Borrowing it
Nothing to install: this file belongs to iashutoshtiwari/qwarp. 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/iashutoshtiwari/qwarp/master/AGENTS.mdgit clone --depth 1 https://github.com/iashutoshtiwari/qwarpWrote 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/iashutoshtiwari/qwarp/agents-md)<a href="https://agentmods.dev/instructions/iashutoshtiwari/qwarp/agents-md"><img src="https://agentmods.dev/badge/instructions/iashutoshtiwari/qwarp/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 | $0.02083 | $0.02083 |
| Opus 5 | $0.01042 | $0.01042 |
| Sonnet 5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
qwarp 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 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.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the repository-wide guide for coding agents working on QWarp. It applies to the whole tree.
Agent handoff
These instructions are the shared operating contract for every LLM or coding agent that works on QWarp. Agent-specific defaults must not override them.
At the beginning of each task, read this file, inspect git status, confirm the
current branch and upstream, and review the relevant code and recent history
before editing. Do not assume the checkout is clean, discard unrelated changes,
expose local credentials, or reuse a release attestation for a different
commit.
The handoff baseline is:
v0.9.1/ Arch0.9.1-1is already published from merge commit06ad02ead0543b709eba4feed8111aefb4b0f3ec. Published tags and release assets are immutable.- The AUR
qwarppackage depends on the separately installedcloudflare-warp-binpackage and owns no Cloudflare binaries or services. - Cloudflare WARP 2026.6 and 2026.7 compatibility includes
Missing registration,WarpProxy on port ..., resolver-based Families values, typed current and legacy settings keys, and per-command--accept-toshandling. Preserve these variants and the existing registration during Terms acceptance. - GitHub release and AUR credentials live only in the protected GitHub
releaseenvironment. Never copy them into the checkout, print them, or use them outside an explicitly authorized release.
Use the repository qwarp skill for features, fixes, GitHub issues, and
releases intended for the next release. Work with one main agent by default;
do not create permanent role agents. A temporary read-only subagent is allowed
only for genuinely independent investigations that would otherwise add
substantial noisy context, never for routine planning, coding, testing,
documentation, or release work.
Project priorities
QWarp is an unofficial, Linux-only PyQt6 GUI for the Cloudflare WARP client. It is intended to remain lightweight, Wayland-native, usable on X11, and suitable for both Python package and frozen PyInstaller builds. Reliability comes before feature velocity or packaging convenience: daemon control must be safe, the Qt event loop must stay responsive, and existing desktop integrations must keep working.
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 · 183 lines · 2,083 tokens per session scan A 206116a2fb6d
qwarp AGENTS.md is an instructions file published in the GitHub repository iashutoshtiwari/qwarp (13 stars, last pushed 7d ago), licensed MIT. It adds 2,083 tokens to every session, about $0.0104 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 2026-08-30.
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.