Borrowing it
Nothing to install: this file belongs to vladm3105/aidoc-flow-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vladm3105/aidoc-flow-framework/dev/.agents/skills/second-opinion/SKILL.mdgit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/second-opinion)<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/second-opinion"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/second-opinion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/second-opinion"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/second-opinion.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.01219 |
| Opus 5.5 | $0.00019 | $0.00488 |
| Sonnet 5.5 | $0.00010 | $0.00244 |
| Haiku 4.5 | $0.00005 | $0.00122 |
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 1mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second opinion (LLM-as-judge)
Muse project skill — port of the canon global skill (
aidoc-flow-claude-agents-config/skills/second-opinion/SKILL.md). Where the canon names a Claude-specific agent type, dispatch your engine's focused read-only subagent equivalent and keep the independence contract.
An independent review pass that raises decision quality before work leaves your hands. It does not replace a human gate — where a human authorizes an action, nothing the judge passes is thereby authorized.
The independence rule — judge ≠ generator
This is the whole mechanism; everything else is packaging.
- The reviewer gets the artifact plus its cited sources — not the generator's reasoning or chain-of-thought. Handing over the reasoning invites the judge to grade the rationalization instead of the work.
- Dispatch a fresh-context read-only subagent as judge. Fresh context by construction; give it the rubric, output format, and independence rules in the delegation prompt. Do not re-author a judge prompt ad hoc — prompt variance silently weakens the judge, and a weakened judge still returns confident-looking verdicts.
- The rubric lives in the delegation prompt, not here. One source;
duplicated rubrics drift. Rubric changes are edits to the delegation prompt,
versioned by its
rubric vNoutput stamp. - Diversity axes, in increasing strength: same model fresh context (default) →
a different model tier via the
modeloverride → a different vendor.
This skill owns the independent-review contract. verified-planning and
preprod-review apply it to their own artifacts; where any of them disagree on
what independence means, this file governs.
When to run
- Any high-stakes or irreversible recommendation before it is acted on.
- Before an approval item is surfaced to a human (see
approval-gate). - Before a status rollup reaches whoever will act on it.
- Granularity: judge the plan, the final, and any irreversible step — not every micro-step. Skip trivial green chatter.
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.
- 1mo ago First seen · 103 lines · 48 tokens per session scan A bfcda54ddc06
second-opinion is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,219 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-28.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…