What is context-firewall?

A plugin for using sub-agents to process large inputs and return summaries backed by evidence.

Use it when dividing research or file analysis into smaller tasks that need consistent evidence and verification.

It helps keep large context manageable and makes important claims easier to check.

context-firewall — Plugin by lollipopkit

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add lollipopkit/cc-plugins

agentmods

npx agentmods add plugins/lollipopkit/cc-plugins/context-firewall

Clone the repo

git clone --depth 1 https://github.com/lollipopkit/cc-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

context-firewall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/context-firewall/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "context-firewall",
  "version": "0.1.0",
  "description": "Context Firewall: use sub-agents to preprocess large inputs with evidence contracts and low-cost verification.",
  "author": {
    "name": "lollipopkit"
  },
  "keywords": [
    "context",
    "sub-agent",
    "summarization",
    "evidence",
    "verification",
    "map-reduce"
  ],
  "repository": "https://github.com/lollipopkit/cc-plugins",
  "license": "MIT",
  "commands": "./commands/"
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 20 lines scan A f4a597175a92

Subscribe to this mod's changes

context-firewall is a plugin published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI LLM Research ai claude-code plugin ralph skills

paperthin

Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.

LilMGenius/paperthin · not measured

rune-kit

Less skills. Deeper connections. A lean, interconnected skill ecosystem for Claude Code — 66 skills, 248 connections, 45 signals, and runtime auto-discipline.

Rune-kit/rune · not measured

rune

67-skill mesh for Claude Code with runtime auto-discipline — native hooks (preflight/sentinel/completion-gate/quarantine) auto-fire at lifecycle boundaries. 248 mesh connections + 46 signals, adaptive routing, mesh analytics, MCP quarantine guidance, and project memory.

Rune-kit/rune · not measured

context-firewall