finops-execute

finops-execute is a command for coding agents from glassity/agent-skills. It costs 62 tokens per session (1,722 once invoked), scanned A, original, Apache-2.0.

A command for carrying out an approved FinOps plan and recording a deployed change, its verified result, and a proven rollback. The automation level ranges from manual work to autonomous CI/CD, with the level chosen for each opportunity.

In plain words
What is it for?
Use it to execute an assignment or opportunity at level L1, L2, L3, or L4, verify the deployment, prove rollback, and record related pull-request or change artifacts.
Why use it?
It turns a ready plan into a controlled change and ensures the result is checked before the feedback stage can close the loop. Two-phase confirmation is required for every write.

Command

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

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-execute

README.md
[![agentmods](https://agentmods.dev/badge/commands/glassity/agent-skills/finops-execute.svg)](https://agentmods.dev/commands/glassity/agent-skills/finops-execute)
Your own site
<a href="https://agentmods.dev/commands/glassity/agent-skills/finops-execute"><img src="https://agentmods.dev/badge/commands/glassity/agent-skills/finops-execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,722 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 $0.00062 $0.01722
Opus 5 $0.00031 $0.00861
Sonnet 5 $0.00012 $0.00344
Haiku 4.5 $0.00006 $0.00172

Measured 3d ago against content hash 71985a18e8cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

finops-execute 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 3d 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-execute.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/finops-execute — step 4: Execution

The automation dial and the level prompt live in the glassity-five-steps skill. Both are summarized below.

Purpose

Turn a Definition-of-Ready plan into a deployed, verified change. Friction is the dominant variable, so the command meets the team where it is by running at one of four automation levels, chosen per opportunity because risk differs idea to idea. Apply the verification gate: the change is deployed, its effect verified, and the rollback proven, before /finops-feedback can close the loop.

Every write goes through the binary's two-phase confirmation.

Variables

Variable Source Default Meaning
TARGET first positional arg required The assignment id to execute, or an opportunity id when run at opportunity scope.
LEVEL asked per opportunity none L1, L2, L3, or L4. No default and no global flag — the human chooses each time.

Tool surface

  • CLI: glassity --output=json opp show-assignment <id> or opp show <id> to re-read state, opp transition and opp register-assignment-artifact to record the change, pr register to record a pull request. At close, the lifecycle-mark-pr-merged skill, whose transition the server accepts only once it has verified the merge.
  • L2: Write, to generate an infrastructure diff or script the human runs.
  • L3: git and gh, to branch, apply the change, and open a pull request.
  • git log supplies the commit sha that artifact registration pins, at every level.
  • 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. First action: ask which automation level. Never assume one. Present the four choices with a recommendation keyed to the idea type:

Read the full file on GitHub · 139 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. 3d ago First seen · 139 lines · 62 tokens per session scan A 71985a18e8cd

Subscribe to this mod's changes

finops-execute is a command published in the GitHub repository glassity/agent-skills (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,722 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.