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.
git clone --depth 1 https://github.com/jokull/icelandic-datanpx agentmods add skills/jokull/icelandic-data/annual-report-cacheWrote 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/jokull/icelandic-data/annual-report-cache)<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>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00363 |
| Opus 5 | $0.00018 | $0.00181 |
| Sonnet 5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00036 |
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.
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
- Checks R2 cache at
annual-reports/{kennitala}/{year}.json - If cached (CACHE_HIT) — returns JSON instantly (~100ms)
- If not cached (CACHE_MISS) — runs skatturinn.py + financials.py, caches result in R2, returns JSON
- 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
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.
- 8d ago First seen · 43 lines · 37 tokens per session scan A f1c01d651d86
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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.