kdd-observability-scan

kdd-observability-scan is a skill for Claude Code, Codex from MauricioPerera/KDD. It costs 134 tokens per session (1,600 once invoked), scanned A, original, MIT.

A KDD-guided review that finds missing logging, alerts, tracing, or metrics on important software paths and records the results in findings.json. Observability means having enough signals to understand when a system fails and why.

In plain words
What is it for?
Use it to inspect critical paths, error handling, alerts, logs, traces, and metrics, and produce a structured observability-gap scan governed by KDD.
Why use it?
It exposes failures that may otherwise go unnoticed or be difficult to investigate, then prepares the findings for a repeatable validation check.

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_observability_findings.py <scan_dir>.

Good fit Use it to inspect critical paths, error handling, alerts, logs, traces, and metrics, and produce a structured observability-gap scan governed by KDD.

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-observability-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-observability-scan

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/mauricioperera/kdd/kdd-observability-scan"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-observability-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,600 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 $0.00134 $0.01600
Opus 5 $0.00067 $0.00800
Sonnet 5 $0.00027 $0.00320
Haiku 4.5 $0.00013 $0.00160

Measured 11d ago against content hash d6b913946723, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kdd-observability-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 11d 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-observability-scan/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Observability Scan (Capa 3 de KDD -- gaps de logging/monitoreo)

Produce hallazgos de gaps de observabilidad 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, revisar su manejo de errores y cobertura de alertas/tracing, juzgar el impacto de cada gap) que el gate despues valida. Distincion central: el agente decide QUE es un gap de observabilidad; el gate solo audita que el artefacto sellado cumpla forma y politica de calidad de datos.

Como los demas dominios nativos de KDD (kdd-compliance-scan, kdd-privacy-scan, kdd-accessibility-scan, kdd-dependency-eol-scan), esta skill NO vendoriza ningun sellador externo -- vos mismo escribis findings.json ya en forma final.

Cuando usarla

El usuario pide auditar si los errores de un sistema se detectan a tiempo (logueados, alertados, trazables) y quiere el resultado gobernado por KDD (versionable, gateado en CI, con politica declarativa), no un reporte suelto en prosa.

Insumos que necesitas antes de empezar

  • repo_root: raiz del repositorio/producto a revisar.
  • scan_dir: donde vas a escribir findings.json. Por defecto observability/scan dentro del repo KDD (coincide con el default de validate_observability_findings.py); si estas gobernando un repo EXTERNO, cualquier directorio disponible sirve, con tal de pasarselo explicito al gate.
  • El schema completo vive en knowledge/data_models/observability/findings.schema.json -- consultalo si dudas de un campo, no adivines la forma.

Flujo

1. Identifica las rutas criticas

Antes de revisar codigo, fija por escrito (2-3 lineas) que operaciones son criticas para este sistema: las que mueven dinero, autentican usuarios, escriben datos irreversibles, o cuyo fallo silencioso tendria el mayor costo de deteccion tardia. Esto acota donde buscar -- no hace falta revisar cada linea del repo, si el sistema entero.

2. Revisa manejo de errores en esas rutas

Read the full file on GitHub · 139 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. 11d ago First seen · 139 lines · 134 tokens per session scan A d6b913946723

Subscribe to this mod's changes

kdd-observability-scan is a skill published in the GitHub repository MauricioPerera/KDD (7 stars, last pushed 2d ago), licensed MIT. It adds 134 tokens to every session and 1,600 once invoked, about $0.0007 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.