second-opinion

second-opinion is a command for Claude Code from s0912758806p/agentic-sop-to-work. It costs 59 tokens per session (1,141 once invoked), scanned A, original, MIT.

A command that gives a finished draft an independent adversarial review by comparing its claims with its evidence.

In plain words
What is it for?
It is for reviewing an agent run directory or a supplied document with sources; the resulting report is advisory and does not approve or reject the draft.
Why use it?
It helps identify unsupported conclusions, fabricated or transcribed numbers, invented dates or names, and incorrect pass-or-fail verdicts before human approval.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the second-opinion-honesty plugin — 1 skill, 1 command shipped together

Good fit It is for reviewing an agent run directory or a supplied document with sources; the resulting report is advisory and does not approve or reject the draft.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add s0912758806p/agentic-sop-to-work
Claude Code
/plugin install second-opinion-honesty

Made for: Claude Code.

Or install second-opinion-honesty, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/s0912758806p/agentic-sop-to-work/second-opinion"><img src="https://agentmods.dev/badge/commands/s0912758806p/agentic-sop-to-work/second-opinion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,141 The whole file, excluding the scripts and references it only reads on demand.
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.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01141
Opus 5 $0.00030 $0.00571
Sonnet 5 $0.00012 $0.00228
Haiku 4.5 $0.00006 $0.00114

Measured 11d ago against content hash d7fc113a8396, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

second-opinion 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 11d 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/commands/second-opinion.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/second-opinion — adversarial honesty review (DRAFT, human owns the verdict)

You are an independent, skeptical second reader. Your job is to attack a finished DRAFT and find where its claims are not backed by its evidence — fabricated/transcribed numbers, invented identifiers/dates that should be 【待補】, wrong PASS/FAIL verdicts, and conclusions the data don't support. You review the output's honesty, NOT source-code quality (that is /code-review) and NOT the workflow architecture (that is agentic-workflow-audit). You never approve or reject — a human owns the verdict.

$ARGUMENTS

Determine the mode

  • A directory containing run_manifest.jsonFULL mode (uses the run's trace).
  • A file path (+ --inputs <file...>) → DEGRADED mode (you supply the sources).
  • No arguments → run the bundled cross-domain demo (secondop/examples/pharma_stability).

Let ROOT="${CLAUDE_PLUGIN_ROOT}" and OUT="${CLAUDE_PROJECT_DIR:-.}/.second-opinion-runs".

Step 1 — deterministic pass (zero-LLM, code-owned)

Run the deterministic checker. It writes second_opinion.{json,md} and an LLM envelope llm_input.json into the run's output dir.

  • FULL: PYTHONPATH="$ROOT" python3 -m secondop.review --run-dir <run_dir> --out-base "$OUT"
  • DEGRADED: PYTHONPATH="$ROOT" python3 -m secondop.review --doc <doc> --inputs <file...> --out-base "$OUT"

Note the output dir it prints (the wrote … lines). Call it RUNOUT.

Step 2 — advisory adversarial pass (you, capped, ADVISORY only)

Read RUNOUT/llm_input.json. It gives you draft_text, declared_sources, claims, already_settled, focus, and rules. Acting as an adversary:

  • Focus on #4 (conclusion overreach) and fuzzy #1 (verdicts/limits the deterministic layer could not parse). The deterministic layer already owns #1/#2/#3 where it could.
  • Obey the envelope rules: every finding must quote a verbatim span from draft_text in claim, and justify it in evidence by citing a declared_sources token or stating NO SOURCE. Do not invent input values. Do not re-flag anything in already_settled.
  • Keep confidence ≤ 0.5 (the code clamps it regardless).

Read the full file on GitHub · 69 lines

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. 11d ago First seen · 69 lines · 59 tokens per session scan A d7fc113a8396

Subscribe to this mod's changes

second-opinion is a command published in the GitHub repository s0912758806p/agentic-sop-to-work (206 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 1,141 once invoked, about $0.0003 per session on Opus 5. 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.