Borrowing it
Nothing to install: this file belongs to zed-industries/zed. 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/zed-industries/zed/main/.agents/skills/gpui-bench/SKILL.mdgit clone --depth 1 https://github.com/zed-industries/zedWrote 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/skills/zed-industries/zed/gpui-bench)<a href="https://agentmods.dev/skills/zed-industries/zed/gpui-bench"><img src="https://agentmods.dev/badge/skills/zed-industries/zed/gpui-bench/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/skills/zed-industries/zed/gpui-bench"><img src="https://agentmods.dev/badge/skills/zed-industries/zed/gpui-bench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 111 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- high Tool Misuse · line 308 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 308 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 308 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00062 | $0.06204 |
| Opus 5.5 | $0.00025 | $0.02482 |
| Sonnet 5.5 | $0.00012 | $0.01241 |
| Haiku 4.5 | $0.00006 | $0.00620 |
Grade C, and why
gpui-bench 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.
rm -rf /tmp/zed-profiles/<name>.trace The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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 Changed · +13 lines 4d6fe184a1f3
- 1mo ago Changed · +54 lines 064507af4657
- 2mo ago First seen · 388 lines · 62 tokens per session scan C 76429dd2b2ad
gpui-bench is a skill published in the GitHub repository zed-industries/zed (92,894 stars, last pushed today), with no licence file. It adds 62 tokens to every session and 6,204 once invoked, about $0.0002 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.
gpui-bench compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gpui-benchzed-industries/zed | Skill | 93k | today | none | C | 62 | Claude Code, Codex |
| cosmos-design-structAzure/azure-sdk-for-rust | Skill | 887 | today | MIT | A | 83 | Claude Code |
| tty7l0ng-ai/tty7 | Skill | 1.4k | 4d ago | Apache-2.0 | A | 293 | Claude Code, Codex |
| cosmos-pre-commit-validationAzure/azure-sdk-for-rust | Skill | 887 | today | MIT | A | 35 | Claude Code |
| gpui-componentlongbridge/gpui-component | Skill | 19k | 5d ago | none | A | 112 | Claude Code, Codex |
| gpuilongbridge/gpui-component | Skill | 19k | 5d ago | none | A | 90 | Claude Code, Codex |
| gpui-toolkitpierreaubert/gpui-toolkit | Skill | 91 | 3d ago | ISC | A | 60 | Claude Code, Codex |