Borrowing it
Nothing to install: this file belongs to tsouth89/ceiling. 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/tsouth89/ceiling/main/AGENTS.mdgit clone --depth 1 https://github.com/tsouth89/ceilingWrote 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/tsouth89/ceiling/agents-md)<a href="https://agentmods.dev/instructions/tsouth89/ceiling/agents-md"><img src="https://agentmods.dev/badge/instructions/tsouth89/ceiling/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/tsouth89/ceiling/agents-md"><img src="https://agentmods.dev/badge/instructions/tsouth89/ceiling/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 | $0.01586 | $0.01586 |
| Opus 5.5 | $0.00634 | $0.00634 |
| Sonnet 5.5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade C, and why
ceiling 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 1mo 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.
- Remove with `git worktree remove ../.worktrees/<task>` then `git worktree prune`. On Windows this deletes the files but leaves the empty directory tree, so follow with `rm -rf ../.worktrees/<task>`. Skipping that is wh How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Current Project State
- This branch launches the Tauri desktop shell by default (
apps/desktop-tauri/src-tauri), whilerust/remains the shared backend/domain crate and standalone CLI. - Many files in
docs/and some workflows reference the upstream macOS/Swift project. Treat those as historical or upstream-sync material unless the task is explicitly about upstream parity. - When repo docs conflict, trust the active Tauri desktop sources in
apps/desktop-tauriplus the shared Rust sources inrust/src.
Project Structure & Modules
apps/desktop-tauri/: Tauri desktop shell (default UI). React frontend inapps/desktop-tauri/src/, Rust backend + tray bridge inapps/desktop-tauri/src-tauri/src/.rust/src: Shared backend crate + CLI (codexbarbinary). Houses providers, settings, login, status, sound, shortcuts, browser cookie extraction, and the shared tray-icon renderer.rust/src/providers: Provider-specific fetch/parsing/auth logic. Keep provider boundaries clean.rust/src/tray(shared):icon.rs+render.rs— pixel-level tray-icon rendering used by the Tauri shell.rust/src/browser: Browser detection + cookie extraction for Windows.rust/src/core: Shared provider-construction (instantiate_provider) and provider IDs.rust/assets,rust/icons,rust/gen,rust/wix: UI assets, generated schemas, installer packaging.docs: Mixed documentation (Windows port docs plus upstream/macOS references). Update only the relevant docs.
Build, Test, Run
- Default desktop work runs from the repo root;
cd rustis for backend/CLI-only tasks. - Build the desktop shell (preferred):
cd apps/desktop-tauri && npm run tauri:build(ortauri:build:debug). Rawcargo build --releaseon the Tauri crate produces an exe that still points at the dev URL. - Build the CLI:
cargo build -p codexbar. - Test:
cargo test --manifest-path rust/Cargo.tomlandcargo test --manifest-path apps/desktop-tauri/src-tauri/Cargo.toml. - Run CLI locally:
cargo run -p codexbar -- --help,cargo run -p codexbar -- usage -p claude,cargo run -p codexbar -- cost. The CLI no longer launches a GUI when run with no subcommand. - Run the desktop shell through Tauri's build/dev flow:
.\dev.ps1,./dev.sh, orcd apps/desktop-tauri && npm run tauri:dev. - Format/lint before handoff when code changed:
cargo fmt --allandcargo clippy --all-targets -- -D warningson both manifests (or explain why not run). - There is no active root-level
Scripts/build pipeline in this port. Do not rely on legacyScripts/*.shcommands.
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.
- 1mo ago First seen · 90 lines · 1,586 tokens per session scan C da4fc9ea9884
ceiling AGENTS.md is an instructions file published in the GitHub repository tsouth89/ceiling (24 stars, last pushed 2mo ago), licensed MIT. It adds 1,586 tokens to every session, about $0.0063 per session on Opus 5.5. 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
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
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, cache eligibility and rollout and applying the notice (cutover).
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.