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.
git clone --depth 1 https://github.com/glassity/agent-skillsWrote 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.
[](https://agentmods.dev/commands/glassity/agent-skills/finops-status)<a href="https://agentmods.dev/commands/glassity/agent-skills/finops-status"><img src="https://agentmods.dev/badge/commands/glassity/agent-skills/finops-status.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.01121 |
| Opus 5 | $0.00032 | $0.00561 |
| Sonnet 5 | $0.00013 | $0.00224 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
finops-status 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/finops-status — where am I, and what unlocks next
A utility command, not one of the five steps. The lifecycle vocabulary and the stage-to-command mapping live in the
glassity-five-stepsskill.
Purpose
Orient the user when a record has no active stage. current_stage is
nullable, and a null value is a legitimate part of the lifecycle rather than an
error:
- an opportunity while it is in
discoveryorexecution— the work is happening inside its assignments, - an assignment whose organization-wide plan has not been approved and seeded yet,
- a rejected or archived assignment, which is terminal by design.
This command is read-only. It mutates nothing and recommends exactly one next action.
Variables
| Variable | Source | Default | Meaning |
|---|---|---|---|
TARGET |
first positional arg | ask | The record to orient on. |
Tool surface
- CLI, the authoritative state:
glassity --output=json opp show <opp-id>for an opportunity,opp show-assignment <assignment-id>for an assignment. These return the server'sstateandcurrent_stage. - Workspace environment, optional: a managed Glassity workspace exports the
primary record's id as
GLASSITY_ISLAND_ID. It only identifies the record — stages and states always come from the CLI re-read, never from the environment. - No mutation verbs. If the user asks to advance or approve from here, point them at the right step command rather than running it.
- Binary check: run
command -v glassitybefore the first CLI call. If it is missing, stop and tell the user to install it withbrew install glassity/tap/glassityor from https://github.com/glassity/cli/releases. No account yet? Sign up at app.glassity.cloud.
Workflow
-
Binary check; stop with the install hint if it is missing.
-
Resolve the record.
- Use
TARGETwhen the user gave one. Route on the prefix, testing the longer one first: an id beginning withopportunity_assignment_is an assignment; an id beginning withopportunity_is an opportunity. (A bareopportunity_test matches assignment ids too — order matters.) - Managed workspaces export the primary record's id as
GLASSITY_ISLAND_ID; when it is set and noTARGETwas given, use it, routed by the same prefix rule (opportunity_assignment_first). - If neither is set, ask the user which record they mean, offering
glassity --output=json opp listto pick from. Never stop merely because the environment does not identify a record.
- Use
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.
- 7d ago First seen · 100 lines · 64 tokens per session scan A 54a6d1b497bb
finops-status is a command published in the GitHub repository glassity/agent-skills (2 stars, last pushed 25d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,121 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.
Other commands, from other repositories
cost-optimize
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, GCP, and OCI. Where provider-specific code appears below, adapt…
finops
Create FinOps strategy with cloud cost management, optimization, governance, and forecasting.
azure-cost
Azure cost and pricing analysis for a subscription — Advisor cost recommendations, retail pricing lookups, and quota-driven right-sizing signals, scoped to one subscription.
estimate-cost
Estimate AWS costs for planned infrastructure or analyze current spending.
estimate-gcp-cost
Estimate GCP resource costs and provide optimization recommendations.
cost-optimize
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, and GCP.