second-opinion SKILL.md skillB

second-opinion from amirfish1/claude-command-center is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add amirfish1/claude-command-center/second-opinion@git:20261009.a664025

Pins git:20261009.a664025 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
amirfish1/claude-command-center
Path
plugin/skills/second-opinion/SKILL.md
Versions recorded
1
Latest version
git:20261009.a664025, committed Oct 9, 2026
Size
5,454 bytes
Repository stars
197
License
a license file GitHub does not identify

Use when, before committing to a non-trivial approach, diagnosis, or answer, you want an independent check — it spawns ONE fresh sibling session via CCC (no shared context) to solve the same task from scratch, then diffs its answer against yours. Disagreement is the product.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

Second-opinion spawns a single fresh CCC session with **no shared context** to
solve the same task you're about to answer, independently, and then diffs the
two answers. Where you and the fresh session agree, the answer is probably
solid; where you disagree, you've found a blind spot to investigate before you
commit. It builds on the spawn/report_to mechanics in the `ccc-orchestration`
skill — read that first for the full Spawn/Inject/Ask API.

## Cost

**1 spawned session.** Each spawn is a real billed session on the user's
kanban — tell the user the count before spawning. Do **not** use this for
trivial questions (just answer them) or one-shot factual lookups (use the
built-in `Task` tool — it's a subagent, not a billed kanban session).

## Setup

```bash
CCC_URL="$(cat ~/.claude/command-center/port.txt 2>/dev/null || echo "${CCC_URL:-http://127.0.0.1:8090}")"
curl -sf --max-time 2 "$CCC_URL/api/version" >/dev/null 2>&1 || CCC_URL="http://127.0.0.1:8090"
curl -sf --max-time 2 "$CCC_URL/api/version" >/dev/null 2>&1 || CCC_DOWN=1
```

- (a) Run every CCC curl with the **network sandbox disabled** — the Bash
  sandbox blocks loopback and fails spuriously even when CCC is up.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add amirfish1/claude-command-center/second-opinion@sha256:fb114d72001d37d5

The line at the top of this page pins the label git:20261009.a664025, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ujxmfditaexhkrlc.svg)](https://markdownregistry.com/a/art_ujxmfditaexhkrlc)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 9, 2026.

versioncommittedcommitsizeaudit
git:20261009.a664025 latest2026-10-09 a664025 5,454 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:8090)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5454 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

amirfish1/claude-command-center · 197 stars · license a license file GitHub does not identify · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ujxmfditaexhkrlc
GET https://markdownregistry.com/api/v1/resolve?ref=amirfish1/claude-command-center/second-opinion
GET https://markdownregistry.com/api/v1/blob/fb114d72001d37d5ff5c1410df7bacc5a70314a4e367aba7aed47f9cb5caab5a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from amirfish1/claude-command-center

testing-ccc-dashboard SKILL.md skill
amirfish1/claude-command-center · .agents/skills/testing-ccc-dashboard/SKILL.md · How to bring up and runtime-test the CCC dashboard (server.py) on a Linux box — ports, duplicate-instance bypass…
git:20261009.6eda475 · audit A · 197 stars
throughput SKILL.md skill
amirfish1/claude-command-center · .claude/skills/throughput/SKILL.md · Use when the user asks to open/show the CCC throughput (token) dashboard, or asks how many tokens they've used —…
git:20260802.cd011ef · audit A · 197 stars
AGENTS.md AGENTS.md file
amirfish1/claude-command-center · AGENTS.md
git:20261015.57a2359 · audit B · 197 stars
CLAUDE.md CLAUDE.md file
amirfish1/claude-command-center · CLAUDE.md
git:20261015.57a2359 · audit A · 197 stars
a-b-copy SKILL.md skill
amirfish1/claude-command-center · plugin/skills/a-b-copy/SKILL.md · Use when you want a marketing-copy A/B — spawns two writer sibling sessions via CCC that draft the SAME message…
git:20261009.a664025 · audit B · 197 stars
bug-race SKILL.md skill
amirfish1/claude-command-center · plugin/skills/bug-race/SKILL.md · Use when a bug has already survived at least one debugging attempt and you have 2-3 genuinely distinct root-cause…
git:20261009.a664025 · audit B · 197 stars
ccc-orchestration SKILL.md skill
amirfish1/claude-command-center · plugin/skills/ccc-orchestration/SKILL.md · Spawn, inject into, and ask questions of persistent sibling sessions via Claude Command Center (CCC).
git:20261009.a664025 · audit B · 197 stars
docs-drift SKILL.md skill
amirfish1/claude-command-center · plugin/skills/docs-drift/SKILL.md · Use to catch documentation that has silently gone stale — it spawns ONE fresh sibling session via CCC that extracts…
git:20261009.a664025 · audit B · 197 stars
dogfood SKILL.md skill
amirfish1/claude-command-center · plugin/skills/dogfood/SKILL.md · Use for docs QA — it spawns ONE fresh sibling session via CCC that has never seen the feature, has it follow the README…
git:20261009.a664025 · audit B · 197 stars
fleet-lane-dispatch SKILL.md skill
amirfish1/claude-command-center · plugin/skills/fleet-lane-dispatch/SKILL.md · Use when dispatching a batch of autonomous CCC worker lanes with a mission brief and a report_to return address, or…
git:20261009.a664025 · audit B · 197 stars
fleet-verify SKILL.md skill
amirfish1/claude-command-center · plugin/skills/fleet-verify/SKILL.md · Use after a UI or user-visible change and before you claim it works — it spawns ONE CCC verification lane that drives a…
git:20261009.a664025 · audit B · 197 stars
group-chat-checkin SKILL.md skill
amirfish1/claude-command-center · plugin/skills/group-chat-checkin/SKILL.md · Coordinate parallel sessions for discussion, task execution, and git commits.
git:20261009.a664025 · audit B · 197 stars

Every file in amirfish1/claude-command-center

Other files named second-opinion

second-opinion SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-verify/tiers/2-embedded/second-opinion/SKILL.md · Get an independent review of code you just wrote by spawning a fresh reviewer instance — a separate one-shot agent…
git:20260911.f7ea1cf · audit A · 61 stars
second-opinion SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/second-opinion/SKILL.md · Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says…
git:20261022.af5bf98 · audit A · 34 stars
second-opinion SKILL.md skill
microsoft/amplifier-bundle-skills · skills/second-opinion/SKILL.md · Independent review of current work or a past session. USE WHEN a user wants a second opinion. DO NOT USE WHEN ordinary…
v0.4.0 · audit A · 12 stars
second-opinion SKILL.md skill
flurdy/agent-skills · skills/second-opinion/SKILL.md · Query an independent peer or a configurable local/OpenRouter review panel, with distinct quorum and evidence-backed…
v3.8.0 · audit A · 9 stars
second-opinion SKILL.md skill
photostructure/coding-skills · plugins/coding/skills/second-opinion/SKILL.md · Get second opinions on freshly written code from fresh Codex and Claude reviewers, one small batch at a time, then…
git:20261002.718383a · audit A · 4 stars

Browse by kind, by grade B, or by owner.