by jfrog
Less is more. Make your agents smarter and faster. It’s not just about saving time; it’s about the feeling of not wasting it.
# Add to your Claude Code skills
git clone https://github.com/jfrog/boostLast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:28:47.215Z",
"npmAuditRan": true,
"pipAuditRan": true
}boost is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by jfrog. Less is more. Make your agents smarter and faster. It’s not just about saving time; it’s about the feeling of not wasting it. It has 253 GitHub stars.
Yes. boost passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/jfrog/boost" and add it to your Claude Code skills directory (see the Installation section above).
boost is primarily written in Shell. It is open-source under jfrog on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh boost against similar tools.
No comments yet. Be the first to share your thoughts!
Boost wraps the commands your agents and CI already run, save tokens, turns noisy logs into compact, structured context. Agents keep the signal: errors, timings, changed counts, cache hits, and next useful clues. Repeated package logs, progress bars, and CI noise stay out of the prompt.
your terminal — prefix any command with boost your coding agent — boost init wires up Cursor, Claude Code, Codex, Gemini CLI, and more your CI — one line: uses: jfrog/boost@v0
Install Boost:
curl -fsSL https://raw.githubusercontent.com/jfrog/boost/main/install.sh | bash
Wire it into Cursor, Claude Code, Codex, Gemini CLI, OpenCode, and supported CI:
boost init
Use it in GitHub Actions:
steps:
- uses: jfrog/boost@v0
- uses: actions/checkout@v4
Boost does not just truncate output. It applies command-aware filters that preserve what agents need to reason about the result.
# Without Boost: ~9,800 tokens of install noise
$ npm ci
npm warn deprecated inflight@1.0.6 / rimraf@3.0.2 / glob@7.2.3 …
added 1285 packages, audited 1286 in 45s
found 0 vulnerabilities
# With Boost: ~640 tokens, same outcome, cache-backed
$ boost npm ci
[OK] npm ci · 1,285 packages restored from boost cache in 2.4s · 0 vulnerabilities
The agent sees the useful summary, not the scrollback. On failures, Boost keeps the failing test, compiler error, stack frame, or CI step that matters.
boost docker build ... — compressed build log and layer-cache summaryboost npm ci — dependency summary, local package cache, retry-safe outputboost pytest — quiet output on green runs, useful failures when tests breakboost gh run view --log — CI logs condensed to top failures plus summaryboost update
See the full documentation for commands, configuration, OpenTelemetry export, and CI recipes.
*_TOKEN, *_SECRET, AWS_*, DATABASE_URL are redacted before write or export.Full policy, supported versions, and how to report a vulnerability: see SECURITY.md.
Copyright © 2026 JFrog Ltd. All rights reserved. See LICENSE and BETA_AGREEMENT.md.
Dedicated to the memory of Dima Gershovich — a brilliant engineer, a talented musician, and a dear friend. Read Dima's story