Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Cocometer

ASecurity

CocoMeter chargeback and FinOps governance. Usage: $meter chargeback refresh | $meter chargeback invoice | $meter chargeback onboarding

724 stars
0 votes
0 copies
2 views
Added 9/5/2026
ai-agentsgosql

Works with

cli

Security Analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned 9/5/2026

$npx -y skills add Snowflake-Labs/cocoplus --skill cocometer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cocometer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Cocometer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/snowflake-labs-cocometer-ca8f0b71/badge)](https://www.skillsdirectory.com/skills/snowflake-labs-cocometer-ca8f0b71)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
archetype-classifier.skill.md
---
name: "meter-chargeback"
description: "CocoMeter chargeback and FinOps governance. Usage: $meter chargeback refresh | $meter chargeback invoice | $meter chargeback onboarding"
version: "1.2.0"
author: "CocoPlus"
tags:
  - cocoplus
  - cocometer
  - chargeback
  - finops
user-invocable: true
---

# CocoMeter Chargeback

Use this skill for `$meter chargeback refresh`, `$meter chargeback invoice`, and `$meter chargeback onboarding`.

Before proceeding, verify that `.cocoplus/` exists. If not, output: "CocoPlus not initialized. Run `$pod init` first." Then stop.

## Source Rules

CocoMeter chargeback reads token/inference usage from Snowflake's Cortex Code usage history surfaces and, when enabled, warehouse compute from query attribution history. Treat the chargeback fact table as governance evidence, not a cosmetic dashboard:

- Token credits come from the Cortex Code CLI, Desktop, and Snowsight usage history surfaces.
- Warehouse credits join through `query_tag.app` and `QUERY_ATTRIBUTION_HISTORY.CREDITS_ATTRIBUTED_COMPUTE`.
- `includeWarehouse` in `cocoplus.toml` controls whether warehouse credits are included.
- `SNOWFLAKE.LOCAL.AI_OBSERVABILITY_EVENTS` `CodingAgent.Step-0` spans are used for near-real-time observability when present.
- Exclude `SYSTEM`, sandbox runs, and background metadata-query traffic.

## `$meter chargeback refresh`

Run a 35-day trailing delete/insert refresh. On first setup, load 60 days. Schedule the Snowflake task for 06:00 UTC daily.

For local validation or dry-run fixtures, use:

```text
invoke cocometer/chargeback-refresh --input <fixture.json>
```

The applies the same deterministic rules used by the warehouse implementation:

- Strip `<system-reminder>...</system-reminder>` blocks before prompt persistence.
- Extract SQL from tool argument arrays.
- Resolve cost centers in this order: explicit user map, user object tag, role map, `UNMAPPED`.
- Produce invoice-ready per-user totals.

## `$meter chargeback invoice`

Generate one HTML and one CSV invoice package per user from the refreshed chargeback facts. Each invoice must include token credits, warehouse credits when included, total credits, credit-rate amount, cost center, and unmapped status.

## `$meter chargeback onboarding`

Report setup readiness:

- `schemaReady`
- `factHasData`
- `costCentersMapped`
- `unmappedUsers`
- `spansPresent`

Block any "chargeback ready" claim until the checklist is green or the remaining gaps are explicitly listed.

## Anti-Rationalization

| Shortcut | Why It Fails |
|----------|--------------|
| Bill every warehouse query by user only | Query attribution must be tied back through Coco usage context; otherwise unrelated Snowflake work is charged to CocoPlus |
| Keep system reminders in prompts | System reminders are infrastructure text, not billable user intent |
| Auto-map unknown users | `UNMAPPED` is deliberate governance signal, not an error to hide |
| Ignore missing spans | Chargeback can still run, but near-real-time observability is not ready |

## Exit Criteria

- [ ] Refresh excludes SYSTEM, sandbox, and background metadata records
- [ ] Cost center resolution uses all four levels
- [ ] Invoice output includes token and optional warehouse credits
- [ ] Onboarding checklist reports unmapped users and span presence

Attribution

Snowflake-LabsSnowflake-Labs
View sourceSee grades on GitHubMore from Snowflake-Labs →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →