agentmods.dev

gpui-fast: Instructions file for Codex

AGENTS.md

gpui-fast AGENTS.md is an instructions file for Codex, OpenCode from longbridge/gpui-fast. It costs 437 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for developing gpui-fast, a Rust fork of Zed's GPUI user-interface toolkit. They summarise the project rules for custom code, upstream synchronization, public APIs, and pull requests.

In plain words
What is it for?
Use them before editing gpui-fast code, checking upstream compatibility, and sending changes through a topic branch and pull request.
Why use it?
They give coding-agent sessions the constraints needed to make compatible changes without adding logic to upstream files or committing directly to the main branch.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md.

This is longbridge/gpui-fast's own configuration. It tells Codex and OpenCode how to work on gpui-fast itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gpui-fast configures →

not rated 393repo +76 changed 3d ago A scan 437 tokens original Apache-2.0
View source ↗ longbridge/gpui-fast
Reuse

Borrowing it

Nothing to install: this file belongs to longbridge/gpui-fast. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/longbridge/gpui-fast/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/longbridge/gpui-fast

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for gpui-fast AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/longbridge/gpui-fast/agents-md/github.svg)](https://agentmods.dev/instructions/longbridge/gpui-fast/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/longbridge/gpui-fast/agents-md"><img src="https://agentmods.dev/badge/instructions/longbridge/gpui-fast/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.

agentmods 80×15 button for gpui-fast AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/longbridge/gpui-fast/agents-md"><img src="https://agentmods.dev/badge/instructions/longbridge/gpui-fast/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 437 This file is loaded in full into every session.
When invoked 437 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00437 $0.00437
Opus 5.5 $0.00175 $0.00175
Sonnet 5.5 $0.00087 $0.00087
Haiku 4.5 $0.00044 $0.00044

Measured 3d ago against content hash 52d4d87e7acf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gpui-fast 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 3d 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.

AGENTS.md · 27 lines

What it actually says

gpui-fast for agents

Read CLAUDE.md and docs/upstream-sync.md before changing anything. In short:

  • Everything gpui-fast changes relative to the baseline GPUI (the import commit in UPSTREAM) is implemented in crates/<crate>/src/fast/: functions, types, algorithms, bookkeeping, tests and the comments that explain them. Methods of upstream types go in impl blocks inside fast/.
  • Upstream files only hold hooks: a field typed by a fast/ struct, a one-line call into fast/, a body that only forwards to fast/, a visibility bump, a #[path = "fast/<file>.rs"] redirect. No logic, and no explanatory comments beyond what a hook needs to be understood.
  • Outside fast/, name fast code by its full path at the point of use (crate::fast::retained::RetainedState::new(cx)), never through a use line. The only use of fast outside fast/ is gpui.rs exporting a test-support item (pub use fast::stats::LayoutStats;). Inside fast/, use lines are fine; never glob imports.
  • No new public API — with the one documented exception of fast::dynamic_textures (see docs/upstream-sync.md, rule 5) — and script/check-upstream must pass.
  • Changes reach main through pull requests from a topic branch; never commit to main directly.
  • Upstream sync commit titles use chore: Sync GPUI upstream <zed-commit>, for example chore: Sync GPUI upstream a1b71072e5. Do not start them with Merge. Preserve replayed upstream commit messages and vendor history.
Changes

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.

  1. 3d ago Changed · +2 lines · +32 tokens per session 52d4d87e7acf
  2. 1mo ago Changed · +3 lines · +62 tokens per session dad37faf1372
  3. 1mo ago First seen · 22 lines · 343 tokens per session scan A 04615f4b3544

Subscribe to this mod's changes

gpui-fast AGENTS.md is an instructions file published in the GitHub repository longbridge/gpui-fast (393 stars, last pushed yesterday), licensed Apache-2.0. It adds 437 tokens to every session, about $0.0017 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 2026-09-29.

CommitsFrontendGit and workflow
Related

gpui-fast AGENTS.md compared with instructions from other repositories

gpui-fast AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gpui-fast AGENTS.mdlongbridge/gpui-fastInstructions file393yesterdayApache-2.0A437Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode