Sop

Reusable, project-agnostic engineering and multi-model skills for Claude Code

Install

npx -y skills add patforna/core-skills --skill sop

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use to get a second opinion on the current conversation or a specific question from an independent model (Codex).

SKILL.md

2.4 KB, 522 tokens by cl100k_base, as published. Nobody here has run it

Second Opinion (Sop)

Precondition

Must be run from main thread (reason: subagents can't spawn other subagents)

Usage

/core-skills:sop [<question>]

If no question is supplied, infer the underlying question from the current conversation.

Goal

Get a second opinion on the current conversation or a specific question from an independent model (Codex).

Step 1: Infer Question (If None Was Provided)

If the user provided a question, skip this step.

Otherwise, look at the conversation and identify the most recent substantive assertion or artifact under discussion and re-derive the underlying question.

Important: Do not carry the prior answer forward to avoid biasing the new model.

Show the inferred question to the user just FYI:

Question inferred from conversation: | "<question>"

Judge whether the underlying question has been inferred correctly. If unsure, ask the user to confirm or correct.

Step 2: Expand Skill References

If the question invokes a skill (explicit /name only — not bare names in prose/diagrams), inline its SKILL.md, clearly fenced, after the instruction. Recurse into /name invocations found inside, but inline each skill at most once — never re-expand one already present (terminates; prevents cycles and bloat).

Example: /core-skills:sop please /at:plan-task 054 but don't write to the task file.

Expanded prompt:

""" Please /at:plan-task 054 but don't write to the task file.

Skill references: === BEGIN plan-task SKILL.md === [full content of the plan-task skill's SKILL.md — resolve the skill wherever it is installed, e.g. the plugin cache under ~/.claude/plugins/cache/ or the project's .claude/skills/] === END plan-task SKILL.md === """

Step 3: Append Anti-Sycophancy Block

Append the block below to the question:

Answer directly and honestly. Do not hedge or soften to be agreeable. If your honest answer differs substantively from what the prompt seems to expect, give that one.

Step 4: Dispatch

Pass the prompt to Codex via codex:codex-rescue.

If Codex is unavailable (e.g. usage limit), fail loudly — do not substitute or skip.

Step 5: Deliver and Reconcile

Present the response.

If the question was inferred (see Step 1), reconcile the second opinion with the ongoing conversation.