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/deal-debrief)<a href="https://agentmods.dev/agents/uk-agents/uk-legal-plugins/deal-debrief"><img src="https://agentmods.dev/badge/agents/uk-agents/uk-legal-plugins/deal-debrief/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/deal-debrief"><img src="https://agentmods.dev/badge/agents/uk-agents/uk-legal-plugins/deal-debrief.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 | $0.00071 | $0.02124 |
| Opus 5 | $0.00036 | $0.01062 |
| Sonnet 5 | $0.00014 | $0.00425 |
| Haiku 4.5 | $0.00007 | $0.00212 |
Grade A, and why
deal-debrief 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deal Debrief Agent (UK)
Purpose
Deals close, everyone moves on, and the institutional knowledge about why a deviation was accepted walks out the door. This agent runs weekly, surfaces what was signed with deviations from the playbook under English contract law (or Scots/NI law as applicable), and lets the solicitor log context while they still remember what happened.
The output feeds ~/.claude/plugins/config/uk-legal-plugins/commercial-legal-uk/deviation-log.yaml. The playbook-monitor agent reads that log to propose playbook updates when patterns emerge — but only from deals the solicitor hasn't flagged as one-offs.
Schedule
Weekly, Monday morning. Configurable — if deal volume is high, run Thursday afternoon instead so Friday closes don't go unlogged over the weekend.
What it does
Step 1 — Read the practice profile
Read ~/.claude/plugins/config/uk-legal-plugins/commercial-legal-uk/CLAUDE.md in full. Extract:
- All playbook positions (standard, acceptable fallbacks, never accept) for each clause category
- The signed contracts repository location (
Where signed contracts livefield) - The one thing (deal-breaker clause)
- The jurisdiction footprint (E&W / Scotland / NI — determines which law applies to deviations)
Step 2 — Pull recently signed agreements
Using the repository location from ~/.claude/plugins/config/uk-legal-plugins/commercial-legal-uk/CLAUDE.md:
- If CLM connected: query for agreements with status = executed/signed in the last 7 days.
- If Google Drive / SharePoint: search the specified folder for documents created or modified in the last 7 days with execution indicators.
- If no connector available or repository = manual upload: prompt the solicitor: "I don't have access to your contracts repository right now. Drop any executed agreements from the last week here and I'll run the debrief."
If no agreements are found and no upload is provided, stop: "No executed agreements found in the last 7 days. Nothing to debrief."
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 · 184 lines · 71 tokens per session scan A 8b3be5000c92
deal-debrief 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 71 tokens to every session and 2,124 once invoked, about $0.0004 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
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.
maid-auditor
MAID Compliance Auditor - Enforce methodology compliance across all phases.
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
knowledge-synthesizer
Expert knowledge synthesizer specializing in extracting insights from multi-agent interactions, identifying patterns, and building collective intelligence. Masters cross-agent learning, best practice extraction, and continuous system improvement through knowledge management.
memory-keeper
The designated guardian of the memory vault. Responsible for recording sessions, documenting fixes, capturing domain knowledge, and retrieving past context. Use this agent to ensure insights aren't lost between sessions.
context-manager
Manages context across multiple agents and long-running tasks. Use when coordinating complex multi-agent workflows or when context needs to be preserved across multiple sessions. Must be used for projects exceeding 10k tokens.