second-opinion-honesty

second-opinion-honesty is a plugin for Claude Code from s0912758806p/agentic-sop-to-work. Its manifest loads nothing; the 1 skill, 1 command it bundles cost 325 tokens per session together, scanned A, original, MIT.

An independent reviewer for draft outputs that compares their claims with the available evidence before a person approves them.

In plain words
What is it for?
It is for checking reports and other drafts for factual overreach, using either an agent run's records or documents and sources supplied by the user.
Why use it?
It helps catch made-up facts, unsupported conclusions, incorrect numbers, and invented names or identifiers.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit It is for checking reports and other drafts for factual overreach, using either an agent run's records or documents and sources supplied by the user.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add s0912758806p/agentic-sop-to-work/plugin install second-opinion-honesty
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.

Clone the repo
git clone --depth 1 https://github.com/s0912758806p/agentic-sop-to-work

Made for: Claude Code.

Wrote 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.

agentmods badge for second-opinion-honesty

README.md
[![agentmods](https://agentmods.dev/badge/plugins/s0912758806p/agentic-sop-to-work/second-opinion-honesty/github.svg)](https://agentmods.dev/plugins/s0912758806p/agentic-sop-to-work/second-opinion-honesty)
Your own site
<a href="https://agentmods.dev/plugins/s0912758806p/agentic-sop-to-work/second-opinion-honesty"><img src="https://agentmods.dev/badge/plugins/s0912758806p/agentic-sop-to-work/second-opinion-honesty/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.

agentmods 80×15 button for second-opinion-honesty

Your own site · 80×15
<a href="https://agentmods.dev/plugins/s0912758806p/agentic-sop-to-work/second-opinion-honesty"><img src="https://agentmods.dev/badge/plugins/s0912758806p/agentic-sop-to-work/second-opinion-honesty.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 1 command cost 325 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

second-opinion-honesty 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 10d 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.

plugins/second-opinion-honesty/.claude-plugin/plugin.json · 15 lines

What it actually says

{
  "name": "second-opinion-honesty",
  "description": "Independent adversarial honesty reviewer for a DRAFT output: checks claims-vs-evidence (no fabrication, no overreach, no invented IDs) before a human approves. FULL mode reads an agentic-sop-kit run dir's trace; DEGRADED mode reviews any plain document with user-supplied inputs. Deterministic honesty checks in code + a capped ADVISORY adversarial LLM pass. The report is itself a DRAFT — a human owns the verdict; it never auto-approves or auto-rejects. An optional project-scoped Stop-hook can enforce that a human acknowledged a review before the session ends. Not a source-code reviewer.",
  "version": "0.2.0",
  "author": { "name": "s0912758806p", "url": "https://github.com/s0912758806p" },
  "homepage": "https://github.com/s0912758806p/agentic-sop-to-work",
  "repository": "https://github.com/s0912758806p/agentic-sop-to-work",
  "license": "MIT",
  "keywords": [
    "second-opinion", "honesty", "claims-vs-evidence", "adversarial-review",
    "fact-check", "no-fabrication", "draft-review", "domain-neutral",
    "agentic-sop", "claude-code", "skills", "hooks", "stop-hook", "acknowledgement"
  ]
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 1 command travel with it, and installing the plugin installs all of them — 325 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 10d ago First seen · 15 lines scan A 4fc9bd609c56

Subscribe to this mod's changes

second-opinion-honesty is a plugin published in the GitHub repository s0912758806p/agentic-sop-to-work (206 stars, last pushed yesterday), 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.