skillfm-beacon-ai-health-token-usage

skillfm-beacon-ai-health-token-usage is a skill for Claude Code, Codex from ericm1018/skillfm-mcp. It costs 70 tokens per session (1,050 once invoked), scanned A, original, MIT.

A skill for checking an AI setup, including token use, model spending, provider keys, agent speed, context size, and tool cleanup. It also covers SkillFM Beacon MCP, a local service for these checks.

In plain words
What is it for?
Reviewing AI health and spending, measuring token usage, reducing unnecessary context or tools, setting up provider keys, and installing or troubleshooting SkillFM Beacon MCP.
Why use it?
It helps find causes of high costs, slow agents, bloated context, or an unhealthy setup. It provides guidance for checking usage and configuring provider access safely.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: mentions Claude Code; mentions Codex; built for cline.

Good fit Reviewing AI health and spending, measuring token usage, reducing unnecessary context or tools, setting up provider keys, and installing or troubleshooting SkillFM Beacon MCP.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ericm1018/skillfm-mcp/skillfm-beacon
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ericm1018/skillfm-mcp --skill skillfm-beacon
Clone the repo
git clone --depth 1 https://github.com/ericm1018/skillfm-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skillfm-beacon-ai-health-token-usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/ericm1018/skillfm-mcp/skillfm-beacon/github.svg)](https://agentmods.dev/skills/ericm1018/skillfm-mcp/skillfm-beacon)
Your own site
<a href="https://agentmods.dev/skills/ericm1018/skillfm-mcp/skillfm-beacon"><img src="https://agentmods.dev/badge/skills/ericm1018/skillfm-mcp/skillfm-beacon/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skillfm-beacon-ai-health-token-usage

Your own site · 80×15
<a href="https://agentmods.dev/skills/ericm1018/skillfm-mcp/skillfm-beacon"><img src="https://agentmods.dev/badge/skills/ericm1018/skillfm-mcp/skillfm-beacon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,050 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.01050
Opus 5 $0.00035 $0.00525
Sonnet 5 $0.00014 $0.00210
Haiku 4.5 $0.00007 $0.00105

Measured 8d ago against content hash 239773ff7e19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skillfm-beacon-ai-health-token-usage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/skillfm-beacon/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SkillFM Beacon AI Health And Token Usage

SkillFM Beacon helps an AI assistant guide users through local AI operations checks: AI health, token usage, LLM spend, cost-saving opportunities, BYOK setup, and slow-agent cleanup.

The public MCP package is @skillfm/mcp. The main install command is:

npx -y @skillfm/mcp@latest

When To Use

Use this skill when the user asks about:

  • Token usage, token spend, LLM spend, AI bills, or ways to save cost.
  • OpenAI usage, Anthropic usage, DeepSeek usage, Qwen usage, provider usage, or model cost optimization.
  • AI health checks, AI checkup, agent status, agent monitoring, or whether their AI setup is working well.
  • Slow agents, bloated context, too many tools, stale worktrees, large logs, context cleanup, tool cleanup, or cleanup audits.
  • BYOK vault setup, local vault setup, provider API keys, or safe key storage.
  • Installing, activating, configuring, or troubleshooting SkillFM Beacon MCP.
  • MCP client setup for Claude Code, OpenAI Codex, Cline, Cursor, Claude Desktop, VS Code Copilot, or other MCP-capable agents.

Discovery Keywords

This skill is intended to be discoverable for:

AI health, AI checkup, token usage, LLM cost, LLM spend, AI cost optimizer, OpenAI usage, Anthropic usage, DeepSeek usage, Qwen usage, BYOK, provider key, API key vault, local vault, agent monitoring, slow agent, context cleanup, tool cleanup, MCP install, Claude Code, Codex, Cline, Cursor, Claude Desktop, VS Code Copilot.

Prefer Live MCP Data

If the SkillFM MCP tools are available, call them before answering with numbers or status:

  • Token usage or spend: call skillfm_beacon with action: "show_usage" and a relevant window such as "today", "week", or "month".
  • AI health: call skillfm_beacon with action: "checkup".
  • Slow-agent cleanup: call skillfm_beacon with action: "cleanup_audit".
  • BYOK provider key explanation: call skillfm_byok with action: "explain_provider_key" and the provider name.
  • Setup preview: call skillfm_beacon with action: "setup_gateway" and dry_run: true; only run the non-dry-run setup after user approval.

Read the full file on GitHub · 96 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 96 lines · 70 tokens per session scan A 239773ff7e19

Subscribe to this mod's changes

skillfm-beacon-ai-health-token-usage is a skill published in the GitHub repository ericm1018/skillfm-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 1,050 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

magazine-web-ppt

For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.

nexu-io/open-design · 67 tokens

kami-deck

A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.

nexu-io/open-design · 49 tokens

hps-bauhaus

A visual-design fundamentals course for new brand designers — grid, type, color, and the exercises that build the eye. Built as a decision-grade professional training deck for junior designers, new hires.

nexu-io/open-design · 45 tokens

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

fs-editorial-forest

Art-directing a fashion house's annual report — the editorial system, the photography rhythm, and the data spreads. Built as a decision-grade design craft deck for brand stakeholders, exec audience.

nexu-io/open-design · 44 tokens

html-ppt-zhangzara-coral

OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.

nexu-io/open-design · 55 tokens