A goal-based workflow in which an agent keeps checking whether a measurable completion condition has been met. It pauses for approval before operations that may be difficult or impossible to undo.

Use it to pursue goals that can be verified with evidence, while requiring approval for actions such as publishing code, changing repository visibility, sending external messages, making payments, exposing secrets, or deleting large amounts of data.

It reduces the chance that autonomous work stops too early or performs sensitive actions without confirmation.

jarvis-goal — Plugin for Claude Code by Ramsbaby

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/Ramsbaby/jarvis

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/ramsbaby/jarvis/jarvis-goal.svg)](https://agentmods.dev/plugins/ramsbaby/jarvis/jarvis-goal)

Your own site

<a href="https://agentmods.dev/plugins/ramsbaby/jarvis/jarvis-goal"><img src="https://agentmods.dev/badge/plugins/ramsbaby/jarvis/jarvis-goal.svg" alt="Measured on agentmods" height="20"></a>

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

When invoked not measured The manifest loads nothing itself; its 1 skill cost 67 tokens a session between them.

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

jarvis-goal 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 7d 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.

plugins/jarvis-goal/.claude-plugin/plugin.json · 13 lines

What it actually says

{
  "name": "jarvis-goal",
  "version": "0.1.0",
  "description": "Goal-driven autonomous execution with built-in irreversibility guard. Port of Anthropic /goal (Claude Code v2.1.139) that auto-pauses on git push, repo changes, payment, secret exposure, mass data deletion.",
  "author": {
    "name": "Ramsbaby",
    "url": "https://github.com/Ramsbaby/jarvis"
  },
  "homepage": "https://github.com/Ramsbaby/jarvis/tree/main/plugins/jarvis-goal",
  "license": "MIT",
  "keywords": ["autonomous", "goal", "verification", "irreversibility-guard"]
}

Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 67 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Skill jarvis-goal C 67 tokens

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.

7d ago First seen · 13 lines scan A fa3c6a156f03

Subscribe to this mod's changes

jarvis-goal is a plugin published in the GitHub repository Ramsbaby/jarvis (16 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 2026-08-30.

Claude Code Planning ai-agent automation claude discord-bot lancedb

cognition

Live control of one Discord server used as a lab for bots and programming experiments. Read the server, build systems as Registry data, run test sessions, schedule work, and gate anything irreversible behind a written preview.

justpainful/Cognition · not measured

marketing-team

Marketing team — 3 agents: Ink, Buzz, Pitch.

jeremylongshore/tons-of-skills-marketplace · not measured

daily-life-discovery

Guide a consent-based conversation that helps a person discover how an AI agent could improve their day-to-day life: routines, friction, attention, decisions, relationships, learning, and small experiments. Use when someone asks for a daily check-in, wants the agent to learn how they work, says "grill me," wants a…

magnus919/agent-skills · not measured

systematic-debugging

Diagnose root causes with a four-phase debugging protocol. Use for ANY technical issue — test failures, production bugs, unexpected behavior, performance problems, build failures, or integration issues. ESPECIALLY when under time pressure, when "one quick fix" seems obvious, or when previous fix attempts have failed.…

magnus919/agent-skills · not measured

jk

GitHub CLI-style interface for Jenkins controllers - create multibranch jobs, inspect config.xml, and manage runs, logs, artifacts, credentials, nodes, and queues.

avivsinai/jenkins-cli · not measured

claude-superskills marketplace

Plugin marketplace listing 1 plugin: claude-superskills.

ericgandrade/claude-superskills · not measured