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/donnfelker/loop-skillsWrote 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/donnfelker/loop-skills/multi-llm-convergence)<a href="https://agentmods.dev/plugins/donnfelker/loop-skills/multi-llm-convergence"><img src="https://agentmods.dev/badge/plugins/donnfelker/loop-skills/multi-llm-convergence/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/donnfelker/loop-skills/multi-llm-convergence"><img src="https://agentmods.dev/badge/plugins/donnfelker/loop-skills/multi-llm-convergence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
multi-llm-convergence 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": "multi-llm-convergence",
"description": "Drives any artifact — a plan, PRD, design doc, spec, or implementation diff — to convergence by alternating two genuinely different LLM reviewers (a Codex reviewer and an independent Claude review subagent), applying each round's findings and looping until both independently agree the artifact clears the bar (default: no critical/high findings). Grounds offline reviewers in local source-of-truth clones so they don't stall, runs a liveness watchdog so a silent reviewer can't hang the loop, and commits per round for an auditable convergence trail.",
"version": "0.3.0",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 192 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 · 7 lines scan A 778ced6d812e
multi-llm-convergence is a plugin published in the GitHub repository donnfelker/loop-skills (19 stars, last pushed 2mo 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.
Other plugins, from other repositories
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…
pedantic-coder
Zero-tolerance code pedantry — naming precision, casing law, structural symmetry, import discipline, and the obsessive details that separate clean code from correct code.
ai-infra-auto-driven-skills
Agent-ready playbooks for LLM serving benchmarks, SGLang model Day-0 support, capacity planning, profiling, code review, incidents, PR-history dossiers, and SGLang PR/article explainer videos.
git-pr
Committing, PR creation and review triage, and dependency upgrades.
code-quality
OxLint, Biome, and Prettier configuration, linting skills, and pre-commit hooks for consistent code quality.
coderabbit
CodeRabbit integration for Claude Code - local code review and PR comment management.