Borrowing it
Nothing to install: this file belongs to netdata/ai-viewer. 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/netdata/ai-viewer/master/.agents/skills/project-second-opinions/SKILL.mdgit clone --depth 1 https://github.com/netdata/ai-viewerWrote 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/netdata/ai-viewer/project-second-opinions)<a href="https://agentmods.dev/skills/netdata/ai-viewer/project-second-opinions"><img src="https://agentmods.dev/badge/skills/netdata/ai-viewer/project-second-opinions/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/netdata/ai-viewer/project-second-opinions"><img src="https://agentmods.dev/badge/skills/netdata/ai-viewer/project-second-opinions.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 | $0.00070 | $0.04530 |
| Opus 5.5 | $0.00028 | $0.01812 |
| Sonnet 5.5 | $0.00014 | $0.00906 |
| Haiku 4.5 | $0.00007 | $0.00453 |
Grade A, and why
project-second-opinions 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 — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Second Opinions — Three Reviewer Gates
Non-Negotiable Open-Ended Review Rule
The only valid review is open-ended over the whole milestone/gate scope. Targeted class verification is necessary during claim verification, but it is not a substitute for a full open-ended review.
When external reviewers find any real P0/P1/P2 issue:
- Verify the exact claim.
- During verification, identify the issue class and count every occurrence of that class across the whole milestone scope.
- Then perform a fresh, unbiased, open-ended review of the entire milestone from scratch. Do not limit this review to the cited finding, the issue class, prior fixes, or prior reviewer rounds.
- Fix or reject every real issue from both the targeted verification and the open-ended review before rerunning external reviewers.
The common failure mode is biased limited review: a reviewer reports "X is wrong", the CTO checks only X-like issues, reruns reviewers, and reviewers then find unrelated Y/Z issues. That turns external reviewers into scouts. Stop and perform the whole-milestone open-ended review before any rerun.
External reviewers are a quality gate, not an implementation strategy. The CTO does the gap analysis, planning, coding, tests, gates, and self-review first. Reviewers then look for what was missed.
Minimal waste is part of correctness. One reviewer round runs six external models. A 19-round gate is roughly 114 model invocations before retries, timeouts, or failed outputs. That is not rigor; it means the CTO used reviewers as a discovery engine. That false framing is forbidden here. The CTO discovers, researches, writes, and self-reviews the stage artifact first; reviewers challenge that completed artifact.
The contract lives in AGENTS.md; this skill is the runtime pattern. If they
disagree, AGENTS.md wins.
Reviewer Set
Run these six reviewers for gate reviews:
| Reviewer | Invocation |
|---|---|
glm |
timeout 1800 opencode run -m "llm-netdata-cloud/glm-5.2-max" --variant max --agent code-reviewer "PROMPT" |
minimax |
timeout 1800 opencode run -m "llm-netdata-cloud/minimax-m3-coder" --variant max --agent code-reviewer "PROMPT" |
kimi |
timeout 1800 opencode run -m "llm-netdata-cloud/kimi-k2.7-code" --variant max --agent code-reviewer "PROMPT" |
mimo |
timeout 1800 opencode run -m "llm-netdata-cloud/mimo-v2.5-pro" --variant max --agent code-reviewer "PROMPT" |
deepseek |
timeout 1800 opencode run -m "llm-netdata-cloud/deepseek-v4-pro" --variant max --agent code-reviewer "PROMPT" |
qwen |
timeout 1800 opencode run -m "llm-netdata-cloud/qwen3.7-plus" --variant max --agent code-reviewer "PROMPT" |
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 · 471 lines · 70 tokens per session scan A 189bb4248762
project-second-opinions is a skill published in the GitHub repository netdata/ai-viewer (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 4,530 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
migrate-state-management
Migrate Redux or React Context to the correct state option (React Query for server state, nuqs for URL/shareable state, Zustand for global client state). Use when refactoring away from Redux/Context, moving state to the right store, or when the user asks to migrate state management.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
opentelemetry-net-instrumentation
Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
repo-health-sweep
Bi-weekly pass over the whole evlog repository, not just the agent's own surface. Checks every SKILL.md against the real package surface, the docs tree for stale or self-contradictory pages, the repo's own conventions, and the examples against the current API. Load this when the repo-health-sweep schedule fires, or…
codebase-review
Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.