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 Martian-Engineering · Codex Skill · ★ 4.9k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is lossless-claw safe to install? View the security audit →
lossless-claw Lossless Context Management plugin for OpenClaw, based on the LCM paper from Voltropy. Replaces OpenClaw's built-in sliding-window compaction with a DAG-based summarization system that preserves every message while keeping active context within model token limits. Table of contents What it does Quick start Configuration Commands And Skill Session Migration CLI Documentation Development Line endings Security License What it does Two ways to learn: read the below, or check out this super cool animated visualization. When a conversation grows beyond the model's context window, OpenClaw (just like all of the other agents) normally truncates older messages. LCM instead: Persists every message in a SQLite database, organized by conversation Summarizes chunks of older messages into summaries using your configured LLM Condenses summaries into higher-level nodes as they accumulate, forming a DAG (directed acyclic graph) Assembles context each turn by combining summaries + recent raw messages Provides tools (, , ) so agents can search and recall details from compac
| Stars | 4,893 |
| Forks | 453 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 73.4636752974275/100 |
| Open Issues | 239 |
| Last Updated | 2026-09-19 |
| Created | 2026-02-18 |
| Platforms | node |
| Est. Tokens | ~21k |
These tools work well together with lossless-claw for enhanced workflows:
Looking for a lossless-claw alternative? If you're comparing lossless-claw with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscrip
The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex
Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark
📚 Sync skills across all AI CLI tools with one command and simplify team sharing. Supporting Codex, Claude Co
Skills for pi coding agent (compatible with Claude Code and Codex CLI)
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery,
Explore other popular codex skill tools:
lossless-claw is Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw. It is categorized as a Codex Skill with 4.9k GitHub stars.
lossless-claw is primarily written in TypeScript.
You can find installation instructions and usage details in the lossless-claw GitHub repository at github.com/Martian-Engineering/lossless-claw. The project has 4.9k stars and 453 forks, indicating an active community.
lossless-claw is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to lossless-claw on Agent Skills Hub include superset, refly, Claude-to-IM-skill. 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: