1---2name: observability-hooks3description: Observability Hooks4---56# Observability Hooks78Purpose: Emit useful local evidence without leaking secrets or adding telemetry.9101. Emit project-scoped events for stage starts, completions, drops, and blockers.112. Redact secrets and token-like values.123. Avoid external analytics or crash reporting.134. Preserve enough detail to debug failed gates.1415Checklist:1617- Events include work item when known.18- Messages are concise.19- No secrets in payloads.20- Failure events name the gate.2122Positive example: MCP capability dropped with name and sanitized reason.23Negative example: log full environment.2425Failure modes: noisy logs, missing blocker evidence, secret leakage.
Run npx skillmds@latest add onfire7777/observability-hooks in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Observability Hooks It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
onfire7777 (@onfire7777) published this skill. Their other Agent Skills are listed on their SkillMD profile.