Borrowing it
Nothing to install: this file belongs to G-Research/bobbit. 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/G-Research/bobbit/main/.claude/skills/file-explorer-preview/SKILL.mdgit clone --depth 1 https://github.com/G-Research/bobbitWrote 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/g-research/bobbit/file-explorer-preview)<a href="https://agentmods.dev/skills/g-research/bobbit/file-explorer-preview"><img src="https://agentmods.dev/badge/skills/g-research/bobbit/file-explorer-preview/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/g-research/bobbit/file-explorer-preview"><img src="https://agentmods.dev/badge/skills/g-research/bobbit/file-explorer-preview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium MCP Rug Pull · line 33 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 50 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00025 | $0.00695 |
| Opus 5.5 | $0.00010 | $0.00278 |
| Sonnet 5.5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
file-explorer-preview 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Explorer Like-for-Like Preview
Create a live preview of the File Explorer panel that is faithful enough for layout and interaction iteration.
Non-negotiables
- Import the exact source:
market-packs/file-explorer/src/file-explorer-panel.ts. - Do not copy panel HTML or CSS by hand.
- Do not define Bobbit theme variables in preview HTML.
- Use
preview_open(file=..., assets=["bundle.js"])so the iframe receives the real theme bridge. - Keep route/store/session behavior in the harness only; production panel logic stays untouched.
- The default fixture must exercise a selected changed file, expanded folders, Git badges, File/Diff tabs, search, direct paths, filtering, and responsive narrow mode.
Bring up the preview
- Create a temporary output directory and copy the stable HTML shell:
mkdir -p .bobbit/tmp/file-explorer-preview
cp .claude/skills/file-explorer-preview/index.html .bobbit/tmp/file-explorer-preview/index.html
- Bundle the harness. It imports the exact panel source and supplies realistic mediated Host API fixtures:
npx esbuild .claude/skills/file-explorer-preview/entry.ts --bundle --format=esm --platform=browser --target=es2022 --outfile=.bobbit/tmp/file-explorer-preview/bundle.js --tsconfig=tsconfig.web.json
- Open the file-backed preview:
preview_open({
file: ".bobbit/tmp/file-explorer-preview/index.html",
assets: ["bundle.js"],
})
Iterate
Edit the real panel source, rebuild only the preview bundle, then refresh the same preview slot:
npx esbuild .claude/skills/file-explorer-preview/entry.ts --bundle --format=esm --platform=browser --target=es2022 --outfile=.bobbit/tmp/file-explorer-preview/bundle.js --tsconfig=tsconfig.web.json
Call preview_open again with the same file and asset. This avoids build:packs, gateway restart, the production dist copy, and the runtime panel-module cache.
Use the harness fixture in entry.ts when a different visual state is needed. Do not add preview-only branches to the production panel.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 66 lines · 25 tokens per session scan A 332cfe467b25
file-explorer-preview is a skill published in the GitHub repository G-Research/bobbit (18 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 695 once invoked, about $0.0001 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 2026-08-30.
file-explorer-preview compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| file-explorer-previewG-Research/bobbit | Skill | 18 | 1mo ago | MIT | A | 25 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |