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 monkilabs/opencastle --skill panel-majority-votegit clone --depth 1 https://github.com/monkilabs/opencastleWrote 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/monkilabs/opencastle/panel-majority-vote)<a href="https://agentmods.dev/skills/monkilabs/opencastle/panel-majority-vote"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/panel-majority-vote/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/monkilabs/opencastle/panel-majority-vote"><img src="https://agentmods.dev/badge/skills/monkilabs/opencastle/panel-majority-vote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.00401 |
| Opus 5.5 | $0.00027 | $0.00160 |
| Sonnet 5.5 | $0.00013 | $0.00080 |
| Haiku 4.5 | $0.00007 | $0.00040 |
Grade A, and why
panel-majority-vote 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 15d 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.
What it actually says
Panel Majority Vote
For changes where a missed defect is expensive: auth and permissions, payments, data migrations, anything that deletes data. Everything else gets one reviewer (fast-review).
-
Ask one question — "Is this change safe to merge?" — with what answers it: the diff, the acceptance criteria, the test results, the files involved.
-
Three reviewers, in parallel, in isolation. Three sub-agents dispatched as the Reviewer with the identical prompt; none sees another's answer or the conversation. Each answers in exactly these sections:
VERDICT: PASS | BLOCK MUST-FIX: <defects that block, each with file:line> SHOULD-FIX: <improvements> QUESTIONS: <what the reviewer could not decide>Where it can, a reviewer exercises the change — runs the entrypoint, the migration, the request — rather than only reading the diff.
-
Count. PASS when two or three say PASS; otherwise BLOCK.
-
Fix the union. Every MUST-FIX any reviewer raised is fixed, or answered with evidence: one reviewer's catch counts, whatever the vote. Mark each with how many raised it (
2/3). -
On BLOCK, change the work and run the panel again with the same question — never reword it to get a PASS. Blocked a second time: stop, and tell the user what blocks it.
Report the verdict, the tally, and each MUST-FIX with what was done about it.
What ships with it
2 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.
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.
- 15d ago Changed · -30 lines · +19 tokens per session 7b183223a851
- 17d ago Changed · +4 tokens per session 5fd24dd55b74
- 1mo ago First seen · 56 lines · 44 tokens per session scan A c861d7b87285
panel-majority-vote is a skill published in the GitHub repository monkilabs/opencastle (80 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 401 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 2026-09-03.
Other skills, from other repositories
simplify-skill
Universal, high-intelligence ecosystem-aware code simplification skill. Detects ANY programming language, framework, package manager, and exact version in use. Consults modern documentation via web search and Context7, and orchestrates specialized sub-agents applying strict, universal engineering heuristics.
code-review
Use when code has been written and needs validation before committing, or when the user asks for a code review or security check.
gentle-ai-judgment-day
Trigger: judgment day, judgement day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.
gentle-ai-work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
commit
A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.
code-reviewer
Staff-engineer-level code review delivering 10 prioritized actionable findings across architecture, security, performance, and maintainability.