Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add valpere/chorus --skill second-opiniongit clone --depth 1 https://github.com/valpere/chorusWrote 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/valpere/chorus/second-opinion)<a href="https://agentmods.dev/skills/valpere/chorus/second-opinion"><img src="https://agentmods.dev/badge/skills/valpere/chorus/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 | $0.00061 | $0.00404 |
| Opus 5 | $0.00030 | $0.00202 |
| Sonnet 5 | $0.00012 | $0.00081 |
| Haiku 4.5 | $0.00006 | $0.00040 |
Grade A, and why
chorus-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 7d 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.
What it actually says
Chorus: Second Opinion
When to use
- Quick sanity check on a decision or approach
- User says "second opinion", "sanity check", "what does Claude/Gemini/Cursor/Kilo think"
Invocation
# Ask Claude (default — depth, correctness, edge cases)
claude --print "Give a concise second opinion. Be direct: agree / concerns / verdict (approve / approve-with-caveats / reject).\n\n<approach>" --dangerously-skip-permissions
# Or ask Gemini (breadth — alternatives, long-context)
gemini --prompt "Give a concise second opinion. Be direct: agree / concerns / verdict (approve / approve-with-caveats / reject).\n\n<approach>" --yolo --output-format text
# Or ask Cursor (integration — does this fit the codebase?)
agent -p --force "Give a concise second opinion. Be direct: agree / concerns / verdict (approve / approve-with-caveats / reject).\n\n<approach>"
# Or ask Kilo (maintainability — naming, readability, long-term impact)
kilo run --auto "Give a concise second opinion. Be direct: agree / concerns / verdict (approve / approve-with-caveats / reject).\n\n<approach>"
Graceful degradation: If the requested agent is not installed (command -v <binary> fails), fall back to the next available one and tell the user which agent you used instead.
Output handling
Return the agent's output verbatim — no additional commentary needed. The agent's verdict is self-contained.
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.
- 7d ago First seen · 34 lines · 61 tokens per session scan A a928cf9615d9
chorus-second-opinion is a skill published in the GitHub repository valpere/chorus (10 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 404 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 2026-08-31.
Other skills, from other repositories
visual-crawl
Crawls the running app at randomized breakpoints, screenshots visual issues, checks design token consistency, and tests interactive elements. Each run covers different ground by design. Trigger on: "visual QA", "audit the app visually", "screenshot all the pages", "check for visual regressions", "crawl the site for…
dead-code-cleanup
Identifies and removes dead/orphaned code, tests, and Storybook stories — including trivial tests that check only obvious behavior or rare edge cases with no real value. Always validates that code is truly unused before deleting anything. Trigger on: "remove dead code", "clean up unused files", "delete orphaned…
issue-maintenance
Periodic and on-demand maintenance pass over a repo's open GitHub issue backlog. Re-labels miscategorized or unlabeled issues (bug/enhancement/question/invalid/duplicate) and bug lifecycle labels (needs-repro/needs-info) following the same decision logic as Anthropic's own dogfooded triage-issue command; re-scores…
evidence-check
An honesty gate that makes an AI back up its claims with real evidence instead of presenting guesses as fact. Use as an always-on background behavior, and invoke explicitly when the user says show your work, prove it, how do you know that, evidence check, what's your source, back that up, or when the AI is…
plain-language-audit
Sweeps a codebase's text — comments, docstrings, markdown docs, and user-facing UI copy — for jargon that could be plainer, AI writing tells/tropes, and verbose text that could be tightened. Auto-fixes unambiguous swaps, surfaces judgment calls for review. Trigger on: "jargon audit", "plain language audit", "find…
test-workflow
Automatically run after editing source files to select and run the appropriate test suite. Triggers on: any src/ file edit before a commit, or when the user says "run tests", "check tests", or "make sure tests pass". Selects unit, E2E, visual regression, or CSS lint based on what changed. Protects running dev servers.…