commerce-agent-bench: Skill for Claude Code

.agents/skills/code-change-verification/SKILL.md

code-change-verification is a skill for Claude Code, Codex from harukiseller-droid/commerce-agent-bench. It costs 21 tokens per session (299 once invoked), scanned A, original, MIT.

A final verification checklist for source-code changes before merging or releasing them.

In plain words
What is it for?
Use it to inspect diffs, run project tests and deterministic evaluations, check the changed scope, and report PASS, PASS WITH WARNINGS, or FAIL with exact results.
Why use it?
It checks whether the change matches its requested behavior and exposes failed tests, unrelated files, dependency issues, secrets, generated-file problems, and unverified risks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is harukiseller-droid/commerce-agent-bench's own configuration. It tells Claude Code and Codex how to work on commerce-agent-bench 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 commerce-agent-bench configures →

Reuse

Borrowing it

Nothing to install: this file belongs to harukiseller-droid/commerce-agent-bench. 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/harukiseller-droid/commerce-agent-bench/main/.agents/skills/code-change-verification/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/harukiseller-droid/commerce-agent-bench

Made for: Claude Code, Codex.

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 code-change-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/harukiseller-droid/commerce-agent-bench/code-change-verification.svg)](https://agentmods.dev/skills/harukiseller-droid/commerce-agent-bench/code-change-verification)
Your own site
<a href="https://agentmods.dev/skills/harukiseller-droid/commerce-agent-bench/code-change-verification"><img src="https://agentmods.dev/badge/skills/harukiseller-droid/commerce-agent-bench/code-change-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 299 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00299
Opus 5 $0.00010 $0.00150
Sonnet 5 $0.00004 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 8d ago against content hash ec93cebe5da5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-change-verification 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 8d 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.

.agents/skills/code-change-verification/SKILL.md · 53 lines

What it actually says

Code Change Verification

Purpose

Provide a repeatable final gate for source changes before merge or release.

When to use

Use for every source-code modification and before completing a substantial pull request.

Inputs

  • the working-tree diff and base revision;
  • project test and eval commands;
  • dependency, generated-artifact, and runtime context.

Required checks

  • Inspect the full diff and changed file list.
  • Run project tests.
  • Run deterministic evals.
  • Check changed behavior against the requested contract.
  • Check for unexpected files.
  • Check dependency changes.
  • Check generated artifacts and secrets.
  • Summarize remaining risk and unverified behavior.

Output contract

Return exactly one top-level status:

PASS
PASS WITH WARNINGS
FAIL

Include commands, exact results, changed scope, warnings, and remaining risk below the status.

Failure conditions

  • FAIL if a required test/eval fails, the diff contains an unrelated change, or a secret is detected.
  • PASS WITH WARNINGS when deterministic checks pass but required runtime or external-platform evidence is unavailable.
  • Never claim a test ran when it did not run.

Verification

Run the final commands from the repository contract, review git diff --check, inspect status, and repeat any invalidated gate after the last change.

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. 8d ago First seen · 53 lines · 21 tokens per session scan A ec93cebe5da5

Subscribe to this mod's changes

code-change-verification is a skill published in the GitHub repository harukiseller-droid/commerce-agent-bench (102 stars, last pushed 26d ago), licensed MIT. It adds 21 tokens to every session and 299 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.

Related

Other skills, from other repositories