Agent skill

Floe Guard

Install Floe Guard

skills CLI

$ npx skills add Floe-Labs/floe-guard --skill floe-guard -a claude-code

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

GitHub CLI

$ gh skill install Floe-Labs/floe-guard floe-guard --agent claude-code

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

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "floe-guard" agent skill from https://github.com/Floe-Labs/floe-guard/tree/main into .claude/skills/floe-guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "floe-guard", 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.

skills CLI

$ npx skills add Floe-Labs/floe-guard --skill floe-guard -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Floe-Labs/floe-guard floe-guard --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "floe-guard" agent skill from https://github.com/Floe-Labs/floe-guard/tree/main into .agents/skills/floe-guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "floe-guard", 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.

skills CLI

$ npx skills add Floe-Labs/floe-guard --skill floe-guard -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Floe-Labs/floe-guard floe-guard --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "floe-guard" agent skill from https://github.com/Floe-Labs/floe-guard/tree/main into .cursor/skills/floe-guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "floe-guard", 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.

skills CLI

$ npx skills add Floe-Labs/floe-guard --skill floe-guard -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Floe-Labs/floe-guard floe-guard --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "floe-guard" agent skill from https://github.com/Floe-Labs/floe-guard/tree/main into .gemini/skills/floe-guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "floe-guard", 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.

GitHub CLI

$ gh skill install Floe-Labs/floe-guard floe-guard

Installs 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).

skills CLI

$ npx skills add Floe-Labs/floe-guard --skill floe-guard -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "floe-guard" agent skill from https://github.com/Floe-Labs/floe-guard/tree/main into .github/skills/floe-guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "floe-guard", 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.

skills CLI

$ npx skills add Floe-Labs/floe-guard --skill floe-guard -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Floe-Labs/floe-guard floe-guard --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "floe-guard" agent skill from https://github.com/Floe-Labs/floe-guard/tree/main into .opencode/skills/floe-guard/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "floe-guard", 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: floe-guard
GitHub stars: 357
Token cost: ~853 tokens
SKILL.md length: 299 words
Files: 179 (incl. scripts)
Skills in repo: 1
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

An agents spend must be seen and capped in-process with no account
SKILL.md covers Install, Wire the hard-stop, Skip the manual wiring —… and Rules, plus 1 more section
Calls npx, pip and npm
Also guards any LLM agent and paid tool calls

What it does

Floe Guard is an agent skill from Floe-Labs/floe-guard. Know what every AI call really costs — floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript), keeps a live ledger of real spend, and hard-stops the next turn before it crosses a USD ceiling. Free Coverage Score + 7-day history on connect. Use when an agent's spend must be seen and capped in-process with no account or telemetry; also guards any LLM agent and paid tool calls.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. The skill folder holds 181 other files, including scripts (for example `.github/ISSUE_TEMPLATE/bug_report.md`, `.github/ISSUE_TEMPLATE/config.yml` and `.github/ISSUE_TEMPLATE/feature_request.md`).

It sits in Media & Creative, covering Text to speech and voice. It works with Python, TypeScript and ElevenLabs. The repository describes itself as: AI Initiative Ledger — local spend meter and budget gate for AI tasks. Meters every vendor leg (LLM, speech, telephony, search, tools), hard-stops before the ceiling. MIT, no… The licence is MIT.

When your agent uses it

An agents spend must be seen and capped in-process with no account
Also guards any LLM agent and paid tool calls

Example prompts

“/floe-guard”

Requirements

Python 3
Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit f9bf99a. 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
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
- npx
- pip
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- github.com
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

Floe Guard loads about 853 tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 299 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~107
When it runs · the whole SKILL.md, loaded when a task matches: ~853

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Floe-Labs/floe-guard at commit f9bf99a, republished under its MIT licence (© Floe-Labs). 299 words, ~853 tokens.

Download SKILL.mdSave it as .claude/skills/floe-guard/SKILL.md (or your agent's skills folder). This skill also uses 178 other files; get the full folder from GitHub.

name: floe-guard
description: Know what every AI call really costs — floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript), keeps a live ledger of real spend, and hard-stops the next turn before it crosses a USD ceiling. Free Coverage Score + 7-day history on connect. Use when an agent's spend must be seen and capped in-process with no account or telemetry; also guards any LLM agent and paid tool calls.
license: MIT
homepage: https://github.com/Floe-Labs/floe-guard

floe-guard — know what every AI call costs

floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript) and keeps a live ledger of your agent's real spend. Connect free for your Coverage Score and 7-day history. It also hard-stops the next turn before it crosses a USD ceiling. In-process, no account, no telemetry. Guards any LLM/tool call the same way. Budget, not balance — it caps spend, holds no money, needs no account.

This is the library skill. For the whole govern-your-spend workflow (spend policies, voice coverage, hosted upgrade, Coverage Score), add the full Floe skill: npx skills add floe-labs/agent-skills.

Install

Python: pip install floe-guard
TypeScript / Node: npm i floe-guard

Wire the hard-stop

check() before each model call (raises if it would cross the ceiling), record() after (prices the tokens offline and accrues them):

python

from floe_guard import BudgetGuard

guard = BudgetGuard(limit_usd=5.00)
guard.check()                         # raises BudgetExceeded before an over-budget call runs
resp = call_your_llm(...)
guard.record("gpt-4o", resp.usage.prompt_tokens, resp.usage.completion_tokens)

Verify offline (no key, no network): floe-guard demo.

Skip the manual wiring — adapters

Frameworks: OpenAI, Anthropic, Gemini, CrewAI, LangChain, LangGraph, LiteLLM, Vercel AI SDK.
Voice (per-turn, prices STT + LLM + TTS + telephony): Python floe_guard.integrations.pipecat / .livekit; TS floe-guard/adapters/{livekit,vapi,retell}.
Pre-call admission: floe_guard.gates (retell / vapi / pre_call) reject an over-budget call before it connects.
Paid tools: reserve_tool() / settle_tool() block before the tool runs.

Rules

Enforcement lives in the call path: check() / reserve() before the call. record() alone meters after the fact — it can't stop a call already made.
Fail-closed: an unpriceable model raises UnpriceableModelError unless you pass a price_overrides rate or fail_closed=False.
Use reserve() / settle() (not check() then record()) under concurrency.
Read advisory() (near-limit flag + $/min burn rate) to taper before the hard-stop.
Opt-in only, off by default: BudgetGuard.from_floe(api_key=…) (hosted headroom) and enable_sync() / floe-guard push (ledger sync for Coverage Score) are the only things that touch the network — nothing does without an explicit opt-in.

References

Full guide: https://github.com/Floe-Labs/floe-guard#readme
Integration steps for an agent: https://github.com/Floe-Labs/floe-guard/blob/main/AGENTS.md
The full Floe skill: https://github.com/Floe-Labs/agent-skills

Files

SKILL.md and 178 other files (scripts) in the repository root of Floe-Labs/floe-guard.

SKILL.md
.github/ISSUE_TEMPLATE/bug_report.md
.github/ISSUE_TEMPLATE/config.yml
.github/ISSUE_TEMPLATE/feature_request.md
.github/PULL_REQUEST_TEMPLATE.md
.github/dependabot.yml
.github/workflows/ci.yml
.github/workflows/publish-npm.yml
.github/workflows/publish.yml
.github/workflows/refresh-cost-map.yml
.github/workflows/version-guard.yml
.gitignore
AGENTS.md
CHANGELOG.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
README.md
… and 161 more

Open the folder on GitHubat commit f9bf99a

Compare with similar skills

Floe Guard 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.

Floe Guard compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Floe Guard this skillFloe-Labs/floe-guard	357	—	~853	Automated safety check: Pass	MIT	5 days ago
Elevenlabs Hello Worldjeremylongshore/tons-of-skills-marketplace	2.8k	—	~1.3k	Automated safety check: Pass	MIT	today
Elevenlabs SDK Patternsjeremylongshore/tons-of-skills-marketplace	2.8k	—	~1.5k	Automated safety check: Pass	MIT	today
Gemini API Devgoogle-gemini/gemini-skills	4.3k	—	~5.1k	Automated safety check: Pass	Apache-2.0	4 days ago
Agentstadaspetra/loop	296	1 repos	~2.5k	Automated safety check: Pass	MIT	8 days ago
Remotionzhuzhaoyun/Molio	433	—	~4k	Automated safety check: Pass	Custom licence	today

Similar skills

Elevenlabs Hello World
jeremylongshore/tons-of-skills-marketplace
Generate your first ElevenLabs text-to-speech audio file. An agent skill from jeremylongshore/tons-of-skills-marketplace.
2.8k GitHub stars~1.3k tokensUpdated today
Media & CreativeAuto-check passed
Elevenlabs SDK Patterns
jeremylongshore/tons-of-skills-marketplace
Apply production-ready ElevenLabs SDK patterns for TypeScript and Python.
2.8k GitHub stars~1.5k tokensUpdated today
Media & CreativeAuto-check passed
Gemini API Dev
google-gemini/gemini-skills
Official
A skill your agent uses when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, speech generation (TTS), voice…
4.3k GitHub stars~5.1k tokensUpdated 4 days ago
AI & LLM EngineeringAuto-check passed
Agents
tadaspetra/loop
Build voice AI agents with ElevenLabs. An agent skill from tadaspetra/loop.
296 GitHub starsUsed in 1 repo~2.5k tokens
AI & LLM EngineeringAuto-check passed
Remotion
zhuzhaoyun/Molio
Molio's builtin skill for MAKING a video from any source — wiki notes, articles, scripts, product info, or a brief — and rendering it to MP4.
433 GitHub stars~4k tokensUpdated today
Media & CreativeAuto-check passed
Speech Engine
elevenlabs/skills
Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine.
482 GitHub stars~2.5k tokensUpdated yesterday
Media & CreativeAuto-check: warnings

Works with

Questions about Floe Guard

What does Floe Guard do?

Know what every AI call really costs — floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript), keeps a live ledger of real spend, and hard-stops the next…. Floe Guard is an agent skill from Floe-Labs/floe-guard. Know what every AI call really costs — floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript), keeps a live ledger of real spend, and hard-stops the next turn before it crosses a USD ceiling.

When should I use Floe Guard?

Floe Guard fits situations like: an agents spend must be seen and capped in-process with no account; also guards any LLM agent and paid tool calls.

How do I install Floe Guard in Claude Code?

Run `npx skills add Floe-Labs/floe-guard --skill floe-guard -a claude-code`. Or copy the skill folder (the Floe-Labs/floe-guard repository) into .claude/skills/floe-guard in your project. Claude Code loads it when a task matches its description.

How do I install Floe Guard in Codex?

Run `npx skills add Floe-Labs/floe-guard --skill floe-guard -a codex`. Or copy the skill folder (the Floe-Labs/floe-guard repository) into .agents/skills/floe-guard in your project. Codex loads it when a task matches its description.

Can I use Floe Guard 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 Floe-Labs/floe-guard --skill floe-guard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/floe-guard, .gemini/skills/floe-guard, .github/skills/floe-guard and .opencode/skills/floe-guard in your project.

What does Floe Guard need to run?

Going by SKILL.md and its folder, Floe Guard needs the command-line tools its instructions call (npx, pip and npm). Our summary lists: Python 3; Node.js.

Does Floe Guard access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Floe Guard 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Floe Guard use?

Floe Guard is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Floe Guard use?

About 853 tokens (SKILL.md is roughly 3.4k 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 Floe Guard?

Skills that share tags, products or a category with Floe Guard: Elevenlabs Hello World (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Elevenlabs SDK Patterns (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Gemini API Dev (google-gemini/gemini-skills, 4.3k stars) and Agents (tadaspetra/loop, 296 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Floe Guard?

Floe-Labs (a GitHub organization) maintains it in Floe-Labs/floe-guard, which has 357 GitHub stars. The repository was last updated on October 5, 2026.

Source: Floe-Labs/floe-guard on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Floe Guard

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

floe-guard — know what every AI call costs

Install

Wire the hard-stop

Skip the manual wiring — adapters

Rules

References

Files

Compare with similar skills

Similar skills

Elevenlabs Hello World

Elevenlabs SDK Patterns

Gemini API Dev

Agents

Remotion

Speech Engine

Related

Questions about Floe Guard