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 nimadorostkar/Claude-Skills-collection --skill observabilitygit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/observability)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/observability"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/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/nimadorostkar/claude-skills-collection/observability"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/observability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01302 |
| Opus 5 | $0.00021 | $0.00651 |
| Sonnet 5 | $0.00008 | $0.00260 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
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 8d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability
Purpose
Instrument a system so that a question you did not anticipate can still be answered from its telemetry. Monitoring tells you that something is wrong; observability lets you find out why without shipping new code.
When to Use
- Instrumenting a new service.
- An incident where the data needed to diagnose it did not exist.
- Defining SLOs and the alerts that derive from them.
- Reducing alert noise that the team has learned to ignore.
Capabilities
- Structured logging with consistent, queryable fields.
- Metrics: RED (rate, errors, duration) for services, USE (utilization, saturation, errors) for resources.
- Distributed tracing with OpenTelemetry and context propagation.
- SLO and error-budget definition.
- Alert design: symptom-based, actionable, and rare.
Inputs
- The service, its dependencies, and its user-facing operations.
- The questions you have needed to answer in past incidents.
- Existing telemetry and its gaps.
Outputs
- Structured logs with a trace ID on every line.
- RED metrics per endpoint and USE metrics per resource.
- SLOs with error budgets, and alerts that fire on symptoms.
Workflow
- Instrument the user-visible path first — Rate, errors, and duration per endpoint. This answers "is it broken and for whom", which is the first question in every incident.
- Log structurally — JSON with consistent field names, including a trace ID. A log line that must be parsed with a regex is a log line nobody will query at 3am.
- Propagate context — OpenTelemetry, with the trace ID flowing through every hop, including the message queue. A trace that stops at a queue boundary is half a trace.
- Define SLOs from the user's perspective — "99.9% of checkout requests succeed within 500ms." Not "CPU stays below 80%", which no user has ever cared about.
- Alert on symptoms, not causes — Page on "error budget burning fast", not on "CPU high". High CPU with a healthy service is not an incident.
- Delete the alerts nobody acts on — An alert that has fired forty times and been acknowledged forty times without action is training the team to ignore alerts.
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.
- 8d ago First seen · 109 lines · 42 tokens per session scan A a3a2d5ebd00d
observability is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 24d ago), licensed MIT. It adds 42 tokens to every session and 1,302 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
investigate
Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps. Use when the user asks to "investigate this bug", "debug this", "figure out why this fails", "find the root cause", "why is this broken"…
audit
Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to "audit the project", "run a full audit", "project health check", "audit my code", "codebase audit", or "comprehensive review".
consult-oracle
Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says "ask the oracle", "consult oracle", "consult chatgpt", "I'm completely…
find-dead-code
Find dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to "find dead code", "find unused code", "find unused exports", "find unreferenced functions", "clean up dead code", or "what code is unused". Analysis-only — does not modify…
polish-code
Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".
simplify-code
Run a multi-agent review of changed files for scope, reuse, quality, efficiency, clarity, and altitude issues followed by fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes"…