verify

verify is a command for coding agents from ab604/claude-code-r-skills. It costs 24 tokens per session (637 once invoked), scanned A, original, MIT.

A pre-commit verification command for R packages. It checks that the package builds, follows style rules, passes lint checks and tests, reaches required test coverage, and has no serious review findings.

In plain words
What is it for?
Use it after a feature or fix, before commits, and before pull requests to find build errors, style problems, lint issues, weak test coverage, or high-severity code-review findings.
Why use it?
It gathers the checks needed before committing or opening a pull request and gives a READY or NOT READY result.

Command

Part of the r-skills plugin — 8 skills, 4 commands, 3 agents, 4 hooks shipped together

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/ab604/claude-code-r-skills/verify
Clone the repo
git clone --depth 1 https://github.com/ab604/claude-code-r-skills

Or install r-skills, the plugin that ships this one along with the rest of its 8 skills, 4 commands, 3 agents, 4 hooks.

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/ab604/claude-code-r-skills/verify.svg)](https://agentmods.dev/commands/ab604/claude-code-r-skills/verify)
Your own site
<a href="https://agentmods.dev/commands/ab604/claude-code-r-skills/verify"><img src="https://agentmods.dev/badge/commands/ab604/claude-code-r-skills/verify.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 637 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 $0.00637
Opus 5 $0.00012 $0.00318
Sonnet 5 $0.00005 $0.00127
Haiku 4.5 $0.00002 $0.00064

Measured 4d ago against content hash ff567c0e84c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

commands/verify.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verify - R Verification Loop

Run all quality gates before committing code. Produces a READY or NOT READY verdict.

When to Use

  • Before every commit
  • After implementing a feature or fix
  • Before opening a pull request
  • Any time you want a full quality check

Verification Phases

Run each phase in order. A failure in any phase blocks the verdict.

Phase 1: Build Check

devtools::check(quiet = TRUE)

Pass criteria: 0 errors, 0 warnings, 0 notes (or only expected notes).

Phase 2: Style Check

styler::style_pkg()

Auto-fixes style. Re-check for any manual fixes needed.

Phase 3: Lint Check

lintr::lint_package()

Pass criteria: 0 lints. Fix all flagged issues before proceeding.

Phase 4: Test Coverage

covr::package_coverage()

Pass criteria: ≥80% overall coverage. Critical paths (validation, stats) require 100%.

Phase 5: Code Review

Invoke the code-reviewer agent to check uncommitted changes:

/code-review

Pass criteria: No CRITICAL or HIGH issues.

Phase 6: Diff Review

git diff --stat HEAD
git diff HEAD

Manually confirm:

  • No unintended files changed
  • No debug code or print()/cat() left in
  • No hardcoded paths or credentials
  • Commit message ready

Verdict Format

## Verification Report

| Phase          | Status | Notes                          |
|----------------|--------|--------------------------------|
| Build check    | ✅ PASS | 0 errors, 0 warnings           |
| Style check    | ✅ PASS | Auto-fixed 3 files             |
| Lint check     | ✅ PASS | 0 lints                        |
| Test coverage  | ✅ PASS | 87% overall                    |
| Code review    | ✅ PASS | No CRITICAL/HIGH issues        |
| Diff review    | ✅ PASS | Changes look correct           |

## Verdict: ✅ READY TO COMMIT

Next step: commit with a descriptive message.

Or if issues found:

## Verdict: ❌ NOT READY

**Blocking issues:**
1. [Phase] - [specific issue]
2. [Phase] - [specific issue]

Fix all blocking issues and re-run /verify.

Read the full file on GitHub · 121 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. 4d ago First seen · 121 lines · 24 tokens per session scan A ff567c0e84c0

Subscribe to this mod's changes

verify is a command published in the GitHub repository ab604/claude-code-r-skills (197 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 637 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 2026-08-30.