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.
npx agentmods add commands/glassity/agent-skills/finops-aligngit 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-align)<a href="https://agentmods.dev/commands/glassity/agent-skills/finops-align"><img src="https://agentmods.dev/badge/commands/glassity/agent-skills/finops-align.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 | $0.00075 | $0.02190 |
| Opus 5 | $0.00037 | $0.01095 |
| Sonnet 5 | $0.00015 | $0.00438 |
| Haiku 4.5 | $0.00007 | $0.00219 |
Grade A, and why
finops-align 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 4d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/finops-align — step 3: Stakeholder & Planning Alignment
The Definition-of-Ready checklist and the lifecycle vocabulary live in the
glassity-five-stepsskill. The three-point checklist is repeated below.
Purpose
Convert a scored opportunity into owned, contextualized, executable work. Alignment has two sub-phases with two different audiences, and this command routes between them:
- Opportunity level (
alignment_step_1), the FinOps leader. Produce the organization-wide execution plan, triage out assignments that do not apply, and approve — which synthesizes a per-service brief into every remaining assignment and advances them. Path A below. - Assignment level (
alignment_step_2), the service owner. Refine the per-service brief, name the single accountable owner, and advance to execution behind the Definition-of-Ready gate. Path B below.
This command mutates, through lifecycle-approve-plan (Path A) or
lifecycle-accept-plan (Path B). Every mutation goes through the binary's
two-phase confirmation.
Variables
| Variable | Source | Default | Meaning |
|---|---|---|---|
TARGET |
first positional arg | required | The opportunity id (Path A) or the assignment id (Path B). |
OWNER |
--owner |
ask | Path B only. The single accountable owner. Ask if it is not supplied — diffuse ownership is how work becomes an orphan ticket. |
PERSONA |
--persona |
both | Path B only. Plan framing: cfo for a savings floor with confidence intervals, devops for headroom and rollback latency. |
Tool surface
- CLI:
glassity --output=json opp show <opp-id>for Path A's authoritative re-read. Path B's re-read is owned bylifecycle-accept-plan. Note thatopp showresolves opportunity ids only — an assignment id needsopp show-assignment. - Path A mutation: the
lifecycle-approve-planskill. It confirms the org plan atplans/<date>-<slug>-plan.mdis committed, then runsopp approvetwo-phase. - Path B mutation: the
lifecycle-accept-planskill. It locatesplan/<date>-<slug>-<service>.md, registers the artifact, and transitions the assignment — two-phase each. - Path A triage:
glassity opp transition <assignment-id> --target-state archiveddrops accounts and services that need no work before approving. - Helpers:
gitto commit a plan and read a file's commit sha,lsto locate plan files. - Subagent (optional): delegate deep per-opportunity investigation to
opportunity-triagethroughTaskwhen the plan needs heavy reasoning. - 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.
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.
- 4d ago First seen · 176 lines · 75 tokens per session scan A a71b22473918
finops-align is a command published in the GitHub repository glassity/agent-skills (2 stars, last pushed 22d ago), licensed Apache-2.0. It adds 75 tokens to every session and 2,190 once invoked, about $0.0004 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.