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/joske/yserver/agents-mdgit clone --depth 1 https://github.com/joske/yserverWhat 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 | $0.00450 | $0.00450 |
| Opus 5 | $0.00225 | $0.00225 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
yserver 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 today.
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.
What it actually says
yserver
A modern X11 server written from scratch in Rust.
Info about the project is in README.md Current status is in docs/status.md and should be kept up to date focus is on yserver (KMS) now
Instructions
- it's fine not to use clippy pedantic in this repo but DO use regular clippy
- before committing, run clippy exactly as CI does:
cargo clippy --all-targets -- -D warnings. CI fails on any warning, and--all-targetslints test code too — a crate-scoped or non---all-targetsrun misses lints in tests (e.g. needless_range_loop) and they only surface on GH. - use
cargo +nightly fmtfor formatting - when adding or changing ioctls, watch for libc linuxisms: request-type aliases like
libc::Ioctlare not portable across all supported targets, and musl/FreeBSD have regressed here before. Keep ioctl request typing/buildability valid on Linux glibc, Linux musl, and FreeBSD. - design docs (specs) go in docs/superpowers/specs
- impl plans go in docs/superpowers/plans
- work on feature branch for phases
- squash merge when ready (ask confirmation)
- Spec compliance is the goal, but if Xorg deviates from spec (unlikely), we need to follow Xorg, clients are tested for 40+ years on Xorg.
environment
- you are most likely running in a bwrap sandbox, if you see /home/jos/realhome, you are.
- the project dir is rw mounted
- in /home/jos/Projects/xserver/hw/kdrive/ephyr/ you can find the source to Xephyr for reference
- in /home/jos/Projects/xserver/hw/xnest/ you can find the sources to Xnest for reference
- to test you can run ynest with RUST_LOG=debug, capture its output
- x11trace is available if you want to trace how Xephyr/Xnest does things, x11trace always needs -n flag
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.
- today First seen · 29 lines · 450 tokens per session scan A 301853b5c533
yserver AGENTS.md is an instructions file published in the GitHub repository joske/yserver (551 stars, last pushed yesterday), licensed MIT. It adds 450 tokens to every session, about $0.0022 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 2026-09-01.
Other instructions, from other repositories
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.
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.