rdocx: Command for Claude Code

.claude/commands/verify.md

verify is a command for Claude Code from tensorbee/rdocx. It costs 19 tokens per session (3,207 once invoked), scanned A, original, MIT.

A verification command that runs formatting, lint checks, tests, repository-policy checks, and other project-specific checks at different scopes.

In plain words
What is it for?
Use it for quick local checks, feature-completion checks, or full integrated checks before closing a sprint.
Why use it?
It provides defined checks for a changed area, a feature, or the whole workspace instead of treating every change as needing the same amount of verification.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Codex.

This is tensorbee/rdocx's own configuration. It tells Claude Code how to work on rdocx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rdocx configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tensorbee/rdocx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tensorbee/rdocx/main/.claude/commands/verify.md
Clone the repo
git clone --depth 1 https://github.com/tensorbee/rdocx

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/tensorbee/rdocx/verify/github.svg)](https://agentmods.dev/commands/tensorbee/rdocx/verify)
Your own site
<a href="https://agentmods.dev/commands/tensorbee/rdocx/verify"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/verify/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 verify

Your own site · 80×15
<a href="https://agentmods.dev/commands/tensorbee/rdocx/verify"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,207 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 $0.00019 $0.03207
Opus 5.5 $0.00008 $0.01283
Sonnet 5.5 $0.00004 $0.00641
Haiku 4.5 $0.00002 $0.00321

Measured 6d ago against content hash 6fc0cdcdcf0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 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/commands/verify.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verify [--fast | --scoped F-XXX | --full]

There are three verification scopes:

  • --fast runs formatting, changed-crate linting and the unique affected local regression tests. It does not run whole-crate or complete installed suites.
  • --scoped F-XXX is the feature-completion gate for local evidence. It binds the fast checks and the approved plan's named local RED/GREEN regressions to the claimed Base and actual source. Independent /microscope remains required.
  • --full is the final integrated sprint gate. It runs the workspace suites and the union of every approved plan's final oracle and risk checks once.

Whole-crate suites, ordinary complete installed suites, external oracle comparisons, native Office controls, hash/pixel corpora, whole-package typing and stub checks, WASM, documentation, publication dry runs and supply-chain checks belong to the final union. A small affected typing or compile check can be a local regression when the change needs it. Do not promote it to another whole-suite run. Keep distinct configurations and artifact identities separate.

The caller consumes an applicable successful observation instead of running it again. Record exact source, command/configuration, tools, inputs and results. A later failed attempt invalidates an older green result for the same check. After a source fix rerun affected checks, preserving earlier failures. Never call an unperformed final oracle a passed local gate. Record in-flight evidence and pending checks in the feature's existing .claude/scratch/<F-ID>-progress.md before handing over.

Acceptance applicability

Build, artifact and semantic outcome

Dependent batches stop after a failed prerequisite. Use set -e in a shell build/test batch or check the actual child status before the next stage. A failed extension build must not fall through to tests or timings on an older installed module. Preserve the failed attempt and authenticate the replacement artifact after a successful build.

Read the full file on GitHub · 250 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. 6d ago Changed · +70 lines 6fc0cdcdcf0e
  2. 11d ago Changed · +14 lines 8d04263525ed
  3. 26d ago First seen · 166 lines · 19 tokens per session scan A c1582f6e7a55

Subscribe to this mod's changes

verify is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 3,207 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.