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 agentmods add instructions/asokore/statcite/claude-mdgit clone --depth 1 https://github.com/asokore/statciteWrote 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/instructions/asokore/statcite/claude-md)<a href="https://agentmods.dev/instructions/asokore/statcite/claude-md"><img src="https://agentmods.dev/badge/instructions/asokore/statcite/claude-md.svg" alt="Measured on agentmods" 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 | $0.02064 | $0.02064 |
| Opus 5 | $0.01032 | $0.01032 |
| Sonnet 5 | $0.00413 | $0.00413 |
| Haiku 4.5 | $0.00206 | $0.00206 |
Grade A, and why
statcite CLAUDE.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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md: StatCite project guide
New to this project? Read BRIEF.md first. It carries the owner's actual goal, the reasoning behind every choice here, what I'd challenge about my own work, ideas considered but not built, and explicit authority to change or replace any of it. This file is the operating manual; BRIEF.md is the mandate.
Also read docs/VENTURE-CONTEXT.md if present (imported 2026-07-26; local-only by design, gitignored, never commit it). It carries owner-sensitive strategic context this repo was built without, including a proposed repricing that contradicts docs/MONETIZATION.md. If it is absent (fresh clone), ask the owner rather than proceeding without it; the public-safe competitive facts from it live in docs/RESEARCH.md §4a.
StatCite is a free remote MCP server + REST API serving official economic statistics where every number carries a full citation, plus a verify_stat claim-checker and its batch form verify_claims. Monorepo: Cloudflare Worker (server/), static site (site/), Apify pay-per-event actor twin (apify/), Claude skill (skill/), distribution kit (distribution/), strategy docs (docs/).
If the task is "take this live" or "deploy": follow HANDOFF.md step by step, but read BRIEF.md §4 and §9 first and decide whether shipping as-is is actually the right move. Growth sequence: docs/LAUNCH.md.
Branch topology and the embargo guard: read before your first push
This repository is public. Local main is not what ships.
maincarries the R2 benchmark RESULTS (bench/runs/R2*), which stay off the public remote until the vendor courtesy-preview window closes.bench/questions/R2*andbench/snapshots/R2*are pre-registered and public by design; onlyruns/is embargoed.public-syncis the branch that actually publishes. It excludesbench/runs/R2*.
Never git push from main. To publish work, put the commit on public-sync and push that:
git checkout public-sync
git cherry-pick <sha> # or: git checkout main -- <safe paths>
git push origin public-sync:main
git checkout main
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.
- 3d ago First seen · 70 lines · 2,064 tokens per session scan A b1c11c3aa1c5
statcite CLAUDE.md is an instructions file published in the GitHub repository asokore/statcite (1 stars, last pushed 5d ago), licensed MIT. It adds 2,064 tokens to every session, about $0.0103 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.
Other instructions, from other repositories
oecd-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/oecd-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
oecd-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/oecd-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
worldbank-mcp-server AGENTS.md
Instructions for cyanheads/worldbank-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
worldbank-mcp-server CLAUDE.md
Instructions for cyanheads/worldbank-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
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).
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).