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.
git clone --depth 1 https://github.com/wdzhwsh4067/supervise-loopWrote 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.
[](https://agentmods.dev/plugins/wdzhwsh4067/supervise-loop/plugin)<a href="https://agentmods.dev/plugins/wdzhwsh4067/supervise-loop/plugin"><img src="https://agentmods.dev/badge/plugins/wdzhwsh4067/supervise-loop/plugin/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.
<a href="https://agentmods.dev/plugins/wdzhwsh4067/supervise-loop/plugin"><img src="https://agentmods.dev/badge/plugins/wdzhwsh4067/supervise-loop/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
supervise-loop 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 1mo 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.
What it actually says
{
"name": "supervise-loop",
"version": "0.1.0",
"description": "Autonomous supervisor/worker/critic iteration loop for Claude Code (the evaluator-optimizer pattern). Delegate a goal once; a supervisor agent grades each round against a checkable rubric — mechanical checks plus a SEPARATE critic sub-agent — and re-dispatches with feedback until the rubric passes or a hard cap is hit. No human in the loop.",
"author": {
"name": "王少煌",
"email": "[email protected]"
},
"repository": "https://github.com/wdzhwsh4067/supervise-loop",
"license": "MIT",
"keywords": [
"claude",
"claude-code",
"claude-code-plugin",
"claude-skills",
"agent",
"multi-agent",
"orchestration",
"evaluator-optimizer",
"orchestrator-workers",
"supervisor",
"critic",
"agent-loop",
"autonomous-agents"
],
"homepage": "https://github.com/wdzhwsh4067/supervise-loop#readme"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 295 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 28 lines scan A 98e511c36613
supervise-loop is a plugin published in the GitHub repository wdzhwsh4067/supervise-loop (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.
Other plugins, from other repositories
forge
Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory.
scout
Autonomous knowledge management and daily briefing system. Monitors your work tools (Slack, Calendar, Linear, GitHub, etc.), synthesizes findings into a persistent knowledge base with a formal ontology, and delivers daily action items — all running unattended via scheduled Claude Code sessions. Six session types…
scout-plugin marketplace
Marketplace for the Scout autonomous knowledge management plugin.
ganvil
Long-running autonomous coding harness with Planner-Generator-Evaluator architecture and Sprint decomposition. Builds complete applications from simple descriptions.
completely
Quality-first harness for autonomous AI coding agents: deterministic gates + a default-FAIL evaluator in the close path of the loop, over a Beads task spine. Done is earned, not asserted. Unifies GSD + Beads; stack-agnostic.
loopy
Universal loop-engineering harness: machine-verifiable stop conditions, cross-model maker/checker (Codex maker, Claude checker), disk-based loop memory, reversibility×impact decision gates that keep human approval to irreversible actions while auto-pushing reversible work-branch commits, autonomous replan on stalls, a.