What is harness-debug?

A staged method for diagnosing difficult software errors. It moves through reproducing the problem, reducing it to a smaller case, forming a hypothesis, adding measurements, fixing it, and running a regression test.

Finding the cause of hard bugs, creating minimal reproductions, gathering evidence during debugging, applying fixes, and checking them against future breakage.

It replaces guesswork with a traceable investigation where each stage produces the information needed for the next. Regression testing checks that the same error does not return.

harness-debug — Plugin by 3xachris

Install

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.

Claude Code

/plugin marketplace add 3xachris/3xa-harness

agentmods

npx agentmods add plugins/3xachris/3xa-harness/debug

Clone the repo

git clone --depth 1 https://github.com/3xachris/3xa-harness

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

harness-debug 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 2d 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.

addons/debug/.claude-plugin/plugin.json · 21 lines

What it actually says

{
  "name": "harness-debug",
  "version": "0.2.0",
  "description": "Six-stage diagnosis order for hard errors: reproduce, minimise, hypothesise, instrument, fix, regression-test — one stage's output is the next stage's entry ticket.",
  "author": {
    "name": "3xachris"
  },
  "repository": "https://github.com/3xachris/3xa-harness",
  "license": "MIT",
  "keywords": [
    "agent-skills",
    "claude-code",
    "debugging",
    "diagnosis",
    "root-cause"
  ],
  "skills": [
    "./skills/staged-diagnosis"
  ]
}

Changes

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.

2d ago First seen · 21 lines scan A 2cc0e43f8957

Subscribe to this mod's changes

harness-debug is a plugin published in the GitHub repository 3xachris/3xa-harness (17 stars, last pushed 16d 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.

Debugging Languages Testing agent-skills ai-agents claude-code codex developer-tools opencode

harness-debug

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

agent-inject

borski

superset

claude

claude-architect

subagent-model-routing