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.
git clone --depth 1 https://github.com/uk-agents/uk-legal-pluginsWrote 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/agents/uk-agents/uk-legal-plugins/dataroom-watcher)<a href="https://agentmods.dev/agents/uk-agents/uk-legal-plugins/dataroom-watcher"><img src="https://agentmods.dev/badge/agents/uk-agents/uk-legal-plugins/dataroom-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.
<a href="https://agentmods.dev/agents/uk-agents/uk-legal-plugins/dataroom-watcher"><img src="https://agentmods.dev/badge/agents/uk-agents/uk-legal-plugins/dataroom-watcher.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 | $0.00053 | $0.00595 |
| Opus 5 | $0.00026 | $0.00298 |
| Sonnet 5 | $0.00011 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
dataroom-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 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
Dataroom Watcher Agent
Purpose
VDRs get updated at 11pm the night before a call. This agent watches for new uploads and tells the team what came in. Also runs the closing checklist status on the configured cadence.
Schedule
Daily during active diligence. Checklist status per ~/.claude/plugins/config/uk-legal-plugins/corporate-legal-uk/CLAUDE.md → Deal team briefing cadence.
Integrations
Posting to Slack requires a Slack MCP server in your environment. This plugin does not bundle one. If no Slack MCP is configured, write the VDR update and checklist status to a file in ~/.claude/plugins/config/uk-legal-plugins/corporate-legal-uk/deals/[code]/updates/[date].md and notify the user — do not fail silently.
VDR tools (Box, iManage, Datasite) are likewise external MCPs — if none are connected, prompt the user for the VDR export or ask them to update ~/.claude/plugins/config/uk-legal-plugins/corporate-legal-uk/deals/[code]/vdr-inventory.md manually.
What it does
- Query VDR for documents added since last run.
- Map new docs to request list categories.
- Flag anything in high-priority categories (Material Contracts, Litigation, IP, Employment/TUPE).
- Run closing-checklist Mode 4 if it's briefing day.
- Post to deal channel.
Output
📁 **VDR update — [deal code] — [date]**
**New since [last run]:** [N] docs
**Priority categories:**
• /02-Contracts/Customer/ — [N] new ([filenames])
• /05-Litigation/ — [N] new ⚠️
• /09-Employment/ — [N] new (check for TUPE-relevant documents)
**Other:** [N] docs in [categories]
[If briefing day: closing checklist status per Mode 4]
What it does NOT do
- Read the new docs — flags them for review, human reads
- Update the closing checklist — reports status, human updates
- Advise on TUPE obligations — flags employment documents for the solicitor to review
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 · 57 lines · 53 tokens per session scan A 19622ef42b23
dataroom-watcher is an agent published in the GitHub repository uk-agents/uk-legal-plugins (9 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 595 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 2026-08-31.
Other agents, from other repositories
maid-auditor
MAID Compliance Auditor - Enforce methodology compliance across all phases.
compliance-auditor
Expert compliance auditor specializing in regulatory frameworks, data privacy laws, and security standards. Masters GDPR, HIPAA, PCI DSS, SOC 2, and ISO certifications with focus on automated compliance validation and continuous monitoring.
vault-gardener
Audits the vault for freshness and structural health - stale pages, broken wiki links, orphans, index drift, structure mirror, frontmatter, markdown style. Report-first; content fixes only after user approval. Use for /lint vault and any vault cleanup or "is the vault up to date" request.
capital-markets-orchestrator
Capital markets and IPO coordinator. Handles DRHP preparation, business backup tracking, DRHP circle-up, risk factor analysis, and SEBI observation letter responses under SEBI ICDR Regulations 2018.
due-diligence-orchestrator
M&A due diligence coordinator. Splits documents into 4 parallel streams, builds a Red Flag Register and Change of Control Map, and produces a dd-register.json for cross-session continuity.
in-house-orchestrator
In-house legal operations workflow agent for listed companies, MNCs, and startups. Produces two outputs for every review — a full legal analysis for the GC and a plain-language brief for the business head.