What is opencaselaw-maintenance?

A conservative maintenance guide for OpenCaseLaw, a project that collects and serves legal case law. It directs an agent through health checks, scraper and collection-completeness checks, safe fixes, and deployment decisions.

It helps assess production health, find missing or incorrect legal records, improve reliability, run offline and full verification checks, and record maintenance outcomes.

It helps maintainers choose one evidence-based action at a time and stops for human review when a change could be risky.

How jonashertner/opencaselaw configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to jonashertner/opencaselaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jonashertner/opencaselaw/main/.agents/skills/opencaselaw-maintenance/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/jonashertner/opencaselaw

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jonashertner/opencaselaw/opencaselaw-maintenance/github.svg)](https://agentmods.dev/skills/jonashertner/opencaselaw/opencaselaw-maintenance)

Your own site

<a href="https://agentmods.dev/skills/jonashertner/opencaselaw/opencaselaw-maintenance"><img src="https://agentmods.dev/badge/skills/jonashertner/opencaselaw/opencaselaw-maintenance/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jonashertner/opencaselaw/opencaselaw-maintenance"><img src="https://agentmods.dev/badge/skills/jonashertner/opencaselaw/opencaselaw-maintenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 558 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00062	$0.00558
Opus 5	$0.00031	$0.00279
Sonnet 5	$0.00012	$0.00112
Haiku 4.5	$0.00006	$0.00056

Measured yesterday against content hash 36e7485c6a78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

opencaselaw-maintenance 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.

.agents/skills/opencaselaw-maintenance/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCaseLaw Maintenance

This skill turns Codex into a conservative OpenCaseLaw maintenance agent. Its job is to find one high-value safe action, verify it, record it, and escalate anything risky.

Workflow

Bootstrap by reading CLAUDE.md, the external memory index, relevant memory notes, TECHNICAL_OVERVIEW.txt, and the private maintenance log under OPENCASELAW_PRIVATE_ROOT when set. Otherwise the maintenance scripts resolve opencaselaw-internal beside the primary checkout, including from a linked worktree.
Run or inspect a deterministic assessment before deciding:
```
python3 scripts/agent_assess.py --json
```
Use --no-network when tests or sandbox policy require an offline run.
Read ops/autonomy-policy.json before edits. If the intended path is proposal_only or always_human, write a proposal under the private maintenance workspace's docs/agent-loop/proposals/ directory and stop.
Pick exactly one action by mission priority: completeness, accuracy, reliability, then user value.
Prefer confirm-health, quantify, and monitor fixes over risky behavior changes. Never use entscheidsuche as a scraper data path.
For code, add or update offline tests first when practical.
Verify with targeted tests plus make test and make verify-offline before claiming a fix is ready to commit or deploy.

Record the outcome:

python3 scripts/agent_record.py --action "..." --evidence "..." --outcome "..."

Deployment Guard

Before any autonomous deploy candidate, run:

python3 scripts/agent_safe_deploy.py --json

Only proceed when it returns allowed: true, the user has explicitly approved the commit/push/deploy, and the required verification commands have passed. Pipeline-gated or human-required paths are proposal-only regardless of test status.

Output Discipline

When producing an automated decision for a runner, conform to schemas/agent_decision.schema.json. A safe decision contains the selected mission priority, the exact files to touch, the verification commands, whether deployment is allowed, and any human escalation.

Read the full file on GitHub · 61 lines

Changes

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 · +2 lines 36e7485c6a78
10d ago First seen · 59 lines · 62 tokens per session scan A 6be4feef58ad

Subscribe to this mod's changes

opencaselaw-maintenance is a skill published in the GitHub repository jonashertner/opencaselaw (62 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 558 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.

DevOps and cloud Legal and compliance ai-agents caselaw citation-graph dataset legal-data legal-research

legaltech-expert

Expert in legal technology: contract lifecycle management, e-discovery, AI-assisted legal research, case and matter management, document automation, and compliance tooling. Use when the user mentions legal case or matter management, e-discovery and legal holds, CLM or contract review and obligation tracking, legal…

personamanagmentlayer/pcl · 74 tokens

legalize-kr

Use this skill when working with Legalize-KR public Korean legal data, including laws, court precedents, administrative rules, and local ordinances. It guides agents to choose between legalize-cli, the local stdio legalize MCP server, git clone workflows, and direct GitHub access for search, retrieval, article lookup…

legalize-kr/agent-skills · 86 tokens

opencaselaw: Skill for Claude Code