set-up-drift-alerts SKILL.md skillA
set-up-drift-alerts from contextjet-ai/awesome-llm-observability is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add contextjet-ai/awesome-llm-observability/set-up-drift-alerts@git:20261015.76d5de4Pins git:20261015.76d5de4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- contextjet-ai/awesome-llm-observability
- Path
skills/set-up-drift-alerts/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261015.76d5de4, committed Oct 15, 2026
- First version recorded
- Jul 5, 2026
- Size
- 3,626 bytes
- Repository stars
- 45
- License
- a license file GitHub does not identify
Use this to catch an LLM app silently getting worse in production - quality dropping, cost creeping up, inputs shifting away from what you tested. Trigger on "monitor my LLM in production", "alert me when quality drops", "detect drift", "my app got worse and I didn't notice", "set up monitoring/alerting for my AI app". Alert on the signals that actually move, not vanity metrics.
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
# Set up drift alerts An LLM app that worked at launch degrades quietly: a model provider updates weights, users start asking different questions, a prompt change trades quality for cost. Drift alerting turns "we found out from an angry customer" into "we got paged when the metric moved." ## The four drifts worth alerting on 1. **Quality drift** - your online eval scores (faithfulness, relevance, hallucination rate) trend down. The one that matters most and the one people forget to watch. Requires online evals (see `add-llm-evals`). 2. **Cost drift** - tokens/request or spend/day creeps up (context bloat, a retry bug, a prompt that grew). Cheap to track, common, expensive to ignore. 3. **Latency / error drift** - p95 latency or error rate rises (provider slowdown, rate limits, a slow retrieval). 4. **Input drift** - production inputs move away from your eval set (new topics, new languages, longer inputs). Your evals stop being representative, so quality can drop *without* your quality metric catching it. Detect via input length/embedding-distribution shift. ## How to set it up …
Read the whole file at its exact version.
How to install
mdr add contextjet-ai/awesome-llm-observability/set-up-drift-alerts@sha256:cf9bb20b6a91e72cThe line at the top of this page pins the label git:20261015.76d5de4, 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.
[](https://markdownregistry.com/a/art_gd4mcf3ak6plsmgc)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 5, 2026 and Oct 15, 2026, about one every 102 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.76d5de4 latest | 2026-10-15 | 76d5de4 | 3,626 B | A | view · diff |
| git:20260705.2cc0ac5 | 2026-07-05 | 2cc0ac5 | 3,585 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3626 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
contextjet-ai/awesome-llm-observability · 45 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gd4mcf3ak6plsmgc GET https://markdownregistry.com/api/v1/resolve?ref=contextjet-ai/awesome-llm-observability/set-up-drift-alerts GET https://markdownregistry.com/api/v1/blob/cf9bb20b6a91e72cba6a3539cb43833eb92c56f5801b57753e851ff151f40f62
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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.