verify

verify is a skill for Claude Code, Codex from melodic-software/claude-code-plugins. It costs 173 tokens per session (1,286 once invoked), scanned A, original, MIT.

An independent check of a reported performance result. It repeats the measurement from a fresh context and checks whether the change preserved existing behavior.

In plain words
What is it for?
Use it to verify optimization claims, compare before-and-after behavior, and decide whether a performance target was actually met.
Why use it?
It helps catch incorrect numbers and defects that normal tests or green continuous integration checks can miss. It also avoids treating a near miss as a success.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the performance plugin — 4 skills 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 skills/melodic-software/claude-code-plugins/verify
Any agent
npx skills add melodic-software/claude-code-plugins --skill verify
Clone the repo
git clone --depth 1 https://github.com/melodic-software/claude-code-plugins

Made for: Claude Code, Codex.

Or install performance, the plugin that ships this one along with the rest of its 4 skills.

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/skills/melodic-software/claude-code-plugins/verify.svg)](https://agentmods.dev/skills/melodic-software/claude-code-plugins/verify)
Your own site
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/verify"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,286 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 $0.00173 $0.01286
Opus 5 $0.00086 $0.00643
Sonnet 5 $0.00035 $0.00257
Haiku 4.5 $0.00017 $0.00129

Measured yesterday against content hash 54f20272e24c, 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 yesterday.

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/performance/skills/verify/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Answers "is this result real, and what does it actually say?"

In the source run behind this plugin, this phase caught two blocking correctness defects that the implementer, the implementer's own 143-test suite, and a full green CI run had all missed. That is why it is a separate phase from measurement and not a step inside it.

Read ${CLAUDE_PLUGIN_ROOT}/reference/harness-integrity.md first.

1. Fresh context, and adversarial by construction

Dispatch a verifier that does not inherit the implementer's numbers. Give it the trees and the claim; withhold the reasoning that produced the figures. A verifier shown the expected answer verifies the answer, not the work.

The brief should say, in substance: distrust the reported numbers, re-derive them yourself, and report what you actually observe including the ways you could not reproduce it.

Two independent verifiers found different defects in the source run. One is the floor, not the target.

2. Prove behavior did not change, with a differential

A passing test suite is not a behavior proof. It proves nothing asserted broke. It does not prove behavior is unchanged, because it only checks what someone thought to assert.

Run a differential: the pre-change and post-change subject over a harvested corpus of real inputs, requiring byte-identical output.

Cover every MODE the subject runs in. The source run's differential covered one of two modes and missed a real deny -> ask downgrade in the other. Enumerate the modes first and record which the differential actually exercised; an unexercised mode is an unverified mode, and it is reported as such rather than assumed fine.

3. Check the harness before believing the result

Every gate in the harness-integrity checklist. In particular, for any discrimination check involved, confirm it asserts that its two arms differ, not merely that each produced its expected string. Four of five harnesses in the source run failed by exiting identically in both arms and reporting a confident verdict.

Read the full file on GitHub · 99 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 99 lines · 173 tokens per session scan A 54f20272e24c

Subscribe to this mod's changes

verify is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 173 tokens to every session and 1,286 once invoked, about $0.0009 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