sop
Skill0 starsChanged 5 months agoMITView on GitHub
Use to get a second opinion on the current conversation or a specific question from an independent model (Codex).
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Docat0209/SoloForgetheir own version, first seen Apr 4, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Docat0209/SoloForge★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- clean-codeSkill
- create-design-briefSkill
- dddSkill
- goosSkill
- ingest-designSkill
- kaizenSkill
- panelSkill
- researchSkill
- review-loopSkill
- software-designSkill
- synthesizeSkill
- tddSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Must be run from main thread (reason: subagents can't spawn other subagents)
- Distinctive: line 16
If no question is supplied, infer the underlying question from the current conversation.
- Distinctive: line 24
If the user provided a question, skip this step.
- Distinctive: line 28
Important: Do not carry the prior answer forward to avoid biasing the new model.
- Distinctive: line 58
If Codex is unavailable (e.g.
- Distinctive: line 64
If the question was inferred (see Step 1), reconcile the second opinion with the ongoing conversation.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.