Agent Plugins Marketplace
← All plugins

claim-audit

v0.5.0

Audit the added prose of a diff as untrusted claims -- every count, status, and attribution re-derived by executing commands, never by reading. Reports claims beside their deriving commands and states its own scope.

Claude Code1 Skill

By fblissjr2 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 24, 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 claim-audit 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 claim-audit@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/fblissjr/fb-claude-skills

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

Plugin files

skills/claim-audit/
├── .claude-plugin/plugin.json
└── skills/claim-audit/SKILL.md

Included Skills1

claim-auditskills/claim-audit/SKILL.md

Audits prose as untrusted claims and re-derives each one by running a command, never by reading and nodding: the added lines of a diff, a standing doc such as a README, AGENTS.md or SKILL.md checked against today's code, or a summary, changelog entry or PR text about to be sent. Checks counts, statuses, capabilities, pointers, attributions and numbers in prose; labels what cannot be derived; with --fix, applies the corrections the evidence settles. Use when the user says 'audit the claims', 'is this README still true', 'check the docs against the code', 'verify this summary', 'check what the changelog says actually happened', or before committing prose that describes work. Do NOT use for auditing a test suite (use test-audit) or for reviewing code changes themselves (use a code review).

Plugin manifests1

skills/claim-audit/.claude-plugin/plugin.json
{
  "name": "claim-audit",
  "version": "0.5.0",
  "description": "Audit the added prose of a diff as untrusted claims -- every count, status, and attribution re-derived by executing commands, never by reading. Reports claims beside their deriving commands and states its own scope.",
  "author": {
    "name": "fblissjr"
  },
  "repository": "https://github.com/fblissjr/fb-claude-skills"
}

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.

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