Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. 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/vanillagreencom/kendex/main/.agents/skills/second-opinion/SKILL.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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/vanillagreencom/kendex/second-opinion)<a href="https://agentmods.dev/skills/vanillagreencom/kendex/second-opinion"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/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/vanillagreencom/kendex/second-opinion"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/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 | $0.00019 | $0.01890 |
| Opus 5.5 | $0.00008 | $0.00756 |
| Sonnet 5.5 | $0.00004 | $0.00378 |
| Haiku 4.5 | $0.00002 | $0.00189 |
Grade C, and why
second-opinion scanned grade C with 1 finding 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 21d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- kendex:project-instructions:start --> How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Problems with a kendex-owned skill go through kendex report; check ownership in the file first.
Second Opinion
Cross-model second opinion via external AI CLI. Every mode walks the SECOND_OPINION_MODELS roster in priority order and takes the first target that is available, runs a different model and, where it has a room check, has room on its account: Codex from a Claude Code session, Claude from a Codex session; when nothing eligible remains the run refuses and says why. Full contract: second-opinion --help.
.agents/skills/second-opinion/scripts/second-opinion <mode> [options]
Workflows
| Command | Workflow | Output |
|---|---|---|
review [scope] |
workflows/review.md | Review finding JSON |
challenge [description] |
workflows/challenge.md | Structured critique (text) |
audit [path] |
workflows/audit.md | Review finding JSON |
quick [question] |
workflows/quick.md | Text response |
detect |
(built-in) | Target name(s) a review would run |
Execution Rules
- Execute all workflow sections in order. The workflow decides what to skip via "Skip if" conditions. Never skip based on your own scope assessment.
<output_format>tags are literal templates: fill[PLACEHOLDERS], omit empty lines, add nothing else, do not paraphrase.- Pass
--targetwhen the user explicitly requests a specific model/CLI (e.g., "use Claude", "ask Codex"). Otherwise omit it. The script selects from the roster and the current session's model. A forced target that runs this session's model is refused; report the refusal, do not work around it. - Do not pass
--timeoutunless the user explicitly asks for a different value for this specific call. The script reads the default from project config. - Always pass
--cwdwith the absolute project root path. Never use--cwd .. - Pass
--foregroundwhen the call can outlast the harness foreground cap. This detaches the run and prints its artifact, deadline, and wait command. - Execute the exact printed wait command and follow its exit handling in
second-opinion --helpuntil terminal. - For
quickmode, you can pass the question inline:.agents/skills/second-opinion/scripts/second-opinion quick "your question here" --cwd /path --foreground.
What ships with it
11 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.
- kendex.settings.toml.example 4.8 KB
- README.md 4.1 KB
- references/multi-lane.md 7.9 KB
- schemas/review-finding-prompt.md 2.5 KB
- scripts/lib/kendex-env.sh 18 KB runs code
- scripts/second-opinion 168 KB
- scripts/second-opinion-runtime 20 KB
- workflows/audit.md 2.0 KB
- workflows/challenge.md 2.3 KB
- workflows/quick.md 1.3 KB
- workflows/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.
- 21d ago Changed · -1 lines fba61b322a12
- 24d ago Changed 2bf3673e10b0
- 25d ago Changed d45bb9232bb1
- 26d ago Changed 7d0868b951f0
- 28d ago Changed · +2 lines 7e89f3aa1a3d
- 29d ago Changed 13c22b693167
- 1mo ago Changed f90254d0e675
- 1mo ago Changed · +2 lines 023afd05c763
- 1mo ago Changed · +4 lines scan A → C fbcc5c3952d6
- 1mo ago First seen · 67 lines · 19 tokens per session scan A ad690ba0f868
second-opinion is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 1,890 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.
rp
Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace. Covers workspace discovery, binding, root verification, and workspace hygiene.
claude-md-improver
Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.
claude-md-revision
Record durable, project-specific learnings from the current session in CLAUDE.md, .claude.local.md, or AGENTS.md—not general documentation, session summaries, or repo-wide audits.
gather-retrospectives
Gather retrospective feedback from past Pi sessions about a package, tool, or workflow. Use for historical retros and recurring friction, not assessment of only the current session.