verify

A quality-check tool that runs configured checks on code and produces a structured report showing which checks passed or failed.

In plain words
What is it for?
Use it before deployment to run local checks, automated tests, integration checks, and smoke checks, which are quick tests that confirm a deployed service is responding.
Why use it?
It gives a clear release checkpoint instead of leaving quality checks scattered across manual commands. It can cover formatting, types, tests, specification compliance, integration, and post-release health.

Skill for Claude CodeCodex

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/mountainunicorn/add/verify
Any agent
npx skills add MountainUnicorn/add --skill verify
Clone the repo
git clone --depth 1 https://github.com/MountainUnicorn/add

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,313 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 $0.00021 $0.04313
Opus 5 $0.00010 $0.02157
Sonnet 5 $0.00004 $0.00863
Haiku 4.5 $0.00002 $0.00431

Measured 2d ago against content hash 6f6ce5f9e290, 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 2d 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.

core/skills/verify/SKILL.md · 433 lines

How it starts

The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADD Verify Skill v{{VERSION}}

Execute quality gates to verify code meets production standards. This skill runs automated checks and produces a structured pass/fail report.

Overview

The Verify skill is the final checkpoint before deployment. It runs a sequence of quality gates determined by context and provides clear go/no-go status for each gate. Output is a structured report with pass/fail status and next steps.

The five-gate system ensures code quality at every stage:

  1. Gate 1 (Local): Lint & code formatting
  2. Gate 2 (Local): Type checking (if applicable)
  3. Gate 3 (CI): Unit tests & coverage
  4. Gate 4 (Deploy): Spec compliance & integration tests
  5. Gate 5 (Smoke): Post-deploy health checks

All gate results are reported using the shared formats in ${CLAUDE_PLUGIN_ROOT}/templates/verify-report.md — one per-gate format, the maturity-scaled sections, and the overall report.

Pre-Flight Checks

  1. Read .add/config.json

    • Load gate definitions: which commands to run, thresholds
    • Load ci.gates array (ordered list of gates)
    • Load test.minCoverage threshold (default 80%)
    • Load code.lint configuration
    • Load code.types configuration
    • Load environment tier settings
    • A configuration example lives in ${CLAUDE_PLUGIN_ROOT}/templates/verify-report.md
  2. Count active rules for maturity level

    • Read maturity level from .add/config.json (default: alpha)
    • Scan all files in rules/ directory
    • For each rule file, read the YAML frontmatter maturity: field
    • Count rules where the maturity field is at or below the current level
      • Maturity hierarchy: poc < alpha < beta < ga
      • A rule with maturity: poc is active at all levels
      • A rule with maturity: beta is active at beta and ga only
    • Include in report header: "{N} rules active at {maturity} level"

Read the full file on GitHub · 433 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. 2d ago First seen · 433 lines · 21 tokens per session scan A 6f6ce5f9e290

Subscribe to this mod's changes

verify is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 4,313 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.