verify-report

verify-report is a command for Claude Code from ethan-haas/docverify-mcp. It costs 21 tokens per session (316 once invoked), scanned A, original, MIT.

A command for extracting and checking a cash-basis combined financial statement. It reports figures only after the statement passes all tie-out checks.

In plain words
What is it for?
Use it to verify a report PDF or check numbers in a pre-extracted JSON file. It can show the verification result, check count, entity, fiscal year end, and verified line items.
Why use it?
It prevents numbers from an internally inconsistent document being presented as valid. For a failed document, it lists the failed arithmetic and reports that no figures are available.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to verify a report PDF or check numbers in a…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ethan-haas/docverify-mcp/verify-report
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.

Clone the repo
git clone --depth 1 https://github.com/ethan-haas/docverify-mcp

Made for: Claude Code.

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 verify-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/ethan-haas/docverify-mcp/verify-report.svg)](https://agentmods.dev/commands/ethan-haas/docverify-mcp/verify-report)
Your own site
<a href="https://agentmods.dev/commands/ethan-haas/docverify-mcp/verify-report"><img src="https://agentmods.dev/badge/commands/ethan-haas/docverify-mcp/verify-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 316 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 $0.00021 $0.00316
Opus 5 $0.00010 $0.00158
Sonnet 5 $0.00004 $0.00063
Haiku 4.5 $0.00002 $0.00032

Measured 6d ago against content hash cb25d8da1cbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verify-report 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 6d 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/verify-report.md · 26 lines

What it actually says

Run extract_statement from the docverify MCP server on: $ARGUMENTS

Then report, in this order:

  1. Verdict. verified: true or verified: false, and the check count from verification.checks_run.
  2. If verified — the entity, the fiscal year end, and a table of the line items with one column per fund type. End with "all N checks passed".
  3. If refused — do NOT report any figure as a value of anything. List each id in refusal.failed_check_ids with its arithmetic from failed_checks, then say that no figures are available for this document because it does not reconcile.

If the caller asks to see the working, follow up with verify_totals on the same path and show the arithmetic per check. On a refused document only the FAILING checks carry arithmetic; the rest come back disclosed: false, and that is the contract working, not a gap to fill in.

extract_statement takes the report PDF. If the caller offers a pre-extracted .json, use verify_totals instead and say what it does and does not establish: it checks that THEIR numbers are internally consistent, it does not certify them as the document's figures.

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. 6d ago First seen · 26 lines · 21 tokens per session scan A cb25d8da1cbb

Subscribe to this mod's changes

verify-report is a command published in the GitHub repository ethan-haas/docverify-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 21 tokens to every session and 316 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.