finops-feedback

finops-feedback is a command for Claude Code from glassity/agent-skills. It costs 57 tokens per session (1,297 once invoked), scanned A, original, Apache-2.0.

A command for closing a cloud-cost saving opportunity after comparing expected and actual savings.

In plain words
What is it for?
Use it to measure realized savings, calculate the documented Cloud Entropy estimate, mark an opportunity complete, and produce follow-up work.
Why use it?
It prevents a cost-saving task from ending with only a report by recording the result and requiring a new idea or policy update for the next cycle.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Part of the glassity plugin — 19 skills, 6 commands, 2 agents shipped together

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/glassity/agent-skills/finops-feedback
Clone the repo
git clone --depth 1 https://github.com/glassity/agent-skills

Made for: Claude Code.

Or install glassity, the plugin that ships this one along with the rest of its 19 skills, 6 commands, 2 agents.

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 finops-feedback

README.md
[![agentmods](https://agentmods.dev/badge/commands/glassity/agent-skills/finops-feedback.svg)](https://agentmods.dev/commands/glassity/agent-skills/finops-feedback)
Your own site
<a href="https://agentmods.dev/commands/glassity/agent-skills/finops-feedback"><img src="https://agentmods.dev/badge/commands/glassity/agent-skills/finops-feedback.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,297 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 $0.00057 $0.01297
Opus 5 $0.00028 $0.00648
Sonnet 5 $0.00011 $0.00259
Haiku 4.5 $0.00006 $0.00130

Measured 5d ago against content hash 51824e4cf968, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

finops-feedback 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 5d 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/finops-feedback.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/finops-feedback — step 5: Feedback Loop & Celebration

The Cloud Entropy proxy and the double-loop gate live in the glassity-five-steps skill. Both are summarized below.

Purpose

Close the loop. Step 5 has two jobs: feed execution outcomes back so /finops-discover generates better ideas next cycle, and reinforce the practice with explicit recognition. Measure realized against projected savings, compute the labelled Cloud Entropy proxy, close the opportunity, and satisfy the double-loop gate: emit at least one new discovery idea or policy update, not merely a closure report.

The closure path mutates: lifecycle-mark-closure-done registers the report and moves the opportunity to completed, two-phase.

Variables

Variable Source Default Meaning
TARGET first positional arg required The opportunity_… id to close out.

Tool surface

  • CLI: glassity --output=json opp show <id> to re-read, and glassity --output=json opp list for the open-opportunity savings that feed the entropy proxy.
  • Skills: cost-mom-trends for realized savings, cost-summary for the denominator, lifecycle-mark-closure-done to register the report and move the opportunity, two-phase.
  • Helpers: git log for the closure report's commit sha, ls to locate it.
  • Binary check: run command -v glassity before the first CLI call. If it is missing, stop and tell the user to install it with brew install glassity/tap/glassity or from https://github.com/glassity/cli/releases. No account yet? Sign up at app.glassity.cloud.

Instructions

  1. Measure realized against projected. Pull the realized saving from cost-mom-trends — the post-change month-over-month delta for the affected service or account — and compare it to the projected annual figure recorded at assessment. Report realized, projected, and the variance. A large negative variance is a reason to lower confidence on similar future recommendations.

Read the full file on GitHub · 115 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. 5d ago First seen · 115 lines · 57 tokens per session scan A 51824e4cf968

Subscribe to this mod's changes

finops-feedback is a command published in the GitHub repository glassity/agent-skills (2 stars, last pushed 23d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,297 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.