A set of controls for managing coding-agent work. It defines budgets, conditions for stopping, and checks that require evidence before work is considered complete.

Use it to govern agent tasks that need time or resource limits, explicit stop rules, and verifier-backed completion evidence.

It helps prevent an agent from running indefinitely or claiming success without verification. The input does not specify the exact budgets or checks.

martinloop — Plugin for Claude Code by Keesan12/martin-loop

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/Keesan12/martin-loop

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/keesan12/martin-loop/martinloop/github.svg)](https://agentmods.dev/plugins/keesan12/martin-loop/martinloop)

Your own site

<a href="https://agentmods.dev/plugins/keesan12/martin-loop/martinloop"><img src="https://agentmods.dev/badge/plugins/keesan12/martin-loop/martinloop/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/keesan12/martin-loop/martinloop"><img src="https://agentmods.dev/badge/plugins/keesan12/martin-loop/martinloop.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 The manifest loads nothing itself; its 1 skill, 1 MCP server cost 29 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

martinloop 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 today.

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/martinloop/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "martinloop",
  "version": "0.8.6",
  "description": "Govern coding-agent work with budgets, stop conditions, and verifier-backed evidence.",
  "author": {
    "name": "MartinLoop contributors"
  },
  "homepage": "https://martinloop.com/",
  "repository": "https://github.com/Keesan12/martin-loop",
  "license": "Apache-2.0"
}

Contents

What it installs

The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 29 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

today Changed 8b94f36a8cd9
yesterday Changed 63de66361e39
2d ago Changed cc27f9c0a3c5
7d ago Changed f3c90ef0e8db
9d ago Changed 9749fa8d563b
13d ago Changed a03603fccd0d
14d ago Changed 9fccca0c7763
17d ago Changed cb726c919acb
20d ago Changed f1b753524acd
21d ago First seen · 12 lines scan A c12e1919154d

Subscribe to this mod's changes

martinloop is a plugin published in the GitHub repository Keesan12/martin-loop (410 stars, last pushed today), licensed Apache-2.0. 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.

Building agents ai-agent-runtime ai-coding-agents ai-governance audit-trail budget-enforcement governed-runtime

ai-sdlc

AI-SDLC governance framework for Claude Code — action enforcement, telemetry, quality gates, and review agents.

ai-sdlc-framework/ai-sdlc · not measured

DingDawg Governance

Governed AI execution. Every action receipted, capability-gated, and rollback-ready.

dingdawg/dingdawg-governance · not measured

bernstein

Drive Bernstein, the open-source governance layer for AI agents, from Cursor. Monitor tasks, agents, costs, approve plans - all without leaving your editor.

sipyourdrink-ltd/bernstein · not measured

vm-disk-cleanup

Prevent and recover from disk-full errors in Cowork session VMs and Claude Code environments. Clears caches, temp files, build artifacts, and nodemodules in phased cleanup.

MSApps-Mobile/claude-plugins · not measured

csoai-gspc

Council of AI GSPC over MCP: 19 tools (14 free, 5 x402-metered). Read the live board, verify signed measurement cards (VALID / INVALID / UNCHECKABLE). Measurement only: a card is evidence, never a grade, mark or endorsement. Verification is free.

CSOAI-ORG/councilof-ai · not measured

vaara-governance

Accountable autonomy for Claude Code. PreToolUse runs a two-layer check on Bash, WebFetch, WebSearch, Write, Edit, NotebookEdit, Task, SendMessage and MCP calls (regex deny patterns on shell, web and file mutation; conformal risk scorer on MCP). PostToolUse writes a hash-chained SQLite audit record across the same set.

vaaraio/vaara · not measured