truestack-observability

truestack-observability is a skill for Claude Code from adtn0810/truestack. It costs 252 tokens per session (2,425 once invoked), scanned A, original, MIT.

A guide for adding production monitoring to a self-hosted backend. It covers logs, metrics, traces, health checks, and alerts so a service’s behaviour can be inspected while it runs.

In plain words
What is it for?
Use it to add structured logs, service metrics, request tracing, health endpoints, monitoring dashboards, or alerts based on reliability targets. It also covers connecting telemetry exporters and monitoring collectors.
Why use it?
It helps reveal errors, slow requests, resource limits, and failures before they become difficult to diagnose. It also keeps the monitoring system bounded so it does not overwhelm the application’s single server.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md.

Part of the truestack plugin — 23 skills, 8 commands, 2 hooks shipped together

Good fit Use it to add structured logs, service metrics, request tracing, health endpoints, monitoring dashboards, or alerts based on reliability targets. It also covers connecting telemetry exporters and monitoring collectors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adtn0810/truestack/truestack-observability
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.

Any agent
npx skills add adtn0810/truestack --skill truestack-observability
Clone the repo
git clone --depth 1 https://github.com/adtn0810/truestack

Made for: Claude Code.

Or install truestack, the plugin that ships this one along with the rest of its 23 skills, 8 commands, 2 hooks.

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 truestack-observability

README.md
[![agentmods](https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-observability/github.svg)](https://agentmods.dev/skills/adtn0810/truestack/truestack-observability)
Your own site
<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-observability"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-observability/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 truestack-observability

Your own site · 80×15
<a href="https://agentmods.dev/skills/adtn0810/truestack/truestack-observability"><img src="https://agentmods.dev/badge/skills/adtn0810/truestack/truestack-observability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 252 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,425 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.
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 $0.00252 $0.02425
Opus 5 $0.00126 $0.01213
Sonnet 5 $0.00050 $0.00485
Haiku 4.5 $0.00025 $0.00243

Measured 10d ago against content hash 2c8c62213222, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

truestack-observability 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 10d 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.

skills/truestack-observability/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

truestack-observability

Make one box tell you the truth about itself — counts as metrics, narrative as logs, causality as traces — without the telemetry pipeline becoming the thing that takes the box down. On a self-hosted single server CPU, memory, connections, and disk are finite; the observability stack is a strictly bounded, lower-priority tenant, never a co-equal of the app.

Read project memory first — CLAUDE.md is auto-loaded (Principles + Boundaries); consult .ai/memory/ for the stack, existing log/metric conventions, and the backend it runs on. If none exists, run truestack-project-memory. Keep the code↔memory tally balanced: if you add a health endpoint, an OTLP endpoint, a Collector config, or a dashboard, record the command/decision in the same change.

Adding a Collector, wiring an OTLP exporter on the request path, or changing a health probe an orchestrator already restarts on is shippable infra — route it through truestack-architecture-planning's approval gate before writing it, and let truestack-quality-control gate it before "done". Destructive or deploy/migration steps (dropping a metrics volume, repointing a probe in prod) hit the PreToolUse gate in hooks/ where it's wired — they need an explicit yes, not just an intent. If the gate is not installed in this environment, ask the user explicitly before any destructive or prod-affecting step — the protection degrades to a manual ask, never to silence.

Where this skill sits: it builds the standing telemetry that lets you see production — it feeds evidence to truestack-root-cause-debugging (it is not the active bug investigation) and is not the one-shot load/perf check truestack-quality-control runs on a change. The container/compose healthcheck and the cutover probe are truestack-deploy-and-runtime's; this skill owns exposing app/dependency health as a monitoring signal wired to SLOs/alerting — reuse whatever probe paths truestack-deploy-and-runtime / .ai/memory/ already recorded rather than inventing new ones.

Read the full file on GitHub · 133 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 133 lines · 252 tokens per session scan A 2c8c62213222

Subscribe to this mod's changes

truestack-observability is a skill published in the GitHub repository adtn0810/truestack (2 stars, last pushed 2mo ago), licensed MIT. It adds 252 tokens to every session and 2,425 once invoked, about $0.0013 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.