Borrowing it
Nothing to install: this file belongs to Mreaggle/JumpstyleUnitedNations. 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/Mreaggle/JumpstyleUnitedNations/main/AGENTS.mdgit clone --depth 1 https://github.com/Mreaggle/JumpstyleUnitedNationsWrote 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/mreaggle/jumpstyleunitednations/agents-md)<a href="https://agentmods.dev/instructions/mreaggle/jumpstyleunitednations/agents-md"><img src="https://agentmods.dev/badge/instructions/mreaggle/jumpstyleunitednations/agents-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 5.1 | $0.00898 | $0.00898 |
| Opus 5 | $0.00449 | $0.00449 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
JumpstyleUnitedNations AGENTS.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 7d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Operating Guide
This file defines how AI agents and automated contributors must work in the Jumpstyle United Nations repository.
Mission
Preserve global Jumpstyle history with traceable evidence, clear uncertainty and respect for the people whose work created the culture.
Non-negotiable rules
- Never commit private chats, contact exports, private group links, phone numbers or personal data.
- Treat private community conversations only as discovery leads. Promote only information supported by a public source or an explicitly approved first-person record.
- Do not publish legacy placeholders such as
Event or Contribution 1as historical facts. - The global timeline is add-only by default. Do not delete existing events while enriching it. Corrections require an explicit maintainer request and a documented reason.
- Never invent dates. Use the event date in a title or description; otherwise label the upload date as a fallback. An archive snapshot date proves page availability, not necessarily the event date.
- Keep original URLs and add Wayback URLs when a live source is fragile or unavailable.
- Separate fact, community testimony and inference. State uncertainty directly.
- Preserve aliases, diacritics and country context. Do not merge people solely because names look similar.
- Do not reorganize or rename historical paths without checking inbound Markdown links and documenting redirects or replacements.
- Run
npm run checkbefore reporting work complete.
Source hierarchy
Prefer sources in this order:
- Official records: artist, label, chart, event organizer or platform metadata.
- Contemporary journalism or institutional coverage.
- Original video title, description, upload metadata and channel context.
- Archived forums, community portals and calendars.
- First-person testimony with clear attribution and approval.
- Secondary compilations, used only as leads unless independently confirmed.
Evidence workflow
- Search
data/source-registry.jsonand existing timelines for duplicates. - Record the public URL, source type, language, country and access status.
- Determine
event_date,upload_dateandarchive_dateseparately. - Assign an evidence status defined in
docs/EDITORIAL_POLICY.md. - Add the smallest useful timeline entry without rewriting unrelated history.
- Update
data/country-research.jsonwhen a country's maturity changes. - Keep
data/country-catalog.jsoncomplete and runnpm run scaffold:countrieswhen a catalog entry or national path is added. - Update
data/global-event-countries.jsonand runnpm run sync:nationalwhen a Global Timeline event is added or changed. - Keep the public museum synchronized: the site pipeline must consume this
repository's
JumpstyleTimeline/Global/global-timeline.md, derive its event count at build time and fail when its generated copy or manifest differs. Never update the front-end count independently from the canonical timeline. - After a Global Timeline change reaches
main, trigger thejun-timeline-updateddispatch (or manually run the site deploy) inMreaggle/jumpstylebrasiland verify the published full-record count. - Run the repository validator and inspect the diff for accidental deletions.
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.
- 7d ago First seen · 71 lines · 898 tokens per session scan A 4f28072c339b
JumpstyleUnitedNations AGENTS.md is an instructions file published in the GitHub repository Mreaggle/JumpstyleUnitedNations (2 stars, last pushed 28d ago), licensed CC0-1.0. It adds 898 tokens to every session, about $0.0045 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.