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 LegalQuants/lq-skills --skill case-file-analyzergit clone --depth 1 https://github.com/LegalQuants/lq-skillsWrote 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/legalquants/lq-skills/case-file-analyzer)<a href="https://agentmods.dev/skills/legalquants/lq-skills/case-file-analyzer"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/case-file-analyzer/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/legalquants/lq-skills/case-file-analyzer"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/case-file-analyzer.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 | $0.00061 | $0.02736 |
| Opus 5 | $0.00030 | $0.01368 |
| Sonnet 5 | $0.00012 | $0.00547 |
| Haiku 4.5 | $0.00006 | $0.00274 |
Grade A, and why
case-file-analyzer 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 12d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stateless Case File Analyzer (Ralph Loop Edition)
⚠️ Proof of concept. This is an open-source demo showing how far agentic case file revision can be implemented efficiently. It is not a finished ready-to-use product.
| Attribute | Value |
|---|---|
| Description | Stateless, autonomous AI agent utilizing the R.A.L.P.H. pattern for adversarial and structured case file analysis. Runs parallel verification for factual claims, logic, and completeness across massive document directories. |
| Author | Attorney Dennis G. Jansen / J-Law.de |
| Version | 3.1.0 |
| Jurisdiction | Agnostic |
| Last Reviewed | 2026-05 |
| Last Reviewed By | LegalQuants (QA remediation) |
| Tags | legal-analysis, quality-control, multi-agent, verification, adversarial, certificate, ralph-loop |
What it does & What it doesn't do
What it does:
- Granular Extraction: Scans case files one by one in isolated executions, extracting facts, claims, and legal views into standardized XML metadata.
- Context Preservation: Uses the R.A.L.P.H. pattern (stateless disk-I/O loops) to prevent "Lost in the Middle" context degradation on massive case files.
- Adversarial Synthesis: Acts as a quality gate, reviewing fully prepared metadata across all files to synthesize a cohesive legal perspective and timeline.
What it doesn't do:
- No Memory: It does not remember past conversational context. If it is not written to
PRD.mdor a state file, it does not exist. - No Legal Advice: It does not replace licensed human counsel. It is a structural decomposition and synthesis tool.
- No Conversational Filler: It does not chat. It reads instructions, executes a single task, writes to disk, and terminates.
The 3-Step Execution Process
When triggered via "scan case files", the agent orchestrator must execute the following sequence via the R.A.L.P.H. loop:
- Step 1: Granular Review & Metadata Extraction Review each file individually. Create metadata, tags, and review results via the Ralphing Skill, unless the existing review on the disk is already complete and sufficient. Output using the Individual Summary Template.
- Step 2: Perspective Analysis Review the fully prepared review results and metadata from Step 1 across all files under a specific, user-defined legal perspective (e.g., procedural errors, substantive validity, evidentiary contradictions).
- Step 3: Holistic Synthesis Synthesize the conclusion and results across all relevant files into a final case report, utilizing the Synthesis Template.
What ships with it
5 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.
- 12d ago First seen · 122 lines · 61 tokens per session scan A 10ec726da50d
case-file-analyzer is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 2,736 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
regulatory-knowledge
A reference guide to trading rules and regulatory constraints across markets including mainland China, Hong Kong, the United States, and crypto markets.
lifecycle-messaging
Email/SMS lifecycle and deliverability framework for SMB Product-Builder products that send transactional or lifecycle messages (booking reminders, CRM sequences, receipts, win-back). Codifies provider selection (Resend/Postmark/Twilio/SendGrid), domain auth (SPF/DKIM/DMARC), consent and compliance (TCPA, CAN-SPAM…
civic-publish-gate
Run deterministic source, citation, freshness, privacy, meeting-certainty, accessibility, correction-state, and human-approval checks before civic publication.
editorial-correction-review
Review a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence.
swcr-register
Software copyright registration materials generated from a code repository or folder, including source-code documents, a user manual, and application information. It can also help with the online application.
bgm-library
A tool for finding and downloading royalty-free background music from ccMixter, a music-sharing site. It supports limited Creative Commons licences and creates the required creator-credit text.