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 GMaN1911 · Claude Skill · ★ 450
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-cognitive safe to install? View the security audit →
Claude Cognitive Working memory for Claude Code — persistent context and multi-instance coordination []() The Problem Claude Code is powerful but stateless. Every new instance: Rediscovers your codebase from scratch Hallucinates integrations that don't exist Repeats debugging you already tried Burns tokens re-reading unchanged files With large codebases (50k+ lines), this becomes painful fast. The Solution Claude Cognitive gives Claude Code working memory through two complementary systems: Context Router Attention-based file injection with cognitive dynamics: HOT (0.8): Full file injection - active development WARM (0.25-0.8): Headers only - background awareness COLD (<0.25): Evicted from context Files decay when not mentioned, activate on keywords, and co-activate with related files. Pool Coordinator Multi-instance state sharing for long-running sessions: Automatic mode: Detects completions/blockers from conversation (every 5min) Manual mode: Explicit blocks for critical coordination Works with persistent sessions (days/weeks), not just short bursts Results Token Savings: Cold start: 79% (120K → 25K chars) Warm context: 70% (80K → 24K c
| Stars | 450 |
| Forks | 39 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 71.6372429503492/100 |
| Open Issues | 1 |
| Last Updated | 2026-01-17 |
| Created | 2025-12-30 |
| Platforms | claude-code, python |
| Est. Tokens | ~31k |
These tools work well together with claude-cognitive for enhanced workflows:
Looking for a claude-cognitive alternative? If you're comparing claude-cognitive with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The easiest way to run multiple Claude Code sessions, each in its own container, with a dashboard to manage th
everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic
Professional slash commands for Claude Code that provide structured workflows for software development tasks
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an ad
Explore other popular claude skill tools:
claude-cognitive is Working memory for Claude Code - persistent context and multi-instance coordination. It is categorized as a Claude Skill with 450 GitHub stars.
claude-cognitive is primarily written in Python. It covers topics such as claude-ai, claude-code, context-management.
You can find installation instructions and usage details in the claude-cognitive GitHub repository at github.com/GMaN1911/claude-cognitive. The project has 450 stars and 39 forks, indicating an active community.
claude-cognitive is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to claude-cognitive on Agent Skills Hub include safeclaw, everything-claude-code-zh, Claude-Command-Suite. 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: