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/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/3xachris/3xa-harness/harness-core"><img src="https://agentmods.dev/badge/plugins/3xachris/3xa-harness/harness-core.svg" alt="Reviewed on agentmods" width="80" 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 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-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.
- 1mo 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 1mo 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
chain-system
Multi-session workflow chains for maintaining linked context across conversations.
daodan
One command per intention, with no parameters: initialize, onboard, check health, brainstorm, investigate, build, fix, refactor, continue, finish, sync, review, map, document, tidy. Each command is a thin entry into the canonical method of its owner, usable alone or as a step of the task cycle.
handoff
Session quality gate for Claude Code. Health checks, resume points, and cross-machine continuity.
yonsei-space-reservation
A Yonsei University space-reservation assistant for Windows, macOS, and Linux. It finds official spaces matching stated conditions and submits a reviewed application only after the user confirms it.
toggl
Toggl time tracking - manage time entries and generate reports.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.