What is statcite GEMINI.md?

Instructions for StatCite, a read-only service that provides official economic statistics from sources such as the World Bank, IMF, BIS, and ECB with citations. They explain how to retrieve figures, handle projections and revisions, and check claims in a draft.

Use them to find or verify indicators such as inflation, economic growth, government debt, interest rates, and unemployment, and to include the supporting citation.

They help prevent outdated, misattributed, or incorrectly reported economic numbers by requiring verification against official data.

statcite GEMINI.md — Instructions file by asokore

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.

agentmods

npx agentmods add instructions/asokore/statcite/gemini-md

Clone the repo

git clone --depth 1 https://github.com/asokore/statcite

Made for: Gemini CLI.

Per session 554 This file is loaded in full into every session.

When invoked 554 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00554	$0.00554
Opus 5	$0.00277	$0.00277
Sonnet 5	$0.00111	$0.00111
Haiku 4.5	$0.00055	$0.00055

Measured 2d ago against content hash 455e37c65eec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

statcite GEMINI.md 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 2d 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.

GEMINI.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StatCite: verify economic statistics before you state them

StatCite is connected as a remote MCP server. It serves official economic statistics (World Bank WDI, IMF WEO/Fiscal Monitor, BIS policy rates, ECB) where every value carries a full citation, and it verifies claimed figures against the official series. Free, no key, read-only.

The rule

Never state a macroeconomic statistic from memory when StatCite is available. Recalled figures are routinely stale (statistics get revised), attributed to the wrong year, or off by a unit. Fetch it, or verify it.

Writing with economic numbers

get_indicator for the figure (inflation_cpi, gdp_growth, govt_debt_gdp, policy_rate, unemployment_rate, …; country as ISO3 or plain name).
Use the returned value exactly, and carry citation.citation_text into the text or footnote. For bibliographies use citation.export_formats.bibtex or .apa.
Read notes. They flag IMF projections, ILO-modelled definitions, fallback sources, and upstream staleness. If a value is a projection, write "the IMF projects", never "was".

Fact-checking a draft

Extract every claim (indicator + country + period + value) and send them to verify_claims in batches of up to 15. Then act on each verdict:

match, keep it, attach the citation.
close, replace with the official value and cite it.
mismatch. Replace it, and read diagnostics (wrong year, percent-vs- decimal, unit scaling, sign flips). Also check revision_check: if matches_previous_vintage is true, the figure was right when written and has since been revised, say that, rather than implying an error.
cannot_verify, report the reason the tool gives. Do not substitute a number from memory.

When sources disagree

Call compare_sources for the indicator and country. It returns each official source's value with its own citation and the spread. Differences are methodological or vintage differences (general vs central government, calendar vs fiscal year), never one source being "wrong", cite the source whose definition matches the claim.

Read the full file on GitHub · 53 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.

2d ago First seen · 53 lines · 554 tokens per session scan A 455e37c65eec

Subscribe to this mod's changes

statcite GEMINI.md is an instructions file published in the GitHub repository asokore/statcite (1 stars, last pushed 4d ago), licensed MIT. It adds 554 tokens to every session, about $0.0028 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 2026-08-31.

Analytics and metrics Research citations economics fact-checking imf mcp mcp-server

imf-mcp-server AGENTS.md

AGENTS.md instructions for cyanheads/imf-mcp-server, covering developer protocol, server overview, core rules, patterns and tool (with canvas spill).

cyanheads/imf-mcp-server · 6,545 tokens

imf-mcp-server CLAUDE.md

Claude Code instructions for cyanheads/imf-mcp-server, covering developer protocol, server overview, core rules, patterns and tool (with canvas spill).

cyanheads/imf-mcp-server · 6,545 tokens

ausecon-mcp-server CLAUDE.md

Instructions for AnthonyPuggs/ausecon-mcp-server, covering claude.md, commands, install dependencies, run all tests and run a single test file.

AnthonyPuggs/ausecon-mcp-server · 1,383 tokens

legwork-skill AGENTS.md

Instructions for dbhq-uk/legwork-skill, covering agents.md, what this is, layout, conventions and validating a change.

dbhq-uk/legwork-skill · 1,582 tokens

sourceright AGENTS.md

AGENTS.md instructions for edithatogo/sourceright, covering sourceright codex instructions, codev - ai agent instructions, project overview, available protocols and file resolution (how codev finds protocols and templates).

edithatogo/sourceright · 2,484 tokens

bobs-big-brain-plugin CLAUDE.md

Instructions for jeremylongshore/bobs-big-brain-plugin: Agent + developer guidance for this repo lives in AGENTS.md — the single source of truth (what it is, the local|team dual-mode dispatch, govern.ts / seed-policy.ts, the team-mode server contract, build + smokes, the tenant-default gotcha, retrieval roadmap…

jeremylongshore/bobs-big-brain-plugin · 295 tokens