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/paulbaranowski/wild-horsesWrote 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/paulbaranowski/wild-horses/harness)<a href="https://agentmods.dev/plugins/paulbaranowski/wild-horses/harness"><img src="https://agentmods.dev/badge/plugins/paulbaranowski/wild-horses/harness/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/paulbaranowski/wild-horses/harness"><img src="https://agentmods.dev/badge/plugins/paulbaranowski/wild-horses/harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
harness 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": "harness",
"description": "Analyze code for feedback-loop blockers and AI reasoning gaps, then build, run, and inspect a structured remediation task list to fix what it finds. Ships two analysis commands (`/harness:feedback-blockers`, `/harness:reasoning-gaps`) and three task-list skills (`task-list-builder`, `task-list-runner`, `task-list-viewer`) for producing, executing, and inspecting the resulting plan. Includes a PreToolUse hook that auto-approves invocations of the bundled task_list_cli.py, which also runs each task's verifySteps as subprocesses.",
"version": "8.3.3",
"author": {
"name": "Paul Baranowski"
}
}
What it installs
The manifest is a name and a version. 3 skills, 2 commands travel with it, and installing the plugin installs all of them — 488 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 · 9 lines scan A 8e09404d6285
harness is a plugin published in the GitHub repository paulbaranowski/wild-horses (14 stars, last pushed 10d 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
e2e
E2E test triage, debugging, and fix implementation toolkit.
matlab-agentic-toolkit
Core MATLAB skills and MCP tools for AI coding agents. Testing, debugging, code review, Live Scripts, App Builder, and code modernization.
polygraph
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
god-prompt-mcp
GodPrompt engineering workflows for task routing, TDD, debugging, verification, and progressive disclosure.
superpowers-deepseek-v4
Superpowers DeepSeek v4: composable agent skills for TDD, debugging, and collaboration. Independently maintained; not identical to obra/superpowers.
knowledge-virtuoso
15 knowledge skills — design patterns, refactoring, SOLID, debugging, clean architecture, testing, API design, security, scrum, performance, microservices, git workflow, CI/CD, accessibility, and database design.