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 skills add costory-io/costory-finops-mcp-skills --skill costory-finopsgit clone --depth 1 https://github.com/costory-io/costory-finops-mcp-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/skills/costory-io/costory-finops-mcp-skills/costory-finops)<a href="https://agentmods.dev/skills/costory-io/costory-finops-mcp-skills/costory-finops"><img src="https://agentmods.dev/badge/skills/costory-io/costory-finops-mcp-skills/costory-finops/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/costory-io/costory-finops-mcp-skills/costory-finops"><img src="https://agentmods.dev/badge/skills/costory-io/costory-finops-mcp-skills/costory-finops.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00091 | $0.01755 |
| Opus 5.5 | $0.00036 | $0.00702 |
| Sonnet 5.5 | $0.00018 | $0.00351 |
| Haiku 4.5 | $0.00009 | $0.00176 |
Grade A, and why
costory-finops 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 today.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Costory FinOps Agent
Overview
Costory is the cost-data layer for a FinOps agent. It ingests and normalizes billing from AWS, GCP, Azure,
Snowflake, Datadog, OpenAI and Anthropic, allocates it to teams, products, environments and features, and exposes it
through the hosted Costory MCP server (costory in this power). Use it to investigate, explain and allocate spend
with structured tool calls instead of raw billing lines.
This skill is the condensed playbook. The detailed workflows (payload formats, edge cases) are served by the MCP
itself: call get_skill with one of these skillId values before non-trivial work.
skillId |
Load it before |
|---|---|
query |
any non-trivial query call: scope vs split, period comparison, unit economics, budgets |
cost-change-investigation |
explaining what changed, when, and why |
virtual-dimensions |
create_virtual_dimension_draft, update_virtual_dimension_draft, publish_virtual_dimension |
dashboards |
create_dashboard, update_dashboard |
reports |
create_report, preview_report_widget (DIGEST), run_report_now |
bigquery |
BigQuery warehouse questions (on-demand vs slots, physical vs logical storage, labels) |
recipes |
the user states an outcome ("tag coverage", "cost per namespace", "EC2 spike alert") rather than a tool |
Prerequisites
- A Costory workspace with billing data connected (a 30-day trial is available at https://www.costory.io).
- On first use, the MCP client opens a browser window for the OAuth login. No IAM keys, Docker or local server.
- If tools fail with an authentication error, ask the user to reconnect the
costoryMCP server and log in again.
Step 1: Load context (always first)
Call get_context at the start of every conversation. It returns the dimensions, popular group-bys, dashboards
and the workspace currency. Never invent dimension or CEL field names; take them from get_context or search.
Several organizations: if get_context returns "Multiple organizations" with a list of slugs, do not pick one.
Ask the user which org to use (from that list, or call list_organizations), then pass that slug to
get_context and to every following tool call. If the user already named the org (e.g. "Use Costory org acme"),
use that slug directly.
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.
- today Changed 6ddfb41e4cf3
- 4d ago Changed c1129ce2837b
- 6d ago First seen · 104 lines · 91 tokens per session scan A 812a626f070d
costory-finops is a skill published in the GitHub repository costory-io/costory-finops-mcp-skills (2 stars, last pushed today), licensed Apache-2.0. It adds 91 tokens to every session and 1,755 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-10.
Other skills, from other repositories
finops-expert
Expert-level cloud financial operations, cost optimization, and cloud economics. Use when the user mentions cloud cost, optimization, cloud economics, or AWS cost, or when the task involves FinOps Fundamentals, Cost Management, FinOps Practices, or Cost Visibility.
finfocus-budget
Configure, check, and troubleshoot FinFocus budget thresholds. Use when setting cost.budgets in config.hujson, reading budget health, filtering scopes with --budget-scope, or making cost projected, cost actual, or overview exit non-zero in CI. Triggers on: "finfocus budget", "budget threshold", "exit-on-threshold"…
finfocus-plugin-dev
Implement and maintain a FinFocus cost plugin in a repository scaffolded by finfocus plugin init. Use when adding or changing pricing logic in a plugin, adding a resource type, writing the Supports handler, returning GetProjectedCost or GetActualCost results, testing a plugin locally against a Pulumi plan, or…
gcp-dispute-kit
Use to assemble a dispute-grade evidence packet and ready-to-file letters after GCP API-key fraud (leaked-key abuse, runaway Gemini/Vertex charges). READ-ONLY — mutates nothing. Triggers on "dispute gcp charges", "google cloud fraud refund", "gemini api fraud dispute", "gcp billing dispute", "chargeback google cloud".
gcp-spend-cap-setup
Use to set up Google Cloud hard spend caps (Public Preview, July 2026) with guided discovery, sizing, and post-creation verification. Spend caps are console-only — this skill prepares everything, walks you through the one manual step, and verifies the result. GUIDED — runs only read-only commands. Triggers on "set up…
gcp-cost-anomaly-scan
Use to detect whether any GCP project has experienced an abnormal spend spike in the recent past, indicating possible API-key abuse or compromised credentials. READ-ONLY. Use standalone or as Phase 1b of gcp-ironclad.