No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by tamaratran · Agent Tool · ★ 4.7k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is fast-jev-compaction safe to install? View the security audit →
Featured in: TypeSafe Jev
fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also usable as an npm library. What and why Most context compaction asks an LLM to summarize old turns. A summary is lossy: a file path, exact error, constraint, or command can disappear even when it matters later. This library never rewrites anything. It only deletes tool calls and tool results Jev says are no longer needed, and it asks Jev while showing it the whole conversation. User and assistant text stays verbatim and in order. The repository is both an npm package () and a Claude Code plugin (, ) that uses the package to replace Claude Code's built-in compaction summary with the original messages. How it works Every is paired with its by . Calls in the first message or in the newest messages are pinned and never touched. The state sent to Jev is the whole conversation so far, oldest first, with every tool result replaced by a short note (). Tool inputs are included, texts are included, nothing is summarized.
| Stars | 4,682 |
| Forks | 259 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 72.3447956028588/100 |
| Open Issues | 54 |
| Last Updated | 2026-09-18 |
| Created | 2026-09-17 |
| Platforms | claude-code, node |
| Est. Tokens | ~16k |
Looking for a fast-jev-compaction alternative? If you're comparing fast-jev-compaction with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A 100% free modern JS SaaS boilerplate (React, NodeJS, Prisma). Full-featured: Auth (email, google, github, sl
Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks. Query your
The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Curso
Skill to give Claude Code (and any coding agent) the ability to generate beautiful and practical Excalidraw di
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and
General-purpose Playwright automation for coding agents
Explore other popular agent tool tools:
fast-jev-compaction is Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbati. It is categorized as a Agent Tool with 4.7k GitHub stars.
fast-jev-compaction is primarily written in TypeScript.
You can find installation instructions and usage details in the fast-jev-compaction GitHub repository at github.com/tamaratran/fast-jev-compaction. The project has 4.7k stars and 259 forks, indicating an active community.
fast-jev-compaction is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to fast-jev-compaction on Agent Skills Hub include open-saas, notebooklm-skill, agent-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: