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.
/plugin marketplace add juanmhidalgo/claude-plugins/plugin install second-opinionWrote 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.
[](https://agentmods.dev/skills/juanmhidalgo/claude-plugins/second-opinion)<a href="https://agentmods.dev/skills/juanmhidalgo/claude-plugins/second-opinion"><img src="https://agentmods.dev/badge/skills/juanmhidalgo/claude-plugins/second-opinion.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.01402 |
| Opus 5 | $0.00020 | $0.00701 |
| Sonnet 5 | $0.00008 | $0.00280 |
| Haiku 4.5 | $0.00004 | $0.00140 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Opinion via External AI
You are gathering context and asking an external AI for a second opinion.
Step 0: Select backend
Parse $ARGUMENTS for --backend <name> or infer from context:
| Flag / keyword | Script |
|---|---|
--backend codex or mentions "codex" or "openai" |
${CLAUDE_PLUGIN_ROOT}/scripts/ask-codex.sh |
--backend gemini or mentions "gemini" or "google" |
${CLAUDE_PLUGIN_ROOT}/scripts/ask-gemini.sh |
--backend copilot or mentions "copilot" or "github" |
${CLAUDE_PLUGIN_ROOT}/scripts/ask-copilot.sh |
--backend claude or mentions "claude" or "anthropic" |
${CLAUDE_PLUGIN_ROOT}/scripts/ask-claude.sh |
| No preference specified | Default to ${CLAUDE_PLUGIN_ROOT}/scripts/ask-codex.sh |
Remove the --backend flag from arguments before continuing to Step 1.
Step 1: Determine the review type
Parse remaining arguments to determine what the user wants reviewed:
| Pattern | Action |
|---|---|
review staged or staged |
Review staged git changes |
review <filepath> |
Review a specific file |
review branch or branch |
Review all changes on current branch vs base |
| Any other text | Treat as a free-form question — still gather relevant code context if possible |
Step 2: Gather context
Based on the review type, gather the minimum necessary context:
- Staged changes: Run
git diff --cachedto get the staged diff - Specific file: Read the file with the Read tool
- Branch review: Detect the base branch dynamically:
- Try
git rev-parse --verify origin/main— if it exists, usemain - Else try
origin/master - Else use the first remote default branch
Then run
git diff <base>...HEAD
- Try
- Free-form question: If the user references specific files or functions, read those. Otherwise proceed with just the question.
Context budget: Keep total context under 8000 characters. If a diff or file is larger:
- For diffs: use
git diff --cached --statto summarize, then include only the most relevant hunks - For files: include only the relevant sections
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.
- 5d ago First seen · 154 lines · 40 tokens per session scan A bb3a10cf9b3a
second-opinion is a skill published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 13d ago), licensed MIT. It adds 40 tokens to every session and 1,402 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
review
Review local code changes for bugs, regressions, missing tests, and pragmatic improvements. Use when the user asks to review the current changes from git status, or to review a specific backlog task by id such as task-65 or TASK-65. Also trigger when the user says things like "review", "review current changes", "check…
claude-friends
Ask AIs from other families to review something before you commit to it. User-triggered, never automatic. Fires when the user signals uncertainty or asks for another perspective: 'ask a friend', 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test this', 'critique this', 'devil's…
facts-discover
Scan the codebase and classify every fact by lifecycle stage — tag @draft, @spec, or @implemented based on what the code actually shows. Add missing facts, fix inaccurate ones, remove obsolete ones. Use when asked to discover facts, bootstrap or update a fact sheet, scan the codebase for truths, sync facts to match…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.