deep-test

deep-test is a skill for Claude Code, Codex from kunalsuri/ai-fication-kit. It costs 49 tokens per session (394 once invoked), scanned A, original, Apache-2.0.

A strict codebase verification workflow that runs smoke tests, checks documented claims and structural drift, scans for license headers, and detects unreplaced template placeholders.

In plain words
What is it for?
Use it after changes or when checking overall code health. Run it with the project's deep-test command after ensuring the required Node.js dependencies are installed.
Why use it?
It catches broken behavior, mismatches between code and documentation, missing project files, licensing omissions, and template variables accidentally left in released files.

Skill for Claude CodeCodex

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

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/kunalsuri/ai-fication-kit/deep-test
Any agent
npx skills add kunalsuri/ai-fication-kit --skill deep-test
Clone the repo
git clone --depth 1 https://github.com/kunalsuri/ai-fication-kit

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 deep-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/kunalsuri/ai-fication-kit/deep-test.svg)](https://agentmods.dev/skills/kunalsuri/ai-fication-kit/deep-test)
Your own site
<a href="https://agentmods.dev/skills/kunalsuri/ai-fication-kit/deep-test"><img src="https://agentmods.dev/badge/skills/kunalsuri/ai-fication-kit/deep-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 394 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 5.1 $0.00049 $0.00394
Opus 5 $0.00024 $0.00197
Sonnet 5 $0.00010 $0.00079
Haiku 4.5 $0.00005 $0.00039

Measured 5d ago against content hash 542a14df34b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deep-test 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 5d 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/deep-test/SKILL.md · 35 lines

What it actually says

Deep test the codebase

This skill performs a thorough and strict verification of the codebase to guarantee that changes are clean, functional, matches Conventions, contains proper license headers, and does not leak template placeholders.

1. Prerequisites

Ensure you have the required runtimes and node dependencies installed:

  • Node.js (>= 18)
  • Run npm install before running tests if dependencies are updated.

2. Run the Deep Test

Run the automated deep test script via npm:

npm run deep-test

3. Verify Output

The script automatically tests:

  • Smoke tests: node test/run-tests.mjs
  • Document Claim verification: node install.mjs verify . --strict
  • Structural Drift verification: node install.mjs drift . --strict --git (falls back to --strict without --git if git is not available)
  • License Headers check: Scans files for copyright markers.
  • Unresolved template placeholders: Confirms template variables are not leaked outside of templates/.

If any of the checks fail, print the failures verbatim and address them before declaring success.

4. Manual Verification / Check Checklist

  • If you introduced new files, check that their paths are added to the appropriate catalog or map (e.g., ai/guide/MODULE_MAP.md) and labeled as [inferred].
  • Verify the change adheres to all project rules in AGENTS.md and conventions in ai/guide/CONVENTIONS.md.
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. 5d ago First seen · 35 lines · 49 tokens per session scan A 542a14df34b1

Subscribe to this mod's changes

deep-test is a skill published in the GitHub repository kunalsuri/ai-fication-kit (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 394 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

close-my-loops

Build and maintain a personal work profile and open-loop tracker for the user's own job — a markdown file covering their org, key contacts, communication style, active initiatives, and open loops synthesized from their own email/Slack; a Cowork Project setup so that file is actually read every session; and a scheduled…

insideout-ai/make-it-work · 193 tokens

fonte

Decide o que fazer com qualquer coisa que chega (e-mail, PDF, planilha, pasta, drive, print, áudio, export de CRM) — recomenda o nível de refino certo, executa até ele e PARA. Use quando a pessoa pergunta "o que eu faço com isso?", "trato ou guardo o bruto?", aponta uma fonte nova, ou pede "ingere o que tá em…

gabrielzucco/cerebro-inevita · 89 tokens

reindex

O ritual semanal (30-45 min) que mantém o cérebro afiado — triagem da bandeja, faxina dos fios, resumo da semana a partir das dailies. Use quando a pessoa diz "bora fazer o reindex", "fechar a semana", ou uma vez por semana em dia fixo.

gabrielzucco/cerebro-inevita · 69 tokens

call

Transforma uma call ou reunião real em decisões, ações, dores, números e memória citável, com aprovação e eval. Use quando a pessoa cola uma transcrição, aponta um arquivo, diz “trata essa call” ou opera o sistema Calls em Decisões.

gabrielzucco/cerebro-inevita · 57 tokens

daily

O fechamento do dia em 5-10 minutos — captura o que aconteceu com a memória quente e destila em até 5 átomos. Use quando a pessoa diz "bora fazer a daily", "fechar o dia", ou no fim do expediente dela.

gabrielzucco/cerebro-inevita · 57 tokens

agent-self-scheduling

Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.

sickn33/agentic-awesome-skills · 24 tokens