Borrowing it
Nothing to install: this file belongs to swoopeagle/standardgraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/swoopeagle/standardgraph/main/.claude/commands/add-country.mdgit clone --depth 1 https://github.com/swoopeagle/standardgraphWrote 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/commands/swoopeagle/standardgraph/add-country)<a href="https://agentmods.dev/commands/swoopeagle/standardgraph/add-country"><img src="https://agentmods.dev/badge/commands/swoopeagle/standardgraph/add-country.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 5.1 | $0.00000 | $0.02510 |
| Opus 5 | $0.00000 | $0.01255 |
| Sonnet 5 | $0.00000 | $0.00502 |
| Haiku 4.5 | $0.00000 | $0.00251 |
Grade A, and why
add-country scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0"})` + How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a new country's curriculum (or extend/fix an existing one) to StandardGraph. This is the battle-tested playbook from the 2026-07 Africa expansion (10 new systems, 3 extended, 5,814+ new standards) — follow it instead of re-deriving the approach from scratch.
The single highest-leverage decision in that session: do extraction with Claude/subagents
directly, not local Ollama models (gemma4, qwen). Local models got fooled by corrupted fonts,
rotated/reversed text, and multi-column tables — Claude subagents caught and fixed all of these
autonomously (one installed Tesseract OCR mid-task on CID-encoded garbage; another
reverse-engineered a custom font substitution cipher; another caught a mislabeled source URL by
actually reading the page). Reserve the Ollama fleet for what it's actually good at:
nomic-embed-text embeddings, which are mechanical and don't need judgment. Only fall back to
the fleet for extraction if the user explicitly asks for it.
Phase 1 — Research
- Identify the country's official curriculum body (ministry of education / curriculum development center / examinations council).
- Find real PDF URLs for the target subject/grade-bands via WebSearch. Before trusting a URL, WebFetch it and read page 1 to confirm it's actually the claimed subject — a government site mislabeling its own links is common. (Nigeria's given "math" URL turned out to be the National Values Curriculum — caught only by reading the extracted text.)
- Work out grade-band coverage (primary/secondary/A-level etc.) and map it to this project's
convention: grades are plain strings
"1"–"9","K"for kindergarten/reception/Grade R,"HS"for any 10-12/A-level/upper-secondary content. Only setgrade_band="9-12"whengrade="HS"— every other grade getsgrade_band=NULL. - Pick a system code: lowercase, hyphenated, country-prefixed (
na-nied,ke-kicd,zw-zimsec). Check it doesn't collide:sqlite3 ~/.standardgraph/common_core.db "SELECT DISTINCT system FROM standards WHERE system LIKE '<prefix>%';" - Crosswalk hub: currently only math→
ccssis wired for new systems. Science/ELA/social studies extractions are fine to add but won't get a crosswalk pass unless you extendcrosswalk_engine/nlp_pass.py's hub logic first.
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 · 185 lines · 0 tokens per session scan A 45c4a987cc4f
add-country is a command published in the GitHub repository swoopeagle/standardgraph (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,510 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
start-10-2.es
Lección 10-2: Integración de GAS con Google Calendar!
start-10-2
A lesson on connecting Google Apps Script with Google Calendar, an online calendar service.
start-10-3.en
Lesson 10-3: GAS and Google Sheets Integration!
start-10-3.es
Lección 10-3: Integración de GAS con Google Sheets!
start-10-3
A guided lesson on connecting Google Apps Script with Google Sheets, Google's online spreadsheet application.
start-13-5.es
Bienvenido a Lección 13-5: Despliegue en Vercel.