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/maddada/ghostex/agents-mdgit clone --depth 1 https://github.com/maddada/GhostexWhat 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 | $0.07923 | $0.07923 |
| Opus 5 | $0.03961 | $0.03961 |
| Sonnet 5 | $0.01585 | $0.01585 |
| Haiku 4.5 | $0.00792 | $0.00792 |
Grade C, and why
Ghostex AGENTS.md scanned grade C 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Before running any destructive command, including but not limited to `git restore .`, `git checkout -- .`, `git reset --hard`, `git clean`, `rm -rf`, or deleting untracked files, you must: How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules for Agents working in this Repository
General notes
- Multiple sub-agents are working in this repository. Don't be alarmed if something gets changed around your code. This is normal. Just get your work done without affecting the work of other sub-agents or breaking their work.
- Don't get stuck on stale git locks. You can delete those and continue on your work without confirmation.
Repository layout (restructured 2026-08-22)
The repository root was restructured on 2026-08-22. Old top-level folders
(gpui/, native/, ghostex-web/, gxserver-rs/, sidebar/, shared/,
components/, lib/, src/, zehn-rs/, ghostex-paths/, ghostex-history/,
mobile-chat/, mobile-find/, ghostty/, tui2/, zmx/, code-server/,
zehn/) no longer exist at the root. If you are working from an old plan,
transcript, or memory file, re-derive the path before you search or edit.
One-line vocabulary:
apps/= deliverables (things that ship and have an entry point).views/= embedded pages an app ships (never call these "webviews" or "surfaces").packages/= libraries imported by apps and by the server..dependencies/= ALL external-origin code, including code we edit.
Current root:
Ghostex/
├── .dependencies/ # ALL external-origin code (edited or not)
│ ├── ghostty/ ghostty-patches/ code-server/ zmx/
│ └── zed/ cef-rs/ gpui-component/
├── apps/
│ ├── desktop/ # Rust/GPUI desktop app (crate ghostex-gpui)
│ │ ├── src/ # Rust
│ │ ├── sidebar/ # CEF entry modules (main, chat, find, kanban, manage)
│ │ └── views/ # embedded pages: modal-host, titlebar-host, manage, kanban, meo
│ ├── web/ # static browser build of the shared workspace UI
│ ├── mobile/
│ │ ├── app/ # React Native / Expo submodule
│ │ └── views/ # chat/ + find/ view bundles embedded by the RN app
│ ├── editor/ # GhostexEditor daemon (Monaco prompt editor)
│ └── history-cli/ # `ghostex-history` CLI crate
├── server/ # gxserver crate (binaries: gxserver, ghostex)
├── packages/
│ ├── shared/ # cross-app contracts + logic
│ ├── core-ui/ # the shared React app UI (sidebar, chat, find, settings, assets)
│ ├── components/ # shadcn primitives (ui/) + utils.ts
│ ├── find/ # Rust prompt-history search (crate ghostex-find)
│ └── paths/ # Rust path resolution (crate ghostex-paths)
├── tooling/ media/ skills/ docs/
└── package.json tsconfig.json AGENTS.md CHANGELOG.md appcast*.xml bun.lock …
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.
- 2d ago First seen · 430 lines · 7,923 tokens per session scan C 371151669497
Ghostex AGENTS.md is an instructions file published in the GitHub repository maddada/Ghostex (714 stars, last pushed 2d ago), licensed MIT. It adds 7,923 tokens to every session, about $0.0396 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
buildNext
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
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
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.