A Claude Code plugin that lets you run terminal commands in the prompt area and view their output without automatically sending it to Claude. Commands that can inspect files or system state are allowed by default, while other commands are gated.

Use it to inspect files, run shell commands, and pass selected command results to Claude for further action.

It lets you check command output privately and share only the results Claude needs, which can reduce unnecessary context and avoid exposing unrelated terminal data.

sethu — Plugin for Claude Code by NamrataAShettar/claude-sethu

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.

Clone the repo

git clone --depth 1 https://github.com/NamrataAShettar/claude-sethu

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/namrataashettar/claude-sethu/claude-sethu/github.svg)](https://agentmods.dev/plugins/namrataashettar/claude-sethu/claude-sethu)

Your own site

<a href="https://agentmods.dev/plugins/namrataashettar/claude-sethu/claude-sethu"><img src="https://agentmods.dev/badge/plugins/namrataashettar/claude-sethu/claude-sethu/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/namrataashettar/claude-sethu/claude-sethu"><img src="https://agentmods.dev/badge/plugins/namrataashettar/claude-sethu/claude-sethu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

sethu 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 25d ago.

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.

.claude-plugin/plugin.json · 25 lines

What it actually says

{
  "name": "sethu",
  "displayName": "sethu: command bridge",
  "version": "0.12.2",
  "description": "Run terminal commands right in the Claude Code prompt box: see the output yourself for free, or share it with Claude when you want it acted on.",
  "author": {
    "name": "namrataashettar"
  },
  "homepage": "https://github.com/NamrataAShettar/claude-sethu",
  "repository": "https://github.com/NamrataAShettar/claude-sethu",
  "keywords": [
    "hook",
    "command",
    "runner",
    "terminal",
    "bridge",
    "tokens"
  ],
  "license": "MIT",
  "icon": "./assets/sethu-icon-512.png",
  "documentationUrl": "https://github.com/NamrataAShettar/claude-sethu#readme",
  "supportUrl": "https://github.com/NamrataAShettar/claude-sethu/issues",
  "privacyPolicyUrl": "https://github.com/NamrataAShettar/claude-sethu/blob/main/PRIVACY.md"
}

Contents

What it installs

The manifest is a name and a version. 2 hooks travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 683 B

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.

25d ago Changed · +4 lines f4c6c92d1d11
2mo ago First seen · 21 lines scan A 6429d223f197

Subscribe to this mod's changes

sethu is a plugin published in the GitHub repository NamrataAShettar/claude-sethu (1 stars, last pushed 15d 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.

Claude Code claude claude-code-plugin cli developer-tools hooks

petprompt

A cute terminal pet that refines your rough prompts using your current session's context, memory, and model. No API key.

zjchenQAQ/petprompt · not measured

hush

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

V-Songbird/hush · not measured

merit-aktiva-workspace

Merit Aktiva accounting + Merit Palk payroll for Claude Code — full API coverage via the elnora-merit CLI, plus how-to skills for the correct Merit procedure: accounting (sales/purchase invoices, payments/bank reconciliation, VAT/KMD, reports, reverse charge) and payroll (employees & contracts, monthly…

Elnora-AI/elnora-merit-aktiva · not measured

dekko

Static code map for LLM agents. /map parses the repository with tree-sitter into MAP.md and map.json (every file, function, signature, type, and call edge) without spending model tokens; an 18-tool MCP server (searchcode, outline, querysymbol, getcallers, workset, impactedtests, ...) answers structural questions fr.

aahlijia/dekko · not measured

howl

Your AI screams — Howl listens. Blazing-fast Go statusline HUD with adaptive layouts and per-metric control.

ai-screams/Howl · not measured

elnora-platform

Elnora AI Platform CLI and skills.

Elnora-AI/elnora-cli · not measured