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 agentmods add skills/nomarj/sigil/second-opinionnpx skills add NOMARJ/sigil --skill second-opiniongit clone --depth 1 https://github.com/NOMARJ/sigilWrote 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/nomarj/sigil/second-opinion)<a href="https://agentmods.dev/skills/nomarj/sigil/second-opinion"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/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 | $0.00085 | $0.00965 |
| Opus 5 | $0.00043 | $0.00483 |
| Sonnet 5 | $0.00017 | $0.00193 |
| Haiku 4.5 | $0.00009 | $0.00097 |
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 yesterday.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Opinion — Multi-Model Review
Adapted from Trail of Bits' second-opinion skill. The insight: every LLM has training-specific blind spots. A vulnerability that Claude misses, Codex might catch — and vice versa. Layer 3 exploits this by running an independent review on a separate model without sharing the first model's findings.
Why Independence Matters
If you show Model B the findings from Model A, Model B's review is contaminated — it will anchor on what Model A found and confirm or deny, rather than doing its own analysis. True independent review means:
- Model B receives the code and a security review prompt
- Model B does NOT receive Model A's findings
- The findings are compared AFTER both reviews complete
- Disagreements are the most valuable output
When to Use
Layer 3 is triggered for changes that touch:
- Authentication or authorization logic
- Payment or financial transaction processing
- PII or sensitive data handling
- Cryptographic operations
- Infrastructure or deployment configuration
- Any change flagged CRITICAL by Layer 1 or Layer 2
Protocol
Step 1: Prepare the Review Package
Extract from the codebase:
- The changed files (full diff)
- Surrounding context (the files the changes interact with)
- The project's security model (auth patterns, trust boundaries)
- Any relevant architecture documentation
Do NOT include: Layer 1/2 findings, the primary model's analysis, or any hints about what to look for.
Step 2: Route to Independent Model
If available, use external LLM CLIs:
# Using OpenAI Codex CLI
codex --model o4-mini --prompt "Review this code for security vulnerabilities..." < review-package.md
# Using Google Gemini CLI
gemini --prompt "Security review of the following code changes..." < review-package.md
If external CLIs aren't available, simulate independence by:
- Starting a fresh context (new session) with no reference to prior analysis
- Using a different system prompt focused purely on security
- Treating the code as if you've never seen the project before
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.
- yesterday First seen · 105 lines · 85 tokens per session scan A d5ca9b5482f9
second-opinion is a skill published in the GitHub repository NOMARJ/sigil (5 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 965 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
sftp-cc
通用 SFTP 上传工具，通过自然语言触发，将本地项目文件上传到远程服务器。支持增量上传、私钥自动绑定与权限修正。.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
devtools-event-client
Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…
jk
Jenkins CLI for controllers. Use when users need to manage jobs, pipelines, config.xml, runs, logs, artifacts, credentials, nodes, or queues in Jenkins. Triggers include "jenkins", "jk", "pipeline", "build", "job create", "job config", "config.xml", "run logs", "jenkins credentials", "jenkins node".
t0-orchestrator
Master orchestration for the VNX multi-terminal system. Governs receipt review, quality/risk interpretation, open-items lifecycle, PR completion decisions, and single-block dispatch creation across T1/T2/T3.
assess-patch-risk
Assess an immutable patch artifact's program impact, regression risk, and auto-merge eligibility. Use for generated patch files, provider pull-request diffs, or commit ranges when reviewers need evidence about affected runtime paths, contracts, tests, and recoverability. This skill is read-only and does not generate…