Borrowing it
Nothing to install: this file belongs to jxsuite/jx. 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/jxsuite/jx/main/AGENTS.mdgit clone --depth 1 https://github.com/jxsuite/jxWrote 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/jxsuite/jx/agents-md)<a href="https://agentmods.dev/instructions/jxsuite/jx/agents-md"><img src="https://agentmods.dev/badge/instructions/jxsuite/jx/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/jxsuite/jx/agents-md"><img src="https://agentmods.dev/badge/instructions/jxsuite/jx/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.07239 | $0.07239 |
| Opus 5.5 | $0.02896 | $0.02896 |
| Sonnet 5.5 | $0.01448 | $0.01448 |
| Haiku 4.5 | $0.00724 | $0.00724 |
Grade A, and why
jx 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 9d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jx Monorepo — Agent Notes
We're crafting a comprehensive web-based application suite that aims to encompass all available web platform APIs within a JSON Schema and provides a runtime, compiler, visual builder, and extension layer (content collections, search, authentication, database connectors) to facilitate website and full-application builds with this schema. Jx targets apps with accounts and data, not only brochure sites: pages are always prerendered at build time and hydrate as islands, while sessions and application data come from extension server mounts which — together with any timing: "server" state entries — compile into one generated Hono worker serving /_jx/* next to the static output whenever build.adapter is set. A project with an active mount (a non-empty data or auth section) must set one, or the build fails; with no adapter, timing: "server" entries fall back to a standalone per-page _server.js handler.
- Prefer WHATWG and ECMA standard alignment (current or emerging) for all nomenclature and architectural paradigms.
- Code in strongly typed Typescript. Ensure all linting, typechecking, and tests pass following all changes.
- Implement tests in parallel with features—use native Bun + Happy DOM and other mock API providers, as appropriate.
- Reference the general and package-specific specs (./specs) prior to planning and implementing features, update specs to reflect user requests prior to adding new features. Edit spec sections in place — never renumber headings (user docs anchor them).
- Every substantive spec edit is a release, user docs (
./docs) track shipped behavior in the same change set, and plans live inplans/and are deleted when they land. "Specs & User-Documentation Policy" below has the commands and the gates; runbun run docs:syncandbun run docs:checkbefore finishing. - Do not wrap Markdown source: write one paragraph per line, and make a line break that carries meaning an explicit
\hard break.bun run format:mdfixes a file. Much of the tree is still wrapped from before the rule and the sweep is pending, so match the rule in what you write rather than reflowing what you touch. The full rule, and why it is not enforced yet, is inscripts/AGENTS.md. - Use Chrome MCP to test new UI/UX changes prior to finishing the task.
- These notes are harness-neutral. Every
CLAUDE.mdis a one-line@AGENTS.mdimport of the file beside it, so Claude Code loads these notes; edit theAGENTS.md, never the stub. Claude Code additionally runs the hooks in.claude/hooks(edit validation, a Bash guard, and a docs-sync check when it stops); in any other harness, runbun run docs:syncand format what you touched withoxfmtbefore finishing.
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.
- 9d ago Changed · +106 lines · +6,070 tokens per session 2cc9225b718f
- 11d ago First seen · 29 lines · 1,169 tokens per session scan A dd1f11525957
jx AGENTS.md is an instructions file published in the GitHub repository jxsuite/jx (7 stars, last pushed 2d ago), licensed MIT. It adds 7,239 tokens to every session, about $0.0290 per session on Opus 5.5. 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 2026-10-02.
Other instructions, from other repositories
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, cache eligibility and rollout and applying the notice (cutover).
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.
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
generative-ai-for-beginners AGENTS.md
AGENTS.md instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.