copilot-setting: Skill for Claude Code

.github/skills/verify/SKILL.md

verify is a skill for Claude Code, Codex from zexion7873/copilot-setting. It costs 136 tokens per session (1,182 once invoked), scanned A, original, MIT.

A verification workflow for checking whether software meets its acceptance criteria. Acceptance criteria are the conditions a feature must satisfy before it is considered done.

In plain words
What is it for?
Use it to derive test cases, run the correct Java 8, Spring 3.2, JUnit 4, and Mockito checks, and gate the result with pass or fail.
Why use it?
It turns requirements into runnable checks and prevents the verification step from simply approving whatever the code already does.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is zexion7873/copilot-setting's own configuration. It tells Claude Code and Codex how to work on copilot-setting 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 copilot-setting configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zexion7873/copilot-setting. 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/zexion7873/copilot-setting/main/.github/skills/verify/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zexion7873/copilot-setting

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 verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/zexion7873/copilot-setting/verify/github.svg)](https://agentmods.dev/skills/zexion7873/copilot-setting/verify)
Your own site
<a href="https://agentmods.dev/skills/zexion7873/copilot-setting/verify"><img src="https://agentmods.dev/badge/skills/zexion7873/copilot-setting/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/skills/zexion7873/copilot-setting/verify"><img src="https://agentmods.dev/badge/skills/zexion7873/copilot-setting/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,182 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 $0.00136 $0.01182
Opus 5.5 $0.00054 $0.00473
Sonnet 5.5 $0.00027 $0.00236
Haiku 4.5 $0.00014 $0.00118

Measured 1mo ago against content hash 375bf7aa87d1, 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 1mo 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.

.github/skills/verify/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify — Workflow

Close-the-loop verification: derive what must be true, bind each to a runnable check, execute, and gate. The gate is a separate pass from authoring — derive the expected behaviour from the requirement, never from the code under test, or the gate just rubber-stamps whatever the code does. Framework rules for any run command or test code referenced here: instructions/testing.instructions.md.

Phase 0 — Load canonical rules

MANDATORY pre-load gate — do NOT derive or run checks until you have opened the instruction files for the layers under verification. Your training data defaults to modern Java/Spring; these files are the version lock for Java 8 / Spring 3.2 / Hibernate 4.2. Open them first, every time. Read-back receipt: NAME each file you opened and QUOTE its single most load-bearing rule for this change — a generic restatement you could have written from memory means you skipped the file.

Open instructions/testing.instructions.md — JUnit 4 / Mockito / Spring Test 3.2, and every run command or test you write must match this stack, not JUnit 5 / Spring Boot Test — plus the layer instruction(s) for the feature under verification (e.g. instructions/sql.instructions.md, instructions/security.instructions.md), whose version-lock and hard-boundary rules are the negative cases Phase 1 must cover.

Phase 1 — Derive the checks

Work from the requirement / plan.md acceptance criteria (AC-NNN), NOT from the code under test — independent derivation is the whole point of a gate.

  • Boundaries — input (min, max, empty, null, overflow), state (initial, in-progress, done, error), integration (external call, DB, file I/O)
  • Categories — tag each check: Happy path, Boundary, Error / Exception, Security, Concurrency, Performance
  • Coverage — every AC maps to ≥1 check; every public method has ≥1 happy + ≥1 error; boundary values for all numeric/string inputs; SQL paths checked for injection and empty results

Phase 2 — Bind each check to a runnable command

Read the full file on GitHub · 79 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. 1mo ago Changed · -3 lines 375bf7aa87d1
  2. 2mo ago First seen · 82 lines · 136 tokens per session scan A aeb0e624cddd

Subscribe to this mod's changes

verify is a skill published in the GitHub repository zexion7873/copilot-setting (1 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 1,182 once invoked, about $0.0005 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 2026-08-31.

Related

verify compared with skills from other repositories

verify next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
verifyzexion7873/copilot-settingSkill11mo agoMITA136Claude Code, Codex
jira-cliCode-and-Sorts/awesome-copilot-agentsSkill5936mo agoCC0-1.0A60Claude Code, Codex
azure-pricesCode-and-Sorts/awesome-copilot-agentsSkill5936mo agoCC0-1.0A90Claude Code, Codex
calculatorCode-and-Sorts/awesome-copilot-agentsSkill5936mo agoCC0-1.0A50Claude Code, Codex
az-cliCode-and-Sorts/awesome-copilot-agentsSkill5936mo agoCC0-1.0A79Claude Code, Codex
plan-tasksavedpixel/ai-agent-rules-generatorSkill86mo agoMITA45Claude Code, Codex
commitsavedpixel/ai-agent-rules-generatorSkill86mo agoMITA40Claude Code, Codex