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 championswimmer · Agent Tool · ★ 245
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is pi-context-prune safe to install? View the security audit →
Featured in: Agent Governance
pi-context-prune A Pi coding-agent extension that summarizes completed tool-call batches, prunes raw tool outputs from future LLM context, and exposes a escape hatch to recover any original output on demand. Related Extensions Here are some other Pi extensions that work well alongside context pruning: pi-context-usage (npm) What it does: Visualizes the current size of your LLM context and breaks it down to show exactly what is taking up space (system prompt, user messages, tool calls, tool results, etc.). Why use it: It's the perfect way to see why you need pruning. You can use it to inspect your context before and after a prune to see exactly how much space the extension just saved you. pi-cache-graph (npm) What it does: Plots your provider's prefix cache hits and misses as a live graph inside the TUI. Why use it: Pruning context directly impacts cache re-use. This extension lets you see the real-time effect of your chosen mode on cache stability. Why 📖 For a deep dive into how pruning works, how prefix caching interacts with it, and the research behind summarization-based context management, se
| Stars | 245 |
| Forks | 26 |
| Language | TypeScript |
| Category | Agent Tool |
| Quality Score | 65.1510916080782/100 |
| Open Issues | 13 |
| Last Updated | 2026-09-30 |
| Created | 2026-04-20 |
| Platforms | node |
| Est. Tokens | ~19k |
These tools work well together with pi-context-prune for enhanced workflows:
Looking for a pi-context-prune alternative? If you're comparing pi-context-prune 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 collection of standardized Agent Skills to teach GitHub Copilot, Claude, Gemini and Cursor about modern Andr
Coding Agents skills for Synalinks OSS
A collection of Agent skills and Claude Code plugins for HashiCorp products.
Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude
Lightweight registry to discover, install, and manage all public Claude plugins and agent skills for your favo
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
Explore other popular agent tool tools:
pi-context-prune is Pi coding-agent extension for pruning tool-call trees. It is categorized as a Agent Tool with 245 GitHub stars.
pi-context-prune is primarily written in TypeScript.
You can find installation instructions and usage details in the pi-context-prune GitHub repository at github.com/championswimmer/pi-context-prune. The project has 245 stars and 26 forks, indicating an active community.
The top alternatives to pi-context-prune on Agent Skills Hub include awesome-android-agent-skills, synalinks-skills, 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: