annual-report-cache

annual-report-cache is a skill for Claude Code, Codex from jokull/icelandic-data. It costs 37 tokens per session (363 once invoked), scanned A, original, MIT.

A command-line tool for fetching Icelandic company annual reports by company ID and year. It returns structured financial, ownership, and board data, using a cache when available.

In plain words
What is it for?
Use it to retrieve annual reports, EBITDA, financial ratios, income statements, balance sheets, cash flows, shareholders, and board members.
Why use it?
It avoids manually running several data-extraction scripts and waiting for reports to be fetched again. Cached reports can be returned quickly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/fetch-annual-report.sh 4612023490.

Good fit Use it to retrieve annual reports, EBITDA, financial ratios, income statements, balance sheets, cash flows, shareholders, and board members.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jokull/icelandic-data
agentmods
npx agentmods add skills/jokull/icelandic-data/annual-report-cache

Made for: Claude Code, Codex.

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.

agentmods badge for annual-report-cache

README.md
[![agentmods](https://agentmods.dev/badge/skills/jokull/icelandic-data/annual-report-cache.svg)](https://agentmods.dev/skills/jokull/icelandic-data/annual-report-cache)
Your own site
<a href="https://agentmods.dev/skills/jokull/icelandic-data/annual-report-cache"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/annual-report-cache.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 363 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00363
Opus 5 $0.00018 $0.00181
Sonnet 5 $0.00007 $0.00073
Haiku 4.5 $0.00004 $0.00036

Measured 8d ago against content hash f1c01d651d86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

annual-report-cache 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 8d 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.

.agents/skills/annual-report-cache/SKILL.md · 43 lines

What it actually says

Annual Report Cache

Always use scripts/fetch-annual-report.sh when fetching annual reports.

This script handles R2 caching transparently — you don't need to manage the cache yourself.

Usage

# Fetch latest year for a kennitala
./scripts/fetch-annual-report.sh 4612023490

# Fetch specific year
./scripts/fetch-annual-report.sh 4612023490 2023

# Fetch multiple years
for year in 2022 2023 2024; do
  ./scripts/fetch-annual-report.sh 4612023490 $year > /tmp/report-$year.json
done

How it works

  1. Checks R2 cache at annual-reports/{kennitala}/{year}.json
  2. If cached (CACHE_HIT) — returns JSON instantly (~100ms)
  3. If not cached (CACHE_MISS) — runs skatturinn.py + financials.py, caches result in R2, returns JSON
  4. Status messages go to stderr, JSON data goes to stdout

Output

Structured JSON with: incomeStatement, balanceSheet, cashFlow, ratios, bankFinancials (if bank), shareholders, boardMembers.

When to use

  • Any query about ársreikningar, EBITDA, financial analysis, company financials
  • Prefer this over running skatturinn.py + financials.py directly
  • The R2 cache has ~2,500 pre-extracted reports for instant access
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.

  1. 8d ago First seen · 43 lines · 37 tokens per session scan A f1c01d651d86

Subscribe to this mod's changes

annual-report-cache is a skill published in the GitHub repository jokull/icelandic-data (52 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 363 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories