agentmods.dev

strip-ansi

A plugin that removes ANSI escape codes from tool output and checks terminal output for prompt-injection attacks, which are attempts to manipulate an agent through text it reads. It provides full protection for MCP tools and partial protection for built-in tools.

In plain words
What is it for?
Use it to sanitize MCP and other tool output and detect known terminal-based prompt-injection attacks.
Why use it?
Untrusted tool output can contain hidden terminal formatting or instructions aimed at changing the agent's behavior. Cleaning and checking that output reduces this risk.

Plugin for Claude Code

1 4mo ago A scan tokens not measured original MIT
View the source file knitli/toolshed
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 knitli/toolshed
agentmods
npx agentmods add plugins/knitli/toolshed/strip-ansi
Clone the repo
git clone --depth 1 https://github.com/knitli/toolshed

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

strip-ansi 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/strip-ansi/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "strip-ansi",
  "version": "1.1.0",
  "description": "Sanitizes ANSI escape sequences from tool output and detects terminal-based prompt injection attacks (CVE-tagged). Full protection for MCP tools via output replacement; partial protection for built-in tools via context injection.",
  "author": {
    "name": "Knitli Inc.",
    "email": "[email protected]"
  },
  "homepage": "https://knitli.com",
  "repository": "https://github.com/knitli/toolshed",
  "license": "MIT OR Apache-2.0",
  "keywords": [
    "ansi",
    "sanitize",
    "security",
    "mcp",
    "prompt-injection",
    "hygiene",
    "context"
  ]
}
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.

  1. yesterday First seen · 22 lines scan A 8050b0f26a03

Subscribe to this mod's changes

strip-ansi is a plugin published in the GitHub repository knitli/toolshed (1 stars, last pushed 4mo 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 AISecurityclaude-code-pluginclaude-skillscodex-plugincodex-skillsgemini-plugingemini-skills
Related

Other plugins, from other repositories

motherduck-skills

Plugin marketplace listing 1 plugin: motherduck-skills.

motherduckdb/agent-skills · not measured

motherduck-skills

MotherDuck skills for agents and developers: use the CLI and Guides, explore schemas, write DuckDB SQL, build Dives and Flights, and ship analytics apps and pipelines.

motherduckdb/agent-skills · not measured

frappe-agent

Plugin marketplace listing 1 plugin: frappe-agent.

Dkm0315/frappe-agent · not measured

frappe-agent

Frappe, ERPNext, and Frappe ecosystem coding, customization, bench, and review intelligence for Claude Code and AI coding workflows.

Dkm0315/frappe-agent · not measured

supergraph

Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.

datit309/supergraph · not measured

supergraph

Plugin marketplace listing 1 plugin: supergraph.

datit309/supergraph · not measured