# Observability Hooks

> Observability Hooks

- Skill: `onfire7777/observability-hooks` (Agent Skill)
- Install (CLI): `npx skillmds@latest add onfire7777/observability-hooks`
- Raw SKILL.md: https://api.skillmd.com/api/skills/onfire7777/observability-hooks/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: onfire7777 (https://skillmd.com/u/onfire7777)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/onfire7777/observability-hooks

---


# Observability Hooks

Purpose: Emit useful local evidence without leaking secrets or adding telemetry.

1. Emit project-scoped events for stage starts, completions, drops, and blockers.
2. Redact secrets and token-like values.
3. Avoid external analytics or crash reporting.
4. Preserve enough detail to debug failed gates.

Checklist:

- Events include work item when known.
- Messages are concise.
- No secrets in payloads.
- Failure events name the gate.

Positive example: MCP capability dropped with name and sanitized reason.
Negative example: log full environment.

Failure modes: noisy logs, missing blocker evidence, secret leakage.