Happy Infra Metrics and Grafana
slopus/happy
Queries live Prometheus metrics and manages Grafana dashboards as code for Happy's infrastructure, using the grafanactl CLI and the Grafana datasource proxy API.
Read what FastLLM has been doing — usage records, time-series aggregates, the configuration audit trail, Prometheus metrics, control-plane health, and per-replica fleet status.
Install Fastllm Observability
$ npx skills add azrtydxb/Fastllm-proxy --skill fastllm-observability -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install azrtydxb/Fastllm-proxy fastllm-observability --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/azrtydxb/Fastllm-proxy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/fastllm-observability .claude/skills/fastllm-observability && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "fastllm-observability" agent skill from https://github.com/azrtydxb/Fastllm-proxy/tree/main/.claude/skills/fastllm-observability into .claude/skills/fastllm-observability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fastllm-observability", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/azrtydxb/Fastllm-proxy/tree/main/.claude/skills/fastllm-observabilityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add azrtydxb/Fastllm-proxy --skill fastllm-observability -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install azrtydxb/Fastllm-proxy fastllm-observability --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/azrtydxb/Fastllm-proxy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/fastllm-observability .agents/skills/fastllm-observability && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fastllm-observability" agent skill from https://github.com/azrtydxb/Fastllm-proxy/tree/main/.claude/skills/fastllm-observability into .agents/skills/fastllm-observability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fastllm-observability", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add azrtydxb/Fastllm-proxy --skill fastllm-observability -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install azrtydxb/Fastllm-proxy fastllm-observability --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/azrtydxb/Fastllm-proxy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/fastllm-observability .cursor/skills/fastllm-observability && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fastllm-observability" agent skill from https://github.com/azrtydxb/Fastllm-proxy/tree/main/.claude/skills/fastllm-observability into .cursor/skills/fastllm-observability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fastllm-observability", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/azrtydxb/Fastllm-proxy.git --path .claude/skills/fastllm-observability--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add azrtydxb/Fastllm-proxy --skill fastllm-observability -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install azrtydxb/Fastllm-proxy fastllm-observability --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/azrtydxb/Fastllm-proxy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/fastllm-observability .gemini/skills/fastllm-observability && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fastllm-observability" agent skill from https://github.com/azrtydxb/Fastllm-proxy/tree/main/.claude/skills/fastllm-observability into .gemini/skills/fastllm-observability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fastllm-observability", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install azrtydxb/Fastllm-proxy fastllm-observabilityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add azrtydxb/Fastllm-proxy --skill fastllm-observability -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/azrtydxb/Fastllm-proxy.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/fastllm-observability .github/skills/fastllm-observability && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fastllm-observability" agent skill from https://github.com/azrtydxb/Fastllm-proxy/tree/main/.claude/skills/fastllm-observability into .github/skills/fastllm-observability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fastllm-observability", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add azrtydxb/Fastllm-proxy --skill fastllm-observability -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install azrtydxb/Fastllm-proxy fastllm-observability --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/azrtydxb/Fastllm-proxy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/fastllm-observability .opencode/skills/fastllm-observability && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fastllm-observability" agent skill from https://github.com/azrtydxb/Fastllm-proxy/tree/main/.claude/skills/fastllm-observability into .opencode/skills/fastllm-observability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fastllm-observability", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
fastllm-observability- GitHub stars
- 108
- Token cost
- ~916 tokens
- SKILL.md length
- 442 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Read what FastLLM has been doing — usage records, time-series aggregates, the configuration audit trail, Prometheus metrics, control-plane health, and per-replica fleet status.
- Asked how much a caller spent
- SKILL.md covers Auth and Facts worth knowing
- Calls curl
- What changed and who changed it
What it does
Fastllm Observability is an agent skill from azrtydxb/Fastllm-proxy. Read what FastLLM has been doing — usage records, time-series aggregates, the configuration audit trail, Prometheus metrics, control-plane health, and per-replica fleet status. Use when asked how much a caller spent, what changed and who changed it, whether a backend is healthy, or to investigate an error-rate or latency question.
Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering Observability, Monitoring and alerting and Forecasting and time series. It works with Prometheus. The repository describes itself as: The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLLM/SGLang — 0.76 µs per request, no I/O… The licence is Apache-2.0.
When your agent uses it
- Asked how much a caller spent
- What changed and who changed it
- Whether a backend is healthy
- Investigate an error-rate
Example prompts
- “/fastllm-observability”
What it can do on your machine
Read from SKILL.md and the folder at commit 5d53db8. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Fastllm Observability loads about 916 tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 442 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from azrtydxb/Fastllm-proxy at commit 5d53db8, republished under its Apache-2.0 licence (© azrtydxb). 442 words, ~916 tokens.
Download SKILL.mdSave it as
.claude/skills/fastllm-observability/SKILL.md (or your agent's skills folder).- name
- fastllm-observability
- description
- Read what FastLLM has been doing — usage records, time-series aggregates, the configuration audit trail, Prometheus metrics, control-plane health, and per-replica fleet status. Use when asked how much a caller spent, what changed and who changed it, whether a backend is healthy, or to investigate an error-rate or latency question.
FastLLM observability
Auth
Admin endpoints need a session cookie, not a bearer token — the gateway master key is not an admin credential.
curl -sk -c /tmp/ck -X POST https://192.168.10.129:4001/login \
-H 'content-type: application/json' -d '{"name":"<user>","password":"<pw>"}'
curl -sk -b /tmp/ck https://192.168.10.129:4001/admin/...<!-- BEGIN GENERATED: endpoints -->| Method | Path | Summary | Body fields |
|---|---|---|---|
GET | /admin/audit | The change log, newest first, keyset-paginated | — |
GET | /admin/fleet | What each proxy replica reports, kept per replica and never merged | — |
GET | /admin/health | Read health | — |
GET | /admin/nodes | The hosts registering their own endpoints, rolled up per node. An agent is not a row: it is a node several dynamic providers share, and its lease is what says it is alive | — |
GET | /admin/timeseries | Bucketed traffic, latency and spend. Empty buckets come back as explicit zeros; latency is null where there was nothing to measure | — |
GET | /admin/usage | Aggregate usage and spend, grouped by model, principal, frontend model or day | — |
GET | /metrics | Prometheus text. Unauthenticated | — |
* optional field
<!-- END GENERATED: endpoints -->Facts worth knowing
The audit trail is middleware, not hand-wired. Everything that is not a GET
under /admin/* passes through it, so a newly added endpoint is audited before
it is written. GETs are deliberately not audited — auditing reads would bury
the changes in noise.
Direct database writes produce no audit row. If a change was made with
psql because no admin credential was available, the audit trail will not show
it; say so explicitly rather than letting the absence imply nothing happened.
A usage row exists for every attributable request, including ones whose
response carried no token counts. usage_reported distinguishes "consumed
nothing" from "counts unknown" — treating them alike understates consumption.
/admin/fleet never averages replicas together. Every replica losing a
backend is a dead backend; one replica losing it is a partition.
Show full SKILL.md (179 more words)Show less
snapshot_version spread is not a measure of staleness. A version is the
microsecond the control plane built that snapshot, and it republishes only when
the content changed — so the gap between two consecutive versions is the time
between two real config changes, not any replica's lag. A replica one version
behind can show a gap of a second or of a minute at identical health.
Judge it by time instead. Proxies poll every config_poll_seconds and report
health every health_report_interval_seconds (both in GET /admin/config), so
a replica is stuck only if the newest snapshot has been available for longer
than their sum — or if it has been behind across several samples spanning that
long. The second test is the one that works on a busy gateway, where
Budget.tokens_used being part of the snapshot means traffic alone republishes
it every few seconds and nothing is ever old. One GET /admin/fleet cannot
distinguish a stuck replica from a converging one there; take a few, spaced.
Reading any spread at all as a fault reports a healthy fleet as split after every change.
© azrtydxb, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/fastllm-observability of azrtydxb/Fastllm-proxy.
Open the folder on GitHubat commit 5d53db8
Compare with similar skills
Fastllm Observability next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Fastllm Observability this skillazrtydxb/Fastllm-proxy | 108 | — | ~916 | Automated safety check: Pass | Apache-2.0 | |
| Happy Infra Metrics and Grafanaslopus/happy | 24k | — | ~2k | Automated safety check: Notes | MIT | |
| WizTelemetry Platform Servicekubesphere/kubesphere | 17k | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Redis Observabilityredis/agent-skills | 166 | 2 repos | ~911 | Automated safety check: Pass | MIT | |
| Developing Funboost Mixinydf0509/funboost | 895 | — | ~2.1k | Automated safety check: Pass | None | |
| Prometheus System Health Checkprometheus/prometheus-mcp | 121 | — | ~584 | Automated safety check: Pass | Apache-2.0 |
Similar skills
WizTelemetry Platform Service
kubesphere/kubesphere
Installs and configures the WizTelemetry Platform Service extension for KubeSphere, the shared API server behind its observability extensions.
- Official
Redis Observability
redis/agent-skills
Redis observability guidance — which metrics to monitor (memory, connections, hit ratio, ops/sec, rejected connections), which built-in commands to reach for during incident triage (SLOWLOG, INFO…
Developing Funboost Mixin
ydf0509/funboost
当需要为 funboost 创建 Consumer 或 Publisher 的 Mixin 扩展类时使用。触发场景：添加监控、熔断、限流、链路追踪等横切关注点，编写自定义前置/后置处理钩子。关键词：mixin, consumeroverridecls, publisheroverridecls, ConsumerMixin, 自定义消费者, hook, 拦截器, 熔断器, 监控…
Prometheus System Health Check
prometheus/prometheus-mcp
Builds a picture of whether Prometheus itself is healthy and successfully monitoring its targets, covering readiness, firing alerts, target health and TSDB load.
Archestra Dev Observability
archestra-ai/archestra
A skill your agent uses when changing Archestra tracing, metrics, OpenTelemetry, Tempo, Grafana, Prometheus, LLM/MCP spans, observability labels, or local observability setup.
More from azrtydxb/Fastllm-proxy
All 14 skills in this repoFastllm Agents
azrtydxb/Fastllm-proxy
Manage and invoke A2A agents behind FastLLM — register, patch, delete and list agents on the control plane, list them through the gateway, fetch an agent card, and invoke an agent by name.
Fastllm Backends
azrtydxb/Fastllm-proxy
Run and troubleshoot the inference backends on the DGX Spark pair that FastLLM proxies to — starting or stopping models with vLLM, SGLang or sparkrun, choosing memory and speculative-decoding…
Fastllm Classifier
azrtydxb/Fastllm-proxy
Manage FastLLM prompt classes for semantic routing — create classes and their example prompts, list or delete them, and evaluate how a given prompt would be classified.
Fastllm Deployment
azrtydxb/Fastllm-proxy
Inspect and control the running FastLLM deployment — read effective configuration and deployment settings, force a snapshot rebuild, fetch the snapshot the proxies consume, and check liveness and…
Fastllm Gateway
azrtydxb/Fastllm-proxy
Send inference requests through the FastLLM OpenAI-compatible gateway — chat completions, completions, embeddings, rerank, score, responses, moderations, audio speech and transcription, image…
Fastllm MCP
azrtydxb/Fastllm-proxy
Manage and use MCP servers behind FastLLM — register, patch, delete and list MCP servers on the control plane, and list or call their tools through the gateway.
Related
Works with
Categories
Questions about Fastllm Observability
What does Fastllm Observability do?
Read what FastLLM has been doing — usage records, time-series aggregates, the configuration audit trail, Prometheus metrics, control-plane health, and per-replica fleet status. Fastllm Observability is an agent skill from azrtydxb/Fastllm-proxy. Read what FastLLM has been doing — usage records, time-series aggregates, the configuration audit trail, Prometheus metrics, control-plane health, and per-replica fleet status.
When should I use Fastllm Observability?
Fastllm Observability fits situations like: asked how much a caller spent; what changed and who changed it; whether a backend is healthy; investigate an error-rate.
How do I install Fastllm Observability in Claude Code?
Run `npx skills add azrtydxb/Fastllm-proxy --skill fastllm-observability -a claude-code`. Or copy the skill folder (.claude/skills/fastllm-observability in azrtydxb/Fastllm-proxy) into .claude/skills/fastllm-observability in your project. Claude Code loads it when a task matches its description.
How do I install Fastllm Observability in Codex?
Run `npx skills add azrtydxb/Fastllm-proxy --skill fastllm-observability -a codex`. Or copy the skill folder (.claude/skills/fastllm-observability in azrtydxb/Fastllm-proxy) into .agents/skills/fastllm-observability in your project. Codex loads it when a task matches its description.
Can I use Fastllm Observability in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add azrtydxb/Fastllm-proxy --skill fastllm-observability -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fastllm-observability, .gemini/skills/fastllm-observability, .github/skills/fastllm-observability and .opencode/skills/fastllm-observability in your project.
What does Fastllm Observability need to run?
Going by SKILL.md and its folder, Fastllm Observability needs the command-line tools its instructions call (curl).
Does Fastllm Observability access the network?
SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Fastllm Observability safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Fastllm Observability use?
Fastllm Observability is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Fastllm Observability use?
About 916 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Fastllm Observability?
Skills that share tags, products or a category with Fastllm Observability: Happy Infra Metrics and Grafana (slopus/happy, 24k stars), WizTelemetry Platform Service (kubesphere/kubesphere, 17k stars), Redis Observability (redis/agent-skills, 166 stars) and Developing Funboost Mixin (ydf0509/funboost, 895 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Fastllm Observability?
azrtydxb (a GitHub organization) maintains it in azrtydxb/Fastllm-proxy, which has 108 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 5, 2026.
Source: azrtydxb/Fastllm-proxy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.