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/3xachris/3xa-harnessWrote 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/3xachris/3xa-harness/harness-core)<a href="https://agentmods.dev/plugins/3xachris/3xa-harness/harness-core"><img src="https://agentmods.dev/badge/plugins/3xachris/3xa-harness/harness-core.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
harness-core 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 3d 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-core",
"source": "./",
"description": "The five-skill discipline loop for long-running agent work: freeze a task's scope into a workorder, gate sensory output behind human review, log decisions so they survive a context reset, hand off state when work changes hands, and close out with evidence instead of claims.",
"version": "0.3.0",
"category": "productivity",
"keywords": [
"agent-skills",
"human-in-the-loop",
"review-gate",
"decision-log",
"workorder",
"closeout",
"handoff"
],
"skills": [
"./skills/core/workorder",
"./skills/core/sensory-gate",
"./skills/core/decision-log",
"./skills/core/handoff",
"./skills/core/honest-closeout"
]
}What it installs
The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 478 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
2 files beside marketplace.json#harness-core in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 23 lines scan A 837e3d26d95f
harness-core is a plugin published in the GitHub repository 3xachris/3xa-harness (17 stars, last pushed 7d 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 2026-09-04.
Other plugins, from other repositories
i-have-adhd
Shape Claude Code output for an ADHD reader: lead with the next action, number steps, suppress tangents, restate state, make wins visible.
chain-system
Multi-session workflow chains for maintaining linked context across conversations.
cc-notify-hooks
A notification plugin for coding agents such as Claude Code, Codex, DeepSeek Harness, and Reasonix. It sends short waiting updates through several notification channels and handles longer updates asynchronously.
authoring
Author text deliverables and deliver them: README / CLAUDE.md / release notes / work logs, and posting the result to Slack. Visual deliverables — slide decks, HTML documents and PDF export — live in the visuals plugin. Install at user scope to make it available across all projects.
taskferry
Background OpenCode task execution through the Taskferry AXI CLI.
claude-ultimate-hud
Ultimate status line combining rate limits, project info, tool activity, todo progress, and improved emoji/CJK support.