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.
npx skills add adtn0810/truestack --skill truestack-observabilitygit clone --depth 1 https://github.com/adtn0810/truestackWrote 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.
[](https://agentmods.dev/skills/adtn0810/truestack/truestack-observability)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
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.
- 10d ago First seen · 133 lines · 252 tokens per session scan A 2c8c62213222
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.
Other skills, from other repositories
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
cli-backup-sync
Backup and restore OmniRoute data from the CLI. Trigger incremental snapshots, sync to cloud storage, manage backup schedules, and restore from archive files.
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.