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 manusco/resonance --skill second-opiniongit clone --depth 1 https://github.com/manusco/resonanceWrote 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/manusco/resonance/second-opinion)<a href="https://agentmods.dev/skills/manusco/resonance/second-opinion"><img src="https://agentmods.dev/badge/skills/manusco/resonance/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 | $0.00102 | $0.01577 |
| Opus 5 | $0.00051 | $0.00788 |
| Sonnet 5 | $0.00020 | $0.00315 |
| Haiku 4.5 | $0.00010 | $0.00158 |
Grade A, and why
resonance-ops-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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resonance-ops-second-opinion: two models catch what one misses
Role: the independent second reviewer, on a different model. Invoked as:
/second-opinion(to cross-check a change with another model). Input: A diff, PR, confirmed goal contract, ADR, or concrete plan. Optionally the primary review. Output: For diff mode, a reconciled findings list ranked P0-P3. For decision mode, a reconciled decision critique: assumptions, evidence gaps, tradeoffs, reversal conditions, and strongest objection. Definition of Done: A configured independent reviewer has reviewed the artifact, or a manual prompt was produced and then answered by a separate reviewer. Agreements and disagreements are explicit. Every finding is verified against the actual artifact, not accepted on the second model's word. Empty, failed, same-identity, or unanswered reviews do not satisfy the gate.
After grounded tests, an independent second model is the strongest quality multiplier there is. One model rationalizes its own blind spots; a different model does not share them. This skill runs that check and reconciles the two views. It does not replace the primary review; it pressures it.
Independent Review Policy
Use independent review as a policy, not as a model ranking.
- Routine and reversible work uses the primary model plus grounded checks.
- A concrete high-risk artifact gets one configured independent reviewer.
- Unresolved evidence, model conflict, or a one-way decision goes to the human or a qualified domain authority.
Independence means a different configured reviewer identity, not a role-played persona and not an unverified command alias. A second model is evidence to reconcile. It is never the done signal.
Do not recurse. Run at most one decision review per artifact hash and the final diff review before ship.
Prerequisites (fail fast)
- There is a concrete artifact to review: a diff for
diffmode, or a confirmed goal contract, plan, or ADR fordecisionmode. A vague "is this good" is not a second-opinion request. - You know what the artifact is supposed to do, so the second reviewer can judge intent.
- Reviewer identity is configured and independent, or the manual path is explicitly marked incomplete until answered.
- The artifact is not too large and does not contain secrets that would leave the machine.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/01_happy_path.json 693 B
- evals/02_no_model_configured.json 667 B
- evals/03_no_blind_trust.json 733 B
- evals/04_planted_defect.json 1.2 KB
- evals/05_decision_mode.json 736 B
- evals/06_identity_unverified.json 567 B
- evals/07_manual_or_empty_not_complete.json 536 B
- evals/08_sensitive_or_oversize_input.json 561 B
- references/multi_model_review.md 3.5 KB
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 · 75 lines · 102 tokens per session scan A 1c64af84c058
resonance-ops-second-opinion is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 1,577 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.