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.
curl -O https://raw.githubusercontent.com/longbridge/gpui-fast/main/CLAUDE.mdgit clone --depth 1 https://github.com/longbridge/gpui-fastWrote 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/longbridge/gpui-fast/claude-md)<a href="https://agentmods.dev/instructions/longbridge/gpui-fast/claude-md"><img src="https://agentmods.dev/badge/instructions/longbridge/gpui-fast/claude-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/longbridge/gpui-fast/claude-md"><img src="https://agentmods.dev/badge/instructions/longbridge/gpui-fast/claude-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 | $0.00691 | $0.00691 |
| Opus 5.5 | $0.00276 | $0.00276 |
| Sonnet 5.5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
gpui-fast CLAUDE.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.
What it actually says
gpui-fast
A fork of Zed's GPUI (crates/gpui and the Zed crates it depends on) that we
keep merging upstream changes into. To keep those merges easy:
- Put gpui-fast's code in
crates/<crate>/src/fast/, one file per topic. New work goes in a newcrates/gpui/src/fast/<topic>.rs(orfast/<topic>/); its tests go incrates/gpui/src/fast/tests/<topic>.rs, or at the bottom of the topic's file when they need its private items. - Upstream files only get small hooks: one field holding a
fast/struct, one-line calls or forwarding method bodies,pub(crate)visibility bumps,modlines, or a#[path = "fast/<file>.rs"]redirect to a rewrite. No new types, algorithms, tests or explanatory comments in upstream files, and no reformatting of upstream code. Methods on upstream types live inimplblocks infast/. - Outside
fast/, name fast code by its full path where it is used:crate::fast::<topic>::Name, never ause crate::fast::…line, so every hook shows where its code lives. The one exception isgpui.rsexporting atest-supportitem (pub use fast::stats::LayoutStats;). Insidefast/,uselines are fine; globs never are,use super::*included. Call a method of afast/type by its path too,crate::fast::layout_key::WindowLayout::end_frame(&mut self.fast_layout), notself.fast_layout.end_frame(). - No new public API. The public API stays upstream's. What tests and
gpui_perfneed (LayoutStats,Window::layout_stats,set_view_retention) is#[cfg(any(test, feature = "test-support"))]. The few forced differences are listed indocs/upstream-sync.md("Where our API differs from upstream's"),fast::dynamic_texturesincluded. - New files only inside
fast/or in our own crates (crates/gpui_perf). - Run
script/check-upstreambefore committing. It fails when a change to an upstream file is more than a hook. - Never commit to
maindirectly; every change goes through a pull request. Work on a topic branch offorigin/main, and when the change is ready to merge, push the branch and open a PR. - Prefix PR titles with the area they change, not
gpui::fast:for gpui-fast's own retained layout and performance work,composition:for window composition (e.g.composition: route pointer input to the correct composition surface).
Upstream directories and the commit they came from are in UPSTREAM. The full
rules, the check and the upstream sync procedure are in docs/upstream-sync.md.
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.
- 3d ago Changed · +1 lines · +10 tokens per session a371f1333329
- 22d ago Changed · +4 lines · +61 tokens per session 08039216fdc4
- 1mo ago Changed · +6 lines · +98 tokens per session 0b1e228aab4a
- 1mo ago First seen · 32 lines · 522 tokens per session scan A 586988278279
gpui-fast CLAUDE.md is an instructions file published in the GitHub repository longbridge/gpui-fast (393 stars, last pushed yesterday), licensed Apache-2.0. It adds 691 tokens to every session, about $0.0028 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.
gpui-fast CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gpui-fast CLAUDE.mdlongbridge/gpui-fast | Instructions file | 393 | yesterday | Apache-2.0 | A | 691 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |