Agent Plugins Marketplace
← All plugins

harness-ledger

v1.0.0

Claude adapter for the harness-ledger contract and append-only run ledger. Mints controller run ids and actor instances, renders research answers into claim-evidence records with per-claim sources and [unsourced] tagging, stamps Run-Id commit trailers at commit creation, and enforces a structural generator-is-not-judge separation at append time. The core schema and CLI are provider-neutral; this plugin is one delivery adapter.

Claude Code1 Skill

By Ahmad AmmarLicense: MIT0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 28, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install harness-ledger for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install harness-ledger@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/ahmadyaseen35-coder/harness-ledger

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

harness-ledger/
├── .claude-plugin/plugin.json
└── skills/harness/SKILL.md

Included Skills1

harnessskills/harness/SKILL.md

Run work under the harness-ledger contract - mint a controller run id before any arm launches, write the task contract, append run events, render research answers into claim-evidence records with per-claim sources, have a different actor judge them, and compute the ratios. Use when the user says "start a harness run", "open a run", "mint a run id", "record this claim", "judge these claims", "render the quote table", "compute the ratios", "harness ledger", "adoption ratio", "outcome ratio", or when delegating generation to a second model and the result must be attributable and checkable afterwards.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "harness-ledger",
  "version": "1.0.0",
  "description": "Claude adapter for the harness-ledger contract and append-only run ledger. Mints controller run ids and actor instances, renders research answers into claim-evidence records with per-claim sources and [unsourced] tagging, stamps Run-Id commit trailers at commit creation, and enforces a structural generator-is-not-judge separation at append time. The core schema and CLI are provider-neutral; this plugin is one delivery adapter.",
  "author": {
    "name": "Ahmad Ammar"
  },
  "license": "MIT",
  "skills": [
    "./skills/harness"
  ],
  "keywords": [
    "harness",
    "ledger",
    "append-only",
    "claim-evidence",
    "generator-judge-separation",
    "adoption-ratio",
    "fabrication-rate",
    "run-id"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[harness-ledger on Agent Plugins Marketplace](https://pluginsmp.com/plugins/harness-ledger)