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 JHostalek/dotclaude --skill judgegit clone --depth 1 https://github.com/JHostalek/dotclaudeWrote 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/jhostalek/dotclaude/judge)<a href="https://agentmods.dev/skills/jhostalek/dotclaude/judge"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/judge.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 5.1 | $0.00017 | $0.00292 |
| Opus 5 | $0.00009 | $0.00146 |
| Sonnet 5 | $0.00003 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
judge 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.
What it actually says
Review $ARGUMENTS, or the latest substantive work when omitted. Infer scope from the conversation and relevant files; ask only if ambiguity would materially change the review.
Delegate to one independent, read-only reviewer with a clean context: the requested outcome, constraints, subject, relevant files, stack, and project conventions. Do not provide your verdict or preferred critique. Add reviewers only for materially distinct expertise. If delegation is unavailable, disclose that limitation; do not call self-review independent.
Ask the reviewer to assess domain fitness, architectural choices, proportionality, and fundamentally different ways to achieve the outcome. Distinguish justified deviations from missed constraints; compare simplicity against real requirements and account for the adoption costs of alternatives. Feature necessity is a separate lens available through /audit necessity, not an automatic additional pass.
Retain findings supported by specific evidence, an actionable alternative, and its costs. Distinguish defects, valid trade-offs, and preferences. Remove claims that misread constraints or lack evidence; preserve meaningful disagreements if multiple reviewers were used.
Report a clear recommendation and its rationale, validated strengths, findings by importance, and the single most valuable change, if any. Identify missing evidence and reviewer limitations. Stop after the report; implement only when asked.
What ships with it
1 file 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.
- yesterday Changed · -50 lines · -6 tokens per session fb5f410b8a08
- 8d ago First seen · 67 lines · 23 tokens per session scan A aaa05fd9f4a4
judge is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 2d ago), licensed CC0-1.0. It adds 17 tokens to every session and 292 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
memstack-development-code-reviewer
Use this skill when the user says 'review code', 'code review', 'check my code', 'audit this', 'review PR', 'review changes', 'what's wrong with this', or is requesting a structured review of code quality, security, performance, or maintainability. Do NOT use for refactoring plans or test generation.
ln-11-plan-reviewer
Reviews an implementation plan against repository evidence before execution; identifies missing decisions and risks. Not for completed-code review.
ln-12-delivery-reviewer
Reviews a completed change for regressions, unmet acceptance, and release risks. Not for whole-codebase audits or repairs.
ln-21-documentation-auditor
Audits documentation and comments for trustworthy claims, coverage, and discoverability. Not for code, test, or architecture audits.
ln-22-codebase-auditor
Audits cross-cutting code health, security, delivery, and maintainability when no specialist audit is primary. Not for a single delivery review.
ln-25-persistence-auditor
Audits queries, transactions, data-path costs, and persistence resource lifetimes. Not for general performance tuning.