docket-watcher

docket-watcher is an agent for Claude Code from anthropics/claude-for-legal. It costs 73 tokens per session (1,220 once invoked), scanned A, original, Apache-2.0.

A scheduled court-docket watcher for active legal matters. A court docket is the court's running record of filings, orders, and other case events.

In plain words
What is it for?
Checking active matters on a schedule, flagging new filings, identifying candidate deadlines, and producing a docket status report.
Why use it?
New docket entries can create deadlines while a team is working elsewhere. It surfaces new filings, estimates possible deadlines, and compares them with each matter's history and open work, but does not replace a docketing system or lawyer review.

Agent for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the litigation-legal plugin — 16 skills, 1 agent shipped together

Good fit Checking active matters on a schedule, flagging new filings, identifying candidate deadlines, and producing a docket status report.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/anthropics/claude-for-legal/docket-watcher
About the project

Claude for Legal is a collection of AI agents, skills, and data connectors for legal work such as commercial, privacy, employment, litigation, regulatory, and intellectual-property matters. Lawyers and legal teams use it through Claude Cowork, Claude Code, or the Claude Managed Agents API, with attorney review required for every output. The catalogue entries are its workflow plugins, skills, agents, and connectors.

anthropics/claude-for-legal · 9,529 stars · on GitHub

Install

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.

Clone the repo
git clone --depth 1 https://github.com/anthropics/claude-for-legal

Made for: Claude Code.

Or install litigation-legal, the plugin that ships this one along with the rest of its 16 skills, 1 agent.

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.

agentmods badge for docket-watcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/anthropics/claude-for-legal/docket-watcher/github.svg)](https://agentmods.dev/agents/anthropics/claude-for-legal/docket-watcher)
Your own site
<a href="https://agentmods.dev/agents/anthropics/claude-for-legal/docket-watcher"><img src="https://agentmods.dev/badge/agents/anthropics/claude-for-legal/docket-watcher/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.

agentmods 80×15 button for docket-watcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/anthropics/claude-for-legal/docket-watcher"><img src="https://agentmods.dev/badge/agents/anthropics/claude-for-legal/docket-watcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,220 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.01220
Opus 5.5 $0.00029 $0.00488
Sonnet 5 $0.00015 $0.00244
Haiku 4.5 $0.00007 $0.00122

Measured 3d ago against content hash a96f58b14158, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-26, from the pricing page.

Security

Grade A, and why

docket-watcher 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 3d 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.

litigation-legal/agents/docket-watcher.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docket Watcher Agent

Purpose

The docket moves whether or not you're watching it. New filings, orders, and minute entries land while you're working on something else, and every one of them can start a clock. This agent checks every active matter's docket on a schedule, flags what's new, computes candidate deadlines from the filing types, and cross-references against the matter's history and open deliverables.

It does not replace a docketing system and it does not replace the lawyer who reads the rule. It surfaces leads so neither gets surprised.

Schedule

Per ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md → Landscape → Frequent fora and the per-matter cadence in ~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml.

  • Default: weekly sweep of every matter in _log.yaml with status not in closed.
  • Daily: matters with an upcoming hearing inside 14 days, matters in trial or late discovery, or any matter flagged risk: critical.

The schedule is the floor, not the ceiling. Big filings land on Friday afternoons.

What it does

  1. Read ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md for house style, escalation rules, and the frequent-fora list. Read ~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml for the active portfolio — per-matter id, jurisdiction, docket identifier, last-checked timestamp, and open deliverables.
  2. For each active matter with a docket identifier, pull new entries since the last check via Trellis (state trial courts) or CourtListener / PACER (federal courts). Capture filing date, filing type, title, filer, docket entry number, and document link.
  3. Map filing types to candidate deadline rules. Federal rules (FRCP, FRAP, local rules where known) are straightforward; state trial-court practice varies; standing orders override local rules; some judges set every schedule by individual case management order. Flag every computed deadline as a lead that requires human verification.
  4. Cross-reference against each matter's history.md and open deliverables. Surface posture changes (motion decided, status conference set, discovery cutoff ordered, trial date moved) and deliverables that slipped past their internal deadline.
  5. Write ./out/docket-report-<date>.md with per-matter sections and a machine-readable ./out/deadlines.yaml the docketing system can ingest. Update each matter's history.md with a dated entry noting what was pulled. Post a summary to Slack per the escalation channel in CLAUDE.md.

Read the full file on GitHub · 71 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.

  1. 3d ago First seen · 71 lines · 73 tokens per session scan A a96f58b14158

Subscribe to this mod's changes

docket-watcher is an agent published in the GitHub repository anthropics/claude-for-legal (9,529 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 1,220 once invoked, about $0.0003 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 2026-09-23.