A workflow guide for creating, previewing, updating, scheduling, running, and exploring Costory reports.

Use it to prepare cost reports with charts, PDFs, rankings, text, or DIGEST cost-change explanations, and to share them through Slack, Teams, or email.

It keeps report context, widgets, previews, and delivery destinations consistent across report tasks.

reports — Skill for Claude Code by costory-io

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.

Any agent

npx skills add costory-io/costory-finops-mcp-skills --skill reports

Clone the repo

git clone --depth 1 https://github.com/costory-io/costory-finops-mcp-skills

Made for: Claude Code.

Or install costory, the plugin that ships this one along with the rest of its 7 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/costory-io/costory-finops-mcp-skills/reports/github.svg)](https://agentmods.dev/skills/costory-io/costory-finops-mcp-skills/reports)

Your own site

<a href="https://agentmods.dev/skills/costory-io/costory-finops-mcp-skills/reports"><img src="https://agentmods.dev/badge/skills/costory-io/costory-finops-mcp-skills/reports/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/costory-io/costory-finops-mcp-skills/reports"><img src="https://agentmods.dev/badge/skills/costory-io/costory-finops-mcp-skills/reports.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,394 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00136	$0.07394
Opus 5.5	$0.00054	$0.02958
Sonnet 5.5	$0.00027	$0.01479
Haiku 4.5	$0.00014	$0.00739

Measured 18d ago against content hash 06f93c7bd62f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reports 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 18d 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.

plugins/costory/skills/reports/SKILL.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reports

Skill body version 0.5.3. Workflows here are named — Schedule, Explain, Update, Run, Explore. Older bodies lettered them A–E, and other Costory surfaces used a different letter order. If you are holding a lettered routing table for reports, it is stale: route by the names in this body and ignore the letters.

A report has a shared reportContext input (global theme) and widgets that inherit it by default. It delivers those widgets (chart snapshot, PDF, top/flop, text, or DIGEST cost-change tree) to one or more destinations (Slack, Teams, email). Same mental model as dashboards: shared context + per-widget overrides. create_report, update_report, and preview_report_widget all take the same report-level reportContext.

Temporary compatibility: the deprecated top-level context alias is accepted during migration, but always generate reportContext. Never send both.

Load this skill first for any report creation, DIGEST preview, substantial update, or delivery conversation.

Must-follow rules

Everything below this section is detail. These eight are the contract:

Ask before build (Schedule / delivery). Do not pick widgets, call preview_report_widget, or call create_report until the design is confirmed. Never silently default to a graph or an AI summary on Schedule.
Explain exception — preview-first DIGEST. For one-shot "what changed / explain last month" (Explain workflow or explain-period-change recipe), defaulting to DIGEST chat preview is required. Do not wait for a full design questionnaire; do not substitute query + compare for the first answer.
Context-first. Once answers are in, define the full reportContext before listing widgets. Widgets carry only overrides — never duplicate what already lives in reportContext.
Destinations last. Do not call list_available_destinations until the user has named the channel type (Slack / Teams / email). Then list only that type and propose matches by name — never paste a whole channel list into the conversation.
AI features are opt-in. DIGEST-only. Set display: "summary" for the executive narrative and/or enableAiInvestigation: true for per-node deep analysis — both default off (tree-only) and are slower.
Confirm delivery. Both NOW and SCHEDULED need explicit confirmation before create_report. UNSCHEDULED does not.
datePreset, never frozen dates, on SCHEDULED reports.
Cost data is ~2 days late. Prefer a Tuesday weekly send (weekday: 2) when the period is LAST_WEEK (a completed calendar week). If the report must land earlier (e.g. Monday), use TRAILING_7_DAYS instead of LAST_WEEK so the window is not a half-empty calendar week.

Read the full file on GitHub · 464 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.

18d ago Changed · +1 lines 06f93c7bd62f
1mo ago Changed · +9 lines b9f948643b2d
1mo ago First seen · 454 lines · 136 tokens per session scan A 434f9cd89b8f

Subscribe to this mod's changes

reports is a skill published in the GitHub repository costory-io/costory-finops-mcp-skills (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 136 tokens to every session and 7,394 once invoked, about $0.0005 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 2026-08-31.

Analytics and metrics aws cloud-cost finops finops-mcp gcp mcp

notion

Notion workspace integration for searching pages, managing databases, creating postmortems, and exporting RCA findings.

Arvo-AI/aurora · 23 tokens

datadog

Datadog monitoring integration for querying logs, metrics, monitors, events, traces, hosts, and incidents during RCA investigations.

Arvo-AI/aurora · 28 tokens

ovh

OVHcloud infrastructure integration for managing instances, Kubernetes clusters, networks, and object storage via CLI and Terraform.

Arvo-AI/aurora · 24 tokens

scaleway

Scaleway cloud integration for managing instances, Kapsule Kubernetes clusters, object storage, and managed databases via CLI and Terraform.

Arvo-AI/aurora · 29 tokens

postmortem

Postmortem generation and management tools for writing, reading, and versioning incident postmortems.