claude-code-harness

A marketplace listing for two Claude Code add-ons: one for setting up and reviewing a Claude Code harness, and another for keeping a development log. A harness is the project configuration and guidance around an AI coding assistant.

In plain words
What is it for?
Use the harness add-on to bootstrap, audit, extend, or explain Claude Code setup, and the devlog add-on to record features, fixes, and decisions.
Why use it?
It organizes assistant instructions and records important changes so work can remain consistent across sessions.

Plugin for Claude Code

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 nikitaCodeSave/claude-code-harness
agentmods
npx agentmods add plugins/nikitacodesave/claude-code-harness/marketplace
Clone the repo
git clone --depth 1 https://github.com/nikitaCodeSave/claude-code-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

claude-code-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 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.

.claude-plugin/marketplace.json · 28 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "claude-code-harness",
  "owner": {
    "name": "nikitaCodeSave",
    "email": "[email protected]"
  },
  "metadata": {
    "description": "The claude-code-harness kit — designs, bootstraps, audits, and extends a Claude Code harness (.claude/ + root CLAUDE.md), plus the devlog continuity companion. Opinion: under a capable model, less harness yields more productivity."
  },
  "plugins": [
    {
      "name": "claude-code-harness",
      "source": "./plugins/harness",
      "description": "Designs, bootstraps, audits, and extends a Claude Code harness (.claude/ + root CLAUDE.md). Bootstrap / Audit / Extend / Explain modes. Ships a skill and its references — no agents, no commands, no hooks.",
      "category": "workflow",
      "keywords": ["claude-code", "harness", "plugin-development", "bootstrap", "audit"]
    },
    {
      "name": "devlog",
      "source": "./plugins/devlog",
      "description": "Records significant changes to .claude/devlog/ — the episodic 'what changed and why' continuity layer, one markdown entry per feature/fix/decision, with index+digest regeneration and a SessionStart digest that auto-surfaces recent devlog + active progress. The harness kit recommends this; installing it makes that guidance runnable.",
      "category": "workflow",
      "keywords": ["claude-code", "devlog", "changelog", "continuity", "session-handoff"]
    }
  ]
}
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.

  1. 2d ago First seen · 28 lines scan A 0adb2ada075c

Subscribe to this mod's changes

claude-code-harness is a plugin published in the GitHub repository nikitaCodeSave/claude-code-harness (5 stars, last pushed 3d 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 2026-08-31.