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 conectlens/lenserfight --skill legal-review-comparisongit clone --depth 1 https://github.com/conectlens/lenserfightWrote 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/conectlens/lenserfight/legal-review-comparison)<a href="https://agentmods.dev/skills/conectlens/lenserfight/legal-review-comparison"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/legal-review-comparison/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/conectlens/lenserfight/legal-review-comparison"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/legal-review-comparison.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 | $0.00024 | $0.00249 |
| Opus 5 | $0.00012 | $0.00125 |
| Sonnet 5 | $0.00005 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
legal-review-comparison 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 9d 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
Legal Review — Claude vs Gemini
This battle runs the legal-contract-reviewer lens on the same contract text through Claude Sonnet 4.6 and Gemini 2.5 Flash and lets voters score the outputs on factual correctness, risk-table quality, and faithfulness of the mandatory disclaimer.
Why this exists
Model selection for legal-adjacent tasks is high stakes. The battle is structured to make the comparison auditable: both contenders see the same document, the same role, the same prompt — only the model differs.
Mandatory disclaimer
Every output rendered by this battle MUST carry the legal disclaimer. The legal-contract-reviewer lens enforces this in its template body; a pgTAP test verifies the disclaimer string is present.
Safety guardrails
- Battles tagged
legalcannot be configured withvoter_eligibility = 'ai_judge'alone — they require either human voters orhybridvoting. - Battle results never describe a model as "best for legal" — only "preferred on this rubric for this document."
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.
- 9d ago First seen · 22 lines · 24 tokens per session scan A f056996cfbbe
legal-review-comparison is a skill published in the GitHub repository conectlens/lenserfight (18 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 249 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 2026-09-03.
Other skills, from other repositories
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
ai-policy-generator
AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.
compliance-engineering
SOC2, HIPAA, GDPR, PCI-DSS, FedRAMP compliance implementation in code. Audit logging, data encryption, access controls, privacy by design, and regulatory requirement mapping. Use when implementing compliance controls, preparing for audits, or building privacy-compliant systems.
anonymization-alternative
Evaluates anonymization as a retention alternative under GDPR Recital 26, applying the WP29 Opinion 05/2014 techniques including randomization and generalization. Validates anonymization effectiveness using k-anonymity, l-diversity, and t-closeness metrics. Activate for anonymization, de-identification, k-anonymity…
bcr-establishment
Guides development and approval of Binding Corporate Rules under GDPR Article 47 for intra-group international data transfers. Covers Art. 47(2)(a)-(n) content requirements, BCR approval process with lead supervisory authority, and WP256/WP257 referentials. Keywords: BCR, binding corporate rules, intra-group…
ai-training-data-class
Classifies sensitive data in AI/ML training datasets including bias detection for Art. 9 categories, data card documentation, provenance tracking, and consent verification for model training. Keywords: AI training data, ML dataset, bias detection, data card, model training, Art 9, consent, GDPR AI.