agentmods.dev

costguard-live

costguard-live is a command for Claude Code from mbanderas/costguard. It costs 43 tokens per session (512 once invoked), scanned A, original, MIT.

A command for checking registered workspaces for wasted CI minutes, scheduled-job time, and selected cloud billing costs. CI is automated building and testing; scheduled jobs are tasks that run at set times.

In plain words
What is it for?
Use it to audit one workspace or all workspaces, limit checks to CI or scheduled jobs, add supported read-only provider billing checks, and produce Markdown or JSON reports.
Why use it?
It identifies recurring infrastructure costs and estimates the monthly waste, so teams can focus on the most expensive findings.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the costguard plugin — 1 skill, 4 commands, 1 MCP server shipped together

not rated 2 3d ago A scan 43 tokens original MIT
View the source file mbanderas/costguard
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.

agentmods
npx agentmods add commands/mbanderas/costguard/costguard-live
Clone the repo
git clone --depth 1 https://github.com/mbanderas/costguard

Made for: Claude Code.

Or install costguard, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 1 MCP server.

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 costguard-live

README.md
[![agentmods](https://agentmods.dev/badge/commands/mbanderas/costguard/costguard-live.svg)](https://agentmods.dev/commands/mbanderas/costguard/costguard-live)
Your own site
<a href="https://agentmods.dev/commands/mbanderas/costguard/costguard-live"><img src="https://agentmods.dev/badge/commands/mbanderas/costguard/costguard-live.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 512 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.00512
Opus 5 $0.00022 $0.00256
Sonnet 5 $0.00009 $0.00102
Haiku 4.5 $0.00004 $0.00051

Measured 6d ago against content hash d8858e06f491, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

costguard-live 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 6d 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.

commands/costguard-live.md · 40 lines

What it actually says

Run a Costguard live billing check for a provider. Requested: $ARGUMENTS

Live mode is opt-in and consent-gated. costguard only PLANS the read (it emits a read-only snippet) and INGESTS the result; the browser action is performed by the playwriter MCP server, authorized by the user. costguard never drives the browser, never submits forms or credentials, and never reads cookies, storage, or screenshots — only rendered billing figures.

Steps (via the costguard MCP server's tools):

  1. Call plan_live_checks with the provider (no confirmLive yet). Surface the returned consentNotice to the user and report the apiFirst decision.
    • If apiFirst is true, STOP and prefer /costguard-audit <ws> --providers <provider> (the API path) — no browser is needed.
  2. Only after the user explicitly agrees (e.g. they passed --confirm), call plan_live_checks again with confirmLive:true to obtain the read-only readOnlySnippet + billingUrl + parseSpec.
  3. Ask the playwriter MCP server to execute that snippet over the user's logged-in session (this is playwriter's own consent gate). It returns the rendered figures.
  4. Call ingest_live_reading with the provider and the returned values to get a Finding. If playwriter is unavailable or the figure is unparseable, ingest returns a kind:"diagnostic" Finding (excluded from cost totals) — the audit never blocks.

Notes:

  • Three consent gates apply: host MCP consent, costguard's confirmLive:true, and playwriter's own consent before execute.
  • A provider with a resolvable API token is API-first — browser is the fallback, never the primary path.
  • This command needs the costguard MCP server (declared in .claude-plugin/.mcp.json) and the playwriter MCP server both connected.
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. 6d ago First seen · 40 lines · 43 tokens per session scan A d8858e06f491

Subscribe to this mod's changes

costguard-live is a command published in the GitHub repository mbanderas/costguard (2 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 512 once invoked, about $0.0002 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.

Analytics and metricsCost OptimizationFinance and fintechciclaude-codecloud-costdeveloper-toolsfinops
Related

Other commands, from other repositories

cost-report

Generate a local Claude Code cost report from the ECC cost-tracker metrics log.

affaan-m/ECC · 16 tokens

sap-fi-closing

SAP FI 월결산/연결산 체크리스트를 단계별로 실행. 환경 확인 → OB52 기간 전환 → GR/IR 청소 → 외화평가 → 자산 감가상각 → 결산 전표 생성 → 재무제표 검증 순서로 진행.

BoxLogoDev/sapstack · 0 tokens

sap-payment-run-debug

F110 지급실행(Payment Run) 에러를 단계별로 진단. 벤더 마스터 → 지급방법 → 하우스뱅크 → 은행결정 → DME 순서로 탐색. 한국 ACH 연동 특화.

BoxLogoDev/sapstack · 55 tokens

wizard

Create, manage, and run guided multi-step wizards.

Smart-AI-Memory/attune-ai · 13 tokens

attune

AI-powered developer workflows with Socratic discovery.

Smart-AI-Memory/attune-ai · 12 tokens

brainstorm

Guided brainstorming with structured discovery and plan output.

Smart-AI-Memory/attune-ai · 12 tokens