Agent skill

Fastllm Limits Budgets

by azrtydxb in azrtydxb/Fastllm-proxy

Inspect and reconcile FastLLM spend and rate limits — read global budgets and limits, trigger limit reconciliation across replicas, and sync provider prices.

Apache-2.0Auto-check passedBusiness, Finance & HR

Install Fastllm Limits Budgets

skills CLI
$ npx skills add azrtydxb/Fastllm-proxy --skill fastllm-limits-budgets -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install azrtydxb/Fastllm-proxy fastllm-limits-budgets --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/azrtydxb/Fastllm-proxy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/fastllm-limits-budgets .claude/skills/fastllm-limits-budgets && rm -rf skills-src

Use ~/.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/

Facts

Skill name
fastllm-limits-budgets
GitHub stars
108
Token cost
~467 tokens
SKILL.md length
159 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Inspect and reconcile FastLLM spend and rate limits — read global budgets and limits, trigger limit reconciliation across replicas, and sync provider prices.

  • Limit reconciliation across replicas
  • SKILL.md covers Auth and Traps
  • Calls curl
  • Sync provider prices

What it does

Fastllm Limits Budgets is an agent skill from azrtydxb/Fastllm-proxy. Inspect and reconcile FastLLM spend and rate limits — read global budgets and limits, trigger limit reconciliation across replicas, and sync provider prices. Use when a caller is being rate-limited or refused for budget, when spend figures look wrong, or after changing provider pricing. Not for setting one principal's cap (fastllm-principals).

Its SKILL.md is about 470 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 Business, Finance & HR, covering Rate limiting and Accounting and bookkeeping. 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

  • Limit reconciliation across replicas
  • Sync provider prices
  • A caller is being rate-limited
  • Refused for budget

Example prompts

  • “/fastllm-limits-budgets”

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 Limits Budgets loads about 467 tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 159 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~467

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). 159 words, ~467 tokens.

Download SKILL.mdSave it as .claude/skills/fastllm-limits-budgets/SKILL.md (or your agent's skills folder).
name
fastllm-limits-budgets
description
Inspect and reconcile FastLLM spend and rate limits — read global budgets and limits, trigger limit reconciliation across replicas, and sync provider prices. Use when a caller is being rate-limited or refused for budget, when spend figures look wrong, or after changing provider pricing. Not for setting one principal's cap (fastllm-principals).

FastLLM limits budgets

Auth

Admin endpoints need a session cookie, not a bearer token — the gateway master key is not an admin credential.

bash
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 -->
MethodPathSummaryBody fields
GET/admin/budgetsRead budgets—
GET/admin/limitsRead limits—
POST/admin/prices/syncCreate prices syncsource, overwrite, dry_run*
POST/limits/reconcileExchange locally observed counts for a fresh rate-limit allowance. Proxy token onlyreplica_id, counts

* optional field

<!-- END GENERATED: endpoints -->

Traps

Cost is computed at ingest from the price at the time of the request, and stored. Deriving it on read would let a later price change rewrite history. prices/sync therefore affects future rows, not past ones.

The provider's own reported cost wins where present. It already accounts for cache discounts and for a routed alias serving a different model; the configured price is the fallback, not the source.

A refusal and an upstream error are different diagnoses. Budget and rate-limit refusals are recorded distinctly from backend failures so they cannot average into one misleading error rate.

© 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-limits-budgets of azrtydxb/Fastllm-proxy.

Open the folder on GitHubat commit 5d53db8

Compare with similar skills

Fastllm Limits Budgets 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.

Fastllm Limits Budgets compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fastllm Limits Budgets this skillazrtydxb/Fastllm-proxy108—~467Automated safety check: PassApache-2.0
Flyio Rate Limitsjeremylongshore/tons-of-skills-marketplace2.8k—~1.2kAutomated safety check: PassMIT
Canva Rate Limitsjeremylongshore/tons-of-skills-marketplace2.8k—~1kAutomated safety check: PassMIT
Roblox Networkinggamedev-skills/awesome-gamedev-agent-skills1.4k—~2.3kAutomated safety check: PassApache-2.0
Configure Authdotnet/skills5.6k1 repos~1.8kAutomated safety check: PassMIT
Sync State Invariantsopenchamber/openchamber11k—~2.7kAutomated safety check: PassMIT

Similar skills

  • Flyio Rate Limits

    jeremylongshore/tons-of-skills-marketplace

    Implement Fly.io Machines API pacing, per-resource serialization, retry, and reconciliation from the documented action limits.

    2.8k GitHub stars~1.2k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Canva Rate Limits

    jeremylongshore/tons-of-skills-marketplace

    Implement endpoint- and user-scoped Canva throttling with bounded backoff and reconciliation.

    2.8k GitHub stars~1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Roblox Networking

    gamedev-skills/awesome-gamedev-agent-skills

    Design and harden Roblox client/server networking with RemoteEvent, RemoteFunction, and UnreliableRemoteEvent; server authority, argument and Instance validation, rate limits, proximity/ownership…

    1.4k GitHub stars~2.3k tokensUpdated yesterday
    DatabasesAuto-check passed
  • Configure Auth

    dotnet/skills

    Official

    Add authentication and authorization to a Blazor Web App, accounting for the app's render mode.

    5.6k GitHub starsUsed in 1 repo~1.8k tokens
    Business, Finance & HRAuto-check passed
  • Sync State Invariants

    openchamber/openchamber

    A skill your agent uses when changing session synchronization, bootstrap or reconnect state, event reducers, polling, optimistic updates, message queues, live activity, ordering/reconciliation…

    11k GitHub stars~2.7k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Unit Commitment Operating Rules

    benchflow-ai/skillsbench

    A skill your agent uses for day-ahead or multi-period unit commitment problems, including thermal on/off schedules, dispatch, startup/shutdown logic, minimum up/down time, ramping, spinning reserve…

    1.8k GitHub stars~2k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed

More from azrtydxb/Fastllm-proxy

All 14 skills in this repo
  • Fastllm 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.

    108 GitHub stars~512 tokensUpdated 5 days ago
    Auto-check passed
  • 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…

    108 GitHub stars~980 tokensUpdated 5 days ago
    Auto-check passed
  • 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.

    108 GitHub stars~499 tokensUpdated 5 days ago
    Auto-check passed
  • 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…

    108 GitHub stars~727 tokensUpdated 5 days ago
    Auto-check passed
  • 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…

    108 GitHub stars~926 tokensUpdated 5 days ago
    Auto-check passed
  • 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.

    108 GitHub stars~515 tokensUpdated 5 days ago
    Auto-check passed

Questions about Fastllm Limits Budgets

What does Fastllm Limits Budgets do?

Inspect and reconcile FastLLM spend and rate limits — read global budgets and limits, trigger limit reconciliation across replicas, and sync provider prices. Fastllm Limits Budgets is an agent skill from azrtydxb/Fastllm-proxy. Inspect and reconcile FastLLM spend and rate limits — read global budgets and limits, trigger limit reconciliation across replicas, and sync provider prices.

When should I use Fastllm Limits Budgets?

Fastllm Limits Budgets fits situations like: limit reconciliation across replicas; sync provider prices; A caller is being rate-limited; refused for budget.

How do I install Fastllm Limits Budgets in Claude Code?

Run `npx skills add azrtydxb/Fastllm-proxy --skill fastllm-limits-budgets -a claude-code`. Or copy the skill folder (.claude/skills/fastllm-limits-budgets in azrtydxb/Fastllm-proxy) into .claude/skills/fastllm-limits-budgets in your project. Claude Code loads it when a task matches its description.

How do I install Fastllm Limits Budgets in Codex?

Run `npx skills add azrtydxb/Fastllm-proxy --skill fastllm-limits-budgets -a codex`. Or copy the skill folder (.claude/skills/fastllm-limits-budgets in azrtydxb/Fastllm-proxy) into .agents/skills/fastllm-limits-budgets in your project. Codex loads it when a task matches its description.

Can I use Fastllm Limits Budgets 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-limits-budgets -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-limits-budgets, .gemini/skills/fastllm-limits-budgets, .github/skills/fastllm-limits-budgets and .opencode/skills/fastllm-limits-budgets in your project.

What does Fastllm Limits Budgets need to run?

Going by SKILL.md and its folder, Fastllm Limits Budgets needs the command-line tools its instructions call (curl).

Does Fastllm Limits Budgets 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 Limits Budgets 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 Limits Budgets use?

Fastllm Limits Budgets 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 Limits Budgets use?

About 467 tokens (SKILL.md is roughly 1.9k 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 Limits Budgets?

Skills that share tags, products or a category with Fastllm Limits Budgets: Flyio Rate Limits (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Canva Rate Limits (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Roblox Networking (gamedev-skills/awesome-gamedev-agent-skills, 1.4k stars) and Configure Auth (dotnet/skills, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fastllm Limits Budgets?

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.