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 Juror-AI/juror --skill juror-reviewgit clone --depth 1 https://github.com/Juror-AI/jurorWrote 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/juror-ai/juror/juror-review)<a href="https://agentmods.dev/skills/juror-ai/juror/juror-review"><img src="https://agentmods.dev/badge/skills/juror-ai/juror/juror-review/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/juror-ai/juror/juror-review"><img src="https://agentmods.dev/badge/skills/juror-ai/juror/juror-review.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 | $0.00028 | $0.00504 |
| Opus 5.5 | $0.00011 | $0.00202 |
| Sonnet 5.5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
juror-review 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 2mo 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Juror Cloud review workflow
Juror is a hosted, multi-model pull-request review service. This plugin does not inspect local repositories, checkouts, raw diffs, artifacts, screenshots, provider credentials, or model prompt text.
Select the workspace first
- Call
juror_list_workspacesbefore any scoped tool. - If exactly one workspace is returned, use its
idasworkspace_id. - If more than one workspace is returned, ask the user to choose. Never guess from repository names or previous conversations.
Safe inspection
Use juror_overview, juror_list_repositories, juror_list_findings, juror_list_runs, and juror_get_run for concise triage. Findings are model-assisted signals, not proof that a change is incorrect. Summarize severity, agreement, status, and next verification steps without inventing source context.
Only call juror_get_finding_detail after the user identifies a particular finding or asks for the body of a particular finding. Do not request finding bodies in bulk and do not restate sensitive detail more broadly than needed.
Starting or rerunning a review
These are hosted Juror Cloud reviews and may use workspace review capacity. They must not be run alongside a Juror GitHub Action in the same repository.
- Call
juror_prepare_reviewfor an open pull request, orjuror_prepare_rerunfor an existing hosted review. - Present the returned repository, PR number, exact SHA, and capacity/billing warning to the user.
- Ask a clear confirmation question. Do not treat silence, a generic request to “continue,” or an earlier confirmation as confirmation for a changed SHA.
- Only after the user explicitly confirms, call
juror_start_revieworjuror_rerun_reviewwith the matching five-minute intent. - Report the new run ID and Juror Cloud link. If the intent expired, was replayed, or the PR SHA changed, prepare again and request a new confirmation.
Never use Juror to cancel runs, alter findings, change billing or workspace settings, access arbitrary GitHub repositories, or run QA. If the user asks for any of those, explain that this plugin does not provide that capability.
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.
- 2mo ago First seen · 33 lines · 28 tokens per session scan A 3daa598ec839
juror-review is a skill published in the GitHub repository Juror-AI/juror (117 stars, last pushed 24d ago), licensed MIT. It adds 28 tokens to every session and 504 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
logic-review
Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Trigger when a user shares code and suspects something is wrong without naming a concrete failure — phrases like "review this", "does this look right", "check this function", "audit this…
logic-fix-all
Autonomous repository-wide audit-and-fix pipeline: health → review → locate/explain → fix → diff-verify → iterate until clean. Starts with a mandatory consent prompt (token-intensive); after consent runs hands-free. Trigger when the user wants ALL logic issues found and fixed — "fix everything", "fix all logic…
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
run-iteration-eval
Run the Logic-Lens content-eval pipeline for one iteration and produce a scored summary.json — use to measure a skill change. Wraps scripts/run-content-evals.sh (runner, costs tokens) and scripts/grade-iteration.py (grader, free, re-runnable). ALWAYS sync the plugin cache first. Use when the user wants to "run the…
argot-setup
Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…
new-skill
Scaffold a new logic- skill in the Logic-Lens repo and wire it into every place a skill must be registered, so no step is missed. Use when adding a seventh (or later) skill to Logic-Lens.