Instrument a service so the questions asked during an incident are answerable from data already being collected — rate, errors, latency distribution and saturation per route, structured events carrying a correlation id that survives process and queue boundaries, and alerts on symptoms users feel. Use before a service or a new critical path goes to production, after an incident that ended in "we had no data for that", or when adding a dependency, queue or job whose failure would be silent. Not…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Observability
Telemetry is written before the incident and read during it. A dashboard nobody had a question for
is a screensaver; a log line nobody can correlate is a receipt for an event you cannot find.
## When this fires
A service is about to carry real traffic, a new critical path is added, or a review asks how a
failure here would be noticed. It fires hardest immediately after an incident where the answer was
not in the data — that is the only moment the gap is precisely known.
It does not fire for a live outage (mitigate first), for a slow path you can already reproduce and
measure, or for LLM/agent run traces.
## Procedure
1. **Write the questions down first.** "Is it up, is it wrong, is it slow, which dependency, which
deploy, which tenant." Each signal you add answers a named question. Instrumentation added
without one becomes cost and noise that later gets sampled away.
2. **Cover every request path with four numbers**: request rate, error rate, duration distribution,
and saturation of whichever resource is actually constrained (connections, workers, memory, queue
…
The line at the top of this page pins the label git:20260919.a0d4f55, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_z2t73eryhkddofea
GET https://markdownregistry.com/api/v1/resolve?ref=nahid-sparktales/agent-dispatcher/observability
GET https://markdownregistry.com/api/v1/blob/63cb72180df25a4c9e47a004785a9145db7ea75f357cc9d2a68bfe5aeff6dbde
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
nahid-sparktales/agent-dispatcher · skills/agent-dispatcher/SKILL.md · Handle requested Agent Dispatcher work with direct execution or prepared specialist guidance. Includes named roles…
nahid-sparktales/agent-dispatcher · skills/ai/agent-design/SKILL.md · Scope an agent or subagent before it is built — the one job it owns, the smallest tool set that closes that job, what…
nahid-sparktales/agent-dispatcher · skills/ai/agent-evals/SKILL.md · Build an eval suite that can actually detect a regression — cases pulled from real traffic, graders that check…
nahid-sparktales/agent-dispatcher · skills/ai/context-engineering/SKILL.md · Decide what actually occupies the model's window — progressive disclosure through an index, retrieval versus inlining…
nahid-sparktales/agent-dispatcher · skills/ai/llm-observability/SKILL.md · See what an agent actually did — one trace per run with nested model, tool and retrieval spans, token and latency…
nahid-sparktales/agent-dispatcher · skills/ai/mcp-design/SKILL.md · Build an MCP server, or bring an existing one into a project — choosing the transport, deciding which tools, resources…
nahid-sparktales/agent-dispatcher · skills/ai/memory-design/SKILL.md · Decide what an agent should remember, which layer holds it, who it is scoped to, and how a stale or contradicted memory…
nahid-sparktales/agent-dispatcher · skills/ai/model-routing/SKILL.md · Pick a model per job and degrade sensibly when one fails — a quality bar per call site, candidates compared on the same…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-engineering/SKILL.md · Write or revise a prompt so it holds up — output contract, instruction placement, examples that earn their place, an…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-injection-defense/SKILL.md · Treat everything an agent reads but did not author as data rather than instructions — an explicit trust boundary, a…
nahid-sparktales/agent-dispatcher · skills/ai/retrieval-rag/SKILL.md · Build and fix retrieval that actually returns the right passage — structure-aware chunking, one pinned embedding model…
nahid-sparktales/agent-dispatcher · skills/ai/structured-output/SKILL.md · Get parseable, trustworthy structured results out of a model — schema design, the enforcement mechanism the provider…
ericrisco/rsc-harness · skills/observability/SKILL.md · Use when instrumenting a service from the inside so an incident can be explained from telemetry alone — wiring…
rjmurillo/ai-agents · .claude/skills/observability/SKILL.md · Use when you say `query agent logs`, `find slow tool calls`, `show agent errors`, or `what to log`. Query and analyze…
rjmurillo/ai-agents · src/claude/skills/observability/SKILL.md · Use when you say `query agent logs`, `find slow tool calls`, `show agent errors`, or `what to log`. Query and analyze…
outlinedriven/odin-claude-plugin · plugins/odin-infra/skills/observability/SKILL.md · Use when adding telemetry, composing an observability surface, reviewing alerts, shipping a production feature, or…
byerlikaya/claude-starter-kit · kit/skills/observability/SKILL.md · Stack-agnostic observability: structured logs, correlation ids, metrics and traces; no PII or secrets in logs.
Makes a…
