, where they came from, and whether the difference is larger than the allowed tolerance.

Command

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.

agentmods
npx agentmods add commands/ethan-haas/docverify-mcp/explain-exception
Clone the repo
git clone --depth 1 https://github.com/ethan-haas/docverify-mcp

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 explain-exception

README.md
[![agentmods](https://agentmods.dev/badge/commands/ethan-haas/docverify-mcp/explain-exception.svg)](https://agentmods.dev/commands/ethan-haas/docverify-mcp/explain-exception)
Your own site
<a href="https://agentmods.dev/commands/ethan-haas/docverify-mcp/explain-exception"><img src="https://agentmods.dev/badge/commands/ethan-haas/docverify-mcp/explain-exception.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.00312
Opus 5 $0.00012 $0.00156
Sonnet 5 $0.00005 $0.00062
Haiku 4.5 $0.00002 $0.00031

Measured 3d ago against content hash 58ba4b91f5af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explain-exception 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.

claude-pack/commands/explain-exception.md · 29 lines

What it actually says

Call explain_exception from the docverify MCP server with check_id: $ARGUMENTS

It defaults to the document most recently extracted or verified in this session. If no document has been loaded yet, ask for the path instead of guessing.

Report:

  • what the check asserts, in one sentence (description)
  • the computed value and the expression it came from, with its source page(s)
  • the reported value, its label and column, and its source page
  • the difference, and whether it exceeds the tolerance

Then say what a difference of that size usually means. A round difference that also shows up in another failing check with the same delta points at one wrong figure feeding both. A difference of exactly the tolerance or less is not a failure at all.

If the response has disclosed: false and no explanation key, the check PASSED inside a document that failed verification, and its numbers are withheld on purpose. Report that, name the ids in withheld.explain_these_instead, and do not try another tool to get at the figure.

Do not propose a corrected figure. This tool reports a disagreement between a document and its own arithmetic; deciding which side is wrong needs the source document.

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 · 29 lines · 24 tokens per session scan A 58ba4b91f5af

Subscribe to this mod's changes

explain-exception is a command published in the GitHub repository ethan-haas/docverify-mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 24 tokens to every session and 312 once invoked, about $0.0001 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.