kdd-test-coverage-scan

kdd-test-coverage-scan is a skill for Claude Code, Codex from MauricioPerera/KDD. It costs 167 tokens per session (1,899 once invoked), scanned A, original, MIT.

A KDD-guided review that finds important software paths and failure cases not covered by tests, and records them in a structured findings.json file. Test coverage means how much of a program’s behaviour is exercised by automated tests.

In plain words
What is it for?
Use it to compare critical paths with coverage reports and incident history, assess the impact of each missing test, and produce a KDD-compatible coverage-gap scan.
Why use it?
It identifies risks that ordinary pass-or-fail test checks do not show, such as untested critical paths, error handling, or past regression scenarios, and prepares results for a validation gate.

Skill for Claude CodeCodex

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/validate_test_coverage_findings.py <scan_dir>.

Good fit Use it to compare critical paths with coverage reports and incident history, assess the impact of each missing test, and produce a KDD-compatible coverage-gap scan.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/MauricioPerera/KDD
agentmods
npx agentmods add skills/mauricioperera/kdd/kdd-test-coverage-scan

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 kdd-test-coverage-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-test-coverage-scan/github.svg)](https://agentmods.dev/skills/mauricioperera/kdd/kdd-test-coverage-scan)
Your own site
<a href="https://agentmods.dev/skills/mauricioperera/kdd/kdd-test-coverage-scan"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-test-coverage-scan/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 kdd-test-coverage-scan

Your own site · 80×15
<a href="https://agentmods.dev/skills/mauricioperera/kdd/kdd-test-coverage-scan"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-test-coverage-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,899 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 $0.00167 $0.01899
Opus 5 $0.00084 $0.00949
Sonnet 5 $0.00033 $0.00380
Haiku 4.5 $0.00017 $0.00190

Measured 12d ago against content hash ace382e93073, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

kdd-test-coverage-scan 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 12d 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/kdd-test-coverage-scan/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Coverage Scan (Capa 3 de KDD -- gaps de cobertura)

Produce hallazgos de gaps de cobertura de tests en el formato de contrato que audita la Capa 3 de KDD. Esta skill NO es el gate -- es la parte creativa/no determinista (identificar rutas criticas, cruzarlas con reportes de cobertura y con el historial de incidentes, juzgar el impacto de cada gap) que el gate despues valida. Distincion central: el agente decide QUE es un gap de cobertura; el gate solo audita que el artefacto sellado cumpla forma y politica de calidad de datos.

Lee esto primero: la frontera con CCDD

Antes de usar esta skill, confirma que lo que buscas NO ya lo cubre CCDD. CCDD (Nivel 1 obligatorio, sin activar nada) exige que todo task contract en knowledge/contracts/ tenga:

  • un oraculo de tests congelado (tests_sha256 en el frontmatter, gateado por validate_contracts.py);
  • su test_command en verde (gateado por validate_test_commands.py).

Si tu pregunta es "¿esta funcion que se implemento via un task contract tiene tests que pasan?", esa respuesta ya existe -- no necesitas esta skill ni el dominio que gobierna.

Esta skill sirve para lo que CCDD deliberadamente NO cubre:

  1. Codigo que nunca paso por un task contract. La mayoria de un proyecto real, sobre todo si KDD se adopto sobre un codebase preexistente.
  2. Gaps de TIPO de cobertura, no de presencia. Un test_command en verde certifica que ESOS tests pasan, no que cubran el caso de error, la condicion de carrera, o el camino que revelo un incidente real.
  3. Test de regresion faltante tras un bug real ya corregido.

Ver la seccion completa de frontera en knowledge/data_models/test_coverage_findings.md.

Cuando usarla

El usuario pide auditar si las rutas criticas de un sistema (dentro o fuera de contratos CCDD) tienen el tipo de cobertura de tests que hace falta, y quiere el resultado gobernado por KDD (versionable, gateado en CI, con politica declarativa), no un reporte suelto en prosa.

Read the full file on GitHub · 163 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. 12d ago First seen · 163 lines · 167 tokens per session scan A ace382e93073

Subscribe to this mod's changes

kdd-test-coverage-scan is a skill published in the GitHub repository MauricioPerera/KDD (8 stars, last pushed 3d ago), licensed MIT. It adds 167 tokens to every session and 1,899 once invoked, about $0.0008 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